Upload stronger Qwen3-4B SQL model
Browse files- .gitattributes +1 -0
- README.md +75 -0
- all_results.json +13 -0
- chat_template.jinja +85 -0
- config.json +71 -0
- eval_results.json +7 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +30 -0
- train_results.json +9 -0
- trainer_log.jsonl +342 -0
- trainer_state.json +2443 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen3-4B-Base
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: train_run_06_qwen3_4b_formal
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# train_run_06_qwen3_4b_formal
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the sql_train dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2490
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-06
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_steps: 300
|
| 49 |
+
- num_epochs: 4.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 0.1851 | 0.3044 | 500 | 0.2562 |
|
| 56 |
+
| 0.1331 | 0.6088 | 1000 | 0.2490 |
|
| 57 |
+
| 0.1293 | 0.9132 | 1500 | 0.2554 |
|
| 58 |
+
| 0.0885 | 1.2174 | 2000 | 0.2661 |
|
| 59 |
+
| 0.0830 | 1.5218 | 2500 | 0.2772 |
|
| 60 |
+
| 0.0843 | 1.8262 | 3000 | 0.2774 |
|
| 61 |
+
| 0.0443 | 2.1303 | 3500 | 0.3124 |
|
| 62 |
+
| 0.0402 | 2.4347 | 4000 | 0.3158 |
|
| 63 |
+
| 0.0414 | 2.7391 | 4500 | 0.3392 |
|
| 64 |
+
| 0.0178 | 3.0432 | 5000 | 0.3912 |
|
| 65 |
+
| 0.0128 | 3.3476 | 5500 | 0.4340 |
|
| 66 |
+
| 0.0110 | 3.6521 | 6000 | 0.4406 |
|
| 67 |
+
| 0.0109 | 3.9565 | 6500 | 0.4410 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 5.2.0
|
| 73 |
+
- Pytorch 2.9.1+cu130
|
| 74 |
+
- Datasets 4.0.0
|
| 75 |
+
- Tokenizers 0.22.2
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"effective_tokens_per_sec": 1153.798380212981,
|
| 3 |
+
"epoch": 4.0,
|
| 4 |
+
"eval_loss": 0.24901165068149567,
|
| 5 |
+
"eval_runtime": 46.8427,
|
| 6 |
+
"eval_samples_per_second": 18.786,
|
| 7 |
+
"eval_steps_per_second": 18.786,
|
| 8 |
+
"total_flos": 3.545203061907456e+17,
|
| 9 |
+
"train_loss": 0.08566030774240586,
|
| 10 |
+
"train_runtime": 13933.4985,
|
| 11 |
+
"train_samples_per_second": 3.772,
|
| 12 |
+
"train_steps_per_second": 0.472
|
| 13 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 9728,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 32768,
|
| 54 |
+
"max_window_layers": 36,
|
| 55 |
+
"model_type": "qwen3",
|
| 56 |
+
"num_attention_heads": 32,
|
| 57 |
+
"num_hidden_layers": 36,
|
| 58 |
+
"num_key_value_heads": 8,
|
| 59 |
+
"pad_token_id": 151643,
|
| 60 |
+
"rms_norm_eps": 1e-06,
|
| 61 |
+
"rope_parameters": {
|
| 62 |
+
"rope_theta": 1000000,
|
| 63 |
+
"rope_type": "default"
|
| 64 |
+
},
|
| 65 |
+
"sliding_window": null,
|
| 66 |
+
"tie_word_embeddings": true,
|
| 67 |
+
"transformers_version": "5.2.0",
|
| 68 |
+
"use_cache": false,
|
| 69 |
+
"use_sliding_window": false,
|
| 70 |
+
"vocab_size": 151936
|
| 71 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_loss": 0.24901165068149567,
|
| 4 |
+
"eval_runtime": 46.8427,
|
| 5 |
+
"eval_samples_per_second": 18.786,
|
| 6 |
+
"eval_steps_per_second": 18.786
|
| 7 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": false,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"max_new_tokens": 2048,
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"transformers_version": "5.2.0"
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a04a88d8d7c026499bc570cdb42e1cbc0af368cf779b2f1060543a5d47dee1a5
|
| 3 |
+
size 16089918232
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": true,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"padding_side": "right",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null
|
| 30 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"effective_tokens_per_sec": 1153.798380212981,
|
| 3 |
+
"epoch": 4.0,
|
| 4 |
+
"total_flos": 3.545203061907456e+17,
|
| 5 |
+
"train_loss": 0.08566030774240586,
|
| 6 |
+
"train_runtime": 13933.4985,
|
| 7 |
+
"train_samples_per_second": 3.772,
|
| 8 |
+
"train_steps_per_second": 0.472
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,342 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 20, "total_steps": 6572, "loss": 1.119423007965088, "lr": 3.166666666666667e-07, "epoch": 0.0121765601217656, "percentage": 0.3, "elapsed_time": "0:00:54", "remaining_time": "4:54:53"}
|
| 2 |
+
{"current_steps": 40, "total_steps": 6572, "loss": 0.8098940849304199, "lr": 6.5e-07, "epoch": 0.0243531202435312, "percentage": 0.61, "elapsed_time": "0:01:37", "remaining_time": "4:25:19"}
|
| 3 |
+
{"current_steps": 60, "total_steps": 6572, "loss": 0.6310151576995849, "lr": 9.833333333333334e-07, "epoch": 0.0365296803652968, "percentage": 0.91, "elapsed_time": "0:02:14", "remaining_time": "4:03:37"}
|
| 4 |
+
{"current_steps": 80, "total_steps": 6572, "loss": 0.5526751518249512, "lr": 1.3166666666666666e-06, "epoch": 0.0487062404870624, "percentage": 1.22, "elapsed_time": "0:02:51", "remaining_time": "3:52:34"}
|
| 5 |
+
{"current_steps": 100, "total_steps": 6572, "loss": 0.4834024906158447, "lr": 1.6500000000000003e-06, "epoch": 0.060882800608828, "percentage": 1.52, "elapsed_time": "0:03:29", "remaining_time": "3:45:38"}
|
| 6 |
+
{"current_steps": 120, "total_steps": 6572, "loss": 0.44873433113098143, "lr": 1.9833333333333335e-06, "epoch": 0.0730593607305936, "percentage": 1.83, "elapsed_time": "0:04:06", "remaining_time": "3:40:39"}
|
| 7 |
+
{"current_steps": 140, "total_steps": 6572, "loss": 0.38286705017089845, "lr": 2.316666666666667e-06, "epoch": 0.0852359208523592, "percentage": 2.13, "elapsed_time": "0:04:44", "remaining_time": "3:37:42"}
|
| 8 |
+
{"current_steps": 160, "total_steps": 6572, "loss": 0.38465352058410646, "lr": 2.6500000000000005e-06, "epoch": 0.0974124809741248, "percentage": 2.43, "elapsed_time": "0:05:21", "remaining_time": "3:34:27"}
|
| 9 |
+
{"current_steps": 180, "total_steps": 6572, "loss": 0.3305965900421143, "lr": 2.9833333333333337e-06, "epoch": 0.1095890410958904, "percentage": 2.74, "elapsed_time": "0:05:56", "remaining_time": "3:31:11"}
|
| 10 |
+
{"current_steps": 200, "total_steps": 6572, "loss": 0.2875316619873047, "lr": 3.316666666666667e-06, "epoch": 0.121765601217656, "percentage": 3.04, "elapsed_time": "0:06:33", "remaining_time": "3:28:43"}
|
| 11 |
+
{"current_steps": 220, "total_steps": 6572, "loss": 0.3140716075897217, "lr": 3.65e-06, "epoch": 0.1339421613394216, "percentage": 3.35, "elapsed_time": "0:07:09", "remaining_time": "3:26:36"}
|
| 12 |
+
{"current_steps": 240, "total_steps": 6572, "loss": 0.2985520839691162, "lr": 3.983333333333334e-06, "epoch": 0.1461187214611872, "percentage": 3.65, "elapsed_time": "0:07:45", "remaining_time": "3:24:30"}
|
| 13 |
+
{"current_steps": 260, "total_steps": 6572, "loss": 0.2449601411819458, "lr": 4.316666666666667e-06, "epoch": 0.1582952815829528, "percentage": 3.96, "elapsed_time": "0:08:21", "remaining_time": "3:22:57"}
|
| 14 |
+
{"current_steps": 280, "total_steps": 6572, "loss": 0.24566495418548584, "lr": 4.65e-06, "epoch": 0.1704718417047184, "percentage": 4.26, "elapsed_time": "0:08:58", "remaining_time": "3:21:42"}
|
| 15 |
+
{"current_steps": 300, "total_steps": 6572, "loss": 0.20863604545593262, "lr": 4.983333333333334e-06, "epoch": 0.182648401826484, "percentage": 4.56, "elapsed_time": "0:09:34", "remaining_time": "3:20:20"}
|
| 16 |
+
{"current_steps": 320, "total_steps": 6572, "loss": 0.19693111181259154, "lr": 4.9998867856224845e-06, "epoch": 0.1948249619482496, "percentage": 4.87, "elapsed_time": "0:10:11", "remaining_time": "3:19:13"}
|
| 17 |
+
{"current_steps": 340, "total_steps": 6572, "loss": 0.21833207607269287, "lr": 4.999523005839606e-06, "epoch": 0.2070015220700152, "percentage": 5.17, "elapsed_time": "0:10:47", "remaining_time": "3:17:45"}
|
| 18 |
+
{"current_steps": 360, "total_steps": 6572, "loss": 0.2382877826690674, "lr": 4.998908383543311e-06, "epoch": 0.2191780821917808, "percentage": 5.48, "elapsed_time": "0:11:21", "remaining_time": "3:16:06"}
|
| 19 |
+
{"current_steps": 380, "total_steps": 6572, "loss": 0.21118538379669188, "lr": 4.9980429804147276e-06, "epoch": 0.2313546423135464, "percentage": 5.78, "elapsed_time": "0:11:58", "remaining_time": "3:15:01"}
|
| 20 |
+
{"current_steps": 400, "total_steps": 6572, "loss": 0.18367968797683715, "lr": 4.996926883302385e-06, "epoch": 0.243531202435312, "percentage": 6.09, "elapsed_time": "0:12:34", "remaining_time": "3:13:55"}
|
| 21 |
+
{"current_steps": 420, "total_steps": 6572, "loss": 0.22483460903167723, "lr": 4.995560204213496e-06, "epoch": 0.2557077625570776, "percentage": 6.39, "elapsed_time": "0:13:12", "remaining_time": "3:13:22"}
|
| 22 |
+
{"current_steps": 440, "total_steps": 6572, "loss": 0.22673561573028564, "lr": 4.993943080302715e-06, "epoch": 0.2678843226788432, "percentage": 6.7, "elapsed_time": "0:13:50", "remaining_time": "3:12:57"}
|
| 23 |
+
{"current_steps": 460, "total_steps": 6572, "loss": 0.185296630859375, "lr": 4.992075673858379e-06, "epoch": 0.2800608828006088, "percentage": 7.0, "elapsed_time": "0:14:26", "remaining_time": "3:11:55"}
|
| 24 |
+
{"current_steps": 480, "total_steps": 6572, "loss": 0.18437937498092652, "lr": 4.989958172286214e-06, "epoch": 0.2922374429223744, "percentage": 7.3, "elapsed_time": "0:15:04", "remaining_time": "3:11:23"}
|
| 25 |
+
{"current_steps": 500, "total_steps": 6572, "loss": 0.1850834846496582, "lr": 4.987590788090533e-06, "epoch": 0.30441400304414, "percentage": 7.61, "elapsed_time": "0:15:42", "remaining_time": "3:10:48"}
|
| 26 |
+
{"current_steps": 500, "total_steps": 6572, "eval_loss": 0.2562323212623596, "epoch": 0.30441400304414, "percentage": 7.61, "elapsed_time": "0:16:30", "remaining_time": "3:20:23"}
|
| 27 |
+
{"current_steps": 520, "total_steps": 6572, "loss": 0.16346561908721924, "lr": 4.984973758852904e-06, "epoch": 0.3165905631659056, "percentage": 7.91, "elapsed_time": "0:18:27", "remaining_time": "3:34:45"}
|
| 28 |
+
{"current_steps": 540, "total_steps": 6572, "loss": 0.18838067054748536, "lr": 4.982107347208317e-06, "epoch": 0.3287671232876712, "percentage": 8.22, "elapsed_time": "0:19:03", "remaining_time": "3:32:49"}
|
| 29 |
+
{"current_steps": 560, "total_steps": 6572, "loss": 0.177593994140625, "lr": 4.978991840818816e-06, "epoch": 0.3409436834094368, "percentage": 8.52, "elapsed_time": "0:19:40", "remaining_time": "3:31:13"}
|
| 30 |
+
{"current_steps": 580, "total_steps": 6572, "loss": 0.20775914192199707, "lr": 4.975627552344638e-06, "epoch": 0.3531202435312024, "percentage": 8.83, "elapsed_time": "0:20:18", "remaining_time": "3:29:49"}
|
| 31 |
+
{"current_steps": 600, "total_steps": 6572, "loss": 0.16498700380325318, "lr": 4.97201481941283e-06, "epoch": 0.365296803652968, "percentage": 9.13, "elapsed_time": "0:20:55", "remaining_time": "3:28:12"}
|
| 32 |
+
{"current_steps": 620, "total_steps": 6572, "loss": 0.17565951347351075, "lr": 4.968154004583374e-06, "epoch": 0.3774733637747336, "percentage": 9.43, "elapsed_time": "0:21:31", "remaining_time": "3:26:35"}
|
| 33 |
+
{"current_steps": 640, "total_steps": 6572, "loss": 0.16204673051834106, "lr": 4.964045495312794e-06, "epoch": 0.3896499238964992, "percentage": 9.74, "elapsed_time": "0:22:07", "remaining_time": "3:24:59"}
|
| 34 |
+
{"current_steps": 660, "total_steps": 6572, "loss": 0.17068564891815186, "lr": 4.959689703915272e-06, "epoch": 0.4018264840182648, "percentage": 10.04, "elapsed_time": "0:22:42", "remaining_time": "3:23:27"}
|
| 35 |
+
{"current_steps": 680, "total_steps": 6572, "loss": 0.1589680790901184, "lr": 4.95508706752128e-06, "epoch": 0.4140030441400304, "percentage": 10.35, "elapsed_time": "0:23:19", "remaining_time": "3:22:07"}
|
| 36 |
+
{"current_steps": 700, "total_steps": 6572, "loss": 0.17568455934524535, "lr": 4.9502380480337e-06, "epoch": 0.426179604261796, "percentage": 10.65, "elapsed_time": "0:23:56", "remaining_time": "3:20:51"}
|
| 37 |
+
{"current_steps": 720, "total_steps": 6572, "loss": 0.16204804182052612, "lr": 4.9451431320814715e-06, "epoch": 0.4383561643835616, "percentage": 10.96, "elapsed_time": "0:24:33", "remaining_time": "3:19:40"}
|
| 38 |
+
{"current_steps": 740, "total_steps": 6572, "loss": 0.16562143564224244, "lr": 4.939802830970762e-06, "epoch": 0.4505327245053272, "percentage": 11.26, "elapsed_time": "0:25:10", "remaining_time": "3:18:26"}
|
| 39 |
+
{"current_steps": 760, "total_steps": 6572, "loss": 0.17697544097900392, "lr": 4.934217680633646e-06, "epoch": 0.4627092846270928, "percentage": 11.56, "elapsed_time": "0:25:46", "remaining_time": "3:17:03"}
|
| 40 |
+
{"current_steps": 780, "total_steps": 6572, "loss": 0.1649466037750244, "lr": 4.928388241574327e-06, "epoch": 0.4748858447488584, "percentage": 11.87, "elapsed_time": "0:26:23", "remaining_time": "3:15:55"}
|
| 41 |
+
{"current_steps": 800, "total_steps": 6572, "loss": 0.1602837324142456, "lr": 4.922315098812883e-06, "epoch": 0.487062404870624, "percentage": 12.17, "elapsed_time": "0:26:59", "remaining_time": "3:14:43"}
|
| 42 |
+
{"current_steps": 820, "total_steps": 6572, "loss": 0.142719042301178, "lr": 4.9159988618265585e-06, "epoch": 0.4992389649923896, "percentage": 12.48, "elapsed_time": "0:27:36", "remaining_time": "3:13:37"}
|
| 43 |
+
{"current_steps": 840, "total_steps": 6572, "loss": 0.14508233070373536, "lr": 4.9094401644886e-06, "epoch": 0.5114155251141552, "percentage": 12.78, "elapsed_time": "0:28:12", "remaining_time": "3:12:31"}
|
| 44 |
+
{"current_steps": 860, "total_steps": 6572, "loss": 0.1821539044380188, "lr": 4.902639665004641e-06, "epoch": 0.5235920852359208, "percentage": 13.09, "elapsed_time": "0:28:49", "remaining_time": "3:11:27"}
|
| 45 |
+
{"current_steps": 880, "total_steps": 6572, "loss": 0.16131887435913086, "lr": 4.89559804584665e-06, "epoch": 0.5357686453576864, "percentage": 13.39, "elapsed_time": "0:29:24", "remaining_time": "3:10:16"}
|
| 46 |
+
{"current_steps": 900, "total_steps": 6572, "loss": 0.17404688596725465, "lr": 4.888316013684435e-06, "epoch": 0.547945205479452, "percentage": 13.69, "elapsed_time": "0:30:01", "remaining_time": "3:09:11"}
|
| 47 |
+
{"current_steps": 920, "total_steps": 6572, "loss": 0.14134640693664552, "lr": 4.880794299314732e-06, "epoch": 0.5601217656012176, "percentage": 14.0, "elapsed_time": "0:30:38", "remaining_time": "3:08:12"}
|
| 48 |
+
{"current_steps": 940, "total_steps": 6572, "loss": 0.14891813993453978, "lr": 4.87303365758786e-06, "epoch": 0.5722983257229832, "percentage": 14.3, "elapsed_time": "0:31:15", "remaining_time": "3:07:19"}
|
| 49 |
+
{"current_steps": 960, "total_steps": 6572, "loss": 0.1696299910545349, "lr": 4.865034867331967e-06, "epoch": 0.5844748858447488, "percentage": 14.61, "elapsed_time": "0:31:52", "remaining_time": "3:06:21"}
|
| 50 |
+
{"current_steps": 980, "total_steps": 6572, "loss": 0.14085158109664916, "lr": 4.856798731274874e-06, "epoch": 0.5966514459665144, "percentage": 14.91, "elapsed_time": "0:32:29", "remaining_time": "3:05:22"}
|
| 51 |
+
{"current_steps": 1000, "total_steps": 6572, "loss": 0.133053982257843, "lr": 4.84832607596351e-06, "epoch": 0.60882800608828, "percentage": 15.22, "elapsed_time": "0:33:04", "remaining_time": "3:04:16"}
|
| 52 |
+
{"current_steps": 1000, "total_steps": 6572, "eval_loss": 0.24901165068149567, "epoch": 0.60882800608828, "percentage": 15.22, "elapsed_time": "0:33:51", "remaining_time": "3:08:37"}
|
| 53 |
+
{"current_steps": 1020, "total_steps": 6572, "loss": 0.12680984735488893, "lr": 4.8396177516809695e-06, "epoch": 0.6210045662100456, "percentage": 15.52, "elapsed_time": "0:36:06", "remaining_time": "3:16:32"}
|
| 54 |
+
{"current_steps": 1040, "total_steps": 6572, "loss": 0.14880582094192504, "lr": 4.830674632361178e-06, "epoch": 0.6331811263318112, "percentage": 15.82, "elapsed_time": "0:36:43", "remaining_time": "3:15:23"}
|
| 55 |
+
{"current_steps": 1060, "total_steps": 6572, "loss": 0.1447562575340271, "lr": 4.821497615501186e-06, "epoch": 0.6453576864535768, "percentage": 16.13, "elapsed_time": "0:37:21", "remaining_time": "3:14:16"}
|
| 56 |
+
{"current_steps": 1080, "total_steps": 6572, "loss": 0.15530819892883302, "lr": 4.812087622071104e-06, "epoch": 0.6575342465753424, "percentage": 16.43, "elapsed_time": "0:37:59", "remaining_time": "3:13:10"}
|
| 57 |
+
{"current_steps": 1100, "total_steps": 6572, "loss": 0.14426586627960206, "lr": 4.80244559642167e-06, "epoch": 0.669710806697108, "percentage": 16.74, "elapsed_time": "0:38:36", "remaining_time": "3:12:03"}
|
| 58 |
+
{"current_steps": 1120, "total_steps": 6572, "loss": 0.15436025857925414, "lr": 4.792572506189489e-06, "epoch": 0.6818873668188736, "percentage": 17.04, "elapsed_time": "0:39:13", "remaining_time": "3:10:54"}
|
| 59 |
+
{"current_steps": 1140, "total_steps": 6572, "loss": 0.14860854148864747, "lr": 4.782469342199915e-06, "epoch": 0.6940639269406392, "percentage": 17.35, "elapsed_time": "0:39:50", "remaining_time": "3:09:48"}
|
| 60 |
+
{"current_steps": 1160, "total_steps": 6572, "loss": 0.1313084125518799, "lr": 4.7721371183676205e-06, "epoch": 0.7062404870624048, "percentage": 17.65, "elapsed_time": "0:40:26", "remaining_time": "3:08:40"}
|
| 61 |
+
{"current_steps": 1180, "total_steps": 6572, "loss": 0.150812029838562, "lr": 4.761576871594841e-06, "epoch": 0.7184170471841704, "percentage": 17.95, "elapsed_time": "0:41:02", "remaining_time": "3:07:33"}
|
| 62 |
+
{"current_steps": 1200, "total_steps": 6572, "loss": 0.13278884887695314, "lr": 4.750789661667318e-06, "epoch": 0.730593607305936, "percentage": 18.26, "elapsed_time": "0:41:38", "remaining_time": "3:06:24"}
|
| 63 |
+
{"current_steps": 1220, "total_steps": 6572, "loss": 0.1612934350967407, "lr": 4.739776571147943e-06, "epoch": 0.7427701674277016, "percentage": 18.56, "elapsed_time": "0:42:14", "remaining_time": "3:05:16"}
|
| 64 |
+
{"current_steps": 1240, "total_steps": 6572, "loss": 0.16211290359497071, "lr": 4.728538705268116e-06, "epoch": 0.7549467275494672, "percentage": 18.87, "elapsed_time": "0:42:49", "remaining_time": "3:04:10"}
|
| 65 |
+
{"current_steps": 1260, "total_steps": 6572, "loss": 0.14386119842529296, "lr": 4.717077191816824e-06, "epoch": 0.7671232876712328, "percentage": 19.17, "elapsed_time": "0:43:26", "remaining_time": "3:03:09"}
|
| 66 |
+
{"current_steps": 1280, "total_steps": 6572, "loss": 0.12942540645599365, "lr": 4.705393181027463e-06, "epoch": 0.7792998477929984, "percentage": 19.48, "elapsed_time": "0:44:01", "remaining_time": "3:02:02"}
|
| 67 |
+
{"current_steps": 1300, "total_steps": 6572, "loss": 0.14771063327789308, "lr": 4.693487845462413e-06, "epoch": 0.791476407914764, "percentage": 19.78, "elapsed_time": "0:44:38", "remaining_time": "3:01:02"}
|
| 68 |
+
{"current_steps": 1320, "total_steps": 6572, "loss": 0.1276724100112915, "lr": 4.681362379895349e-06, "epoch": 0.8036529680365296, "percentage": 20.09, "elapsed_time": "0:45:14", "remaining_time": "3:00:00"}
|
| 69 |
+
{"current_steps": 1340, "total_steps": 6572, "loss": 0.1319241166114807, "lr": 4.6690180011913524e-06, "epoch": 0.8158295281582952, "percentage": 20.39, "elapsed_time": "0:45:50", "remaining_time": "2:58:59"}
|
| 70 |
+
{"current_steps": 1360, "total_steps": 6572, "loss": 0.1557891011238098, "lr": 4.6564559481847795e-06, "epoch": 0.8280060882800608, "percentage": 20.69, "elapsed_time": "0:46:27", "remaining_time": "2:58:01"}
|
| 71 |
+
{"current_steps": 1380, "total_steps": 6572, "loss": 0.11075855493545532, "lr": 4.643677481554947e-06, "epoch": 0.8401826484018264, "percentage": 21.0, "elapsed_time": "0:47:04", "remaining_time": "2:57:07"}
|
| 72 |
+
{"current_steps": 1400, "total_steps": 6572, "loss": 0.1580789566040039, "lr": 4.630683883699607e-06, "epoch": 0.852359208523592, "percentage": 21.3, "elapsed_time": "0:47:40", "remaining_time": "2:56:08"}
|
| 73 |
+
{"current_steps": 1420, "total_steps": 6572, "loss": 0.16006500720977784, "lr": 4.6174764586062556e-06, "epoch": 0.8645357686453576, "percentage": 21.61, "elapsed_time": "0:48:18", "remaining_time": "2:55:14"}
|
| 74 |
+
{"current_steps": 1440, "total_steps": 6572, "loss": 0.1462727189064026, "lr": 4.6040565317212685e-06, "epoch": 0.8767123287671232, "percentage": 21.91, "elapsed_time": "0:48:54", "remaining_time": "2:54:20"}
|
| 75 |
+
{"current_steps": 1460, "total_steps": 6572, "loss": 0.14725338220596312, "lr": 4.59042544981688e-06, "epoch": 0.8888888888888888, "percentage": 22.22, "elapsed_time": "0:49:30", "remaining_time": "2:53:22"}
|
| 76 |
+
{"current_steps": 1480, "total_steps": 6572, "loss": 0.1304166793823242, "lr": 4.5765845808560334e-06, "epoch": 0.9010654490106544, "percentage": 22.52, "elapsed_time": "0:50:07", "remaining_time": "2:52:27"}
|
| 77 |
+
{"current_steps": 1500, "total_steps": 6572, "loss": 0.1293134570121765, "lr": 4.562535313855094e-06, "epoch": 0.91324200913242, "percentage": 22.82, "elapsed_time": "0:50:45", "remaining_time": "2:51:38"}
|
| 78 |
+
{"current_steps": 1500, "total_steps": 6572, "eval_loss": 0.25538697838783264, "epoch": 0.91324200913242, "percentage": 22.82, "elapsed_time": "0:51:32", "remaining_time": "2:54:17"}
|
| 79 |
+
{"current_steps": 1520, "total_steps": 6572, "loss": 0.11359381675720215, "lr": 4.548279058744451e-06, "epoch": 0.9254185692541856, "percentage": 23.13, "elapsed_time": "0:53:39", "remaining_time": "2:58:20"}
|
| 80 |
+
{"current_steps": 1540, "total_steps": 6572, "loss": 0.15145074129104613, "lr": 4.533817246227024e-06, "epoch": 0.9375951293759512, "percentage": 23.43, "elapsed_time": "0:54:15", "remaining_time": "2:57:18"}
|
| 81 |
+
{"current_steps": 1560, "total_steps": 6572, "loss": 0.11953675746917725, "lr": 4.519151327634685e-06, "epoch": 0.9497716894977168, "percentage": 23.74, "elapsed_time": "0:54:52", "remaining_time": "2:56:18"}
|
| 82 |
+
{"current_steps": 1580, "total_steps": 6572, "loss": 0.13977375030517578, "lr": 4.504282774782605e-06, "epoch": 0.9619482496194824, "percentage": 24.04, "elapsed_time": "0:55:30", "remaining_time": "2:55:21"}
|
| 83 |
+
{"current_steps": 1600, "total_steps": 6572, "loss": 0.1338045358657837, "lr": 4.489213079821551e-06, "epoch": 0.974124809741248, "percentage": 24.35, "elapsed_time": "0:56:07", "remaining_time": "2:54:25"}
|
| 84 |
+
{"current_steps": 1620, "total_steps": 6572, "loss": 0.11776142120361328, "lr": 4.4739437550881355e-06, "epoch": 0.9863013698630136, "percentage": 24.65, "elapsed_time": "0:56:43", "remaining_time": "2:53:24"}
|
| 85 |
+
{"current_steps": 1640, "total_steps": 6572, "loss": 0.12504475116729735, "lr": 4.458476332953051e-06, "epoch": 0.9984779299847792, "percentage": 24.95, "elapsed_time": "0:57:19", "remaining_time": "2:52:23"}
|
| 86 |
+
{"current_steps": 1660, "total_steps": 6572, "loss": 0.08379222154617309, "lr": 4.442812365667281e-06, "epoch": 1.0103500761035007, "percentage": 25.26, "elapsed_time": "0:57:55", "remaining_time": "2:51:23"}
|
| 87 |
+
{"current_steps": 1680, "total_steps": 6572, "loss": 0.08407147526741028, "lr": 4.426953425206322e-06, "epoch": 1.0225266362252663, "percentage": 25.56, "elapsed_time": "0:58:32", "remaining_time": "2:50:27"}
|
| 88 |
+
{"current_steps": 1700, "total_steps": 6572, "loss": 0.08041079640388489, "lr": 4.410901103112434e-06, "epoch": 1.034703196347032, "percentage": 25.87, "elapsed_time": "0:59:08", "remaining_time": "2:49:28"}
|
| 89 |
+
{"current_steps": 1720, "total_steps": 6572, "loss": 0.07876392006874085, "lr": 4.394657010334908e-06, "epoch": 1.0468797564687975, "percentage": 26.17, "elapsed_time": "0:59:43", "remaining_time": "2:48:29"}
|
| 90 |
+
{"current_steps": 1740, "total_steps": 6572, "loss": 0.10302903652191162, "lr": 4.378222777068406e-06, "epoch": 1.059056316590563, "percentage": 26.48, "elapsed_time": "1:00:19", "remaining_time": "2:47:32"}
|
| 91 |
+
{"current_steps": 1760, "total_steps": 6572, "loss": 0.08733606934547425, "lr": 4.361600052589358e-06, "epoch": 1.0712328767123287, "percentage": 26.78, "elapsed_time": "1:00:55", "remaining_time": "2:46:34"}
|
| 92 |
+
{"current_steps": 1780, "total_steps": 6572, "loss": 0.08532609939575195, "lr": 4.344790505090447e-06, "epoch": 1.0834094368340943, "percentage": 27.08, "elapsed_time": "1:01:31", "remaining_time": "2:45:38"}
|
| 93 |
+
{"current_steps": 1800, "total_steps": 6572, "loss": 0.08734336495399475, "lr": 4.327795821513195e-06, "epoch": 1.09558599695586, "percentage": 27.39, "elapsed_time": "1:02:09", "remaining_time": "2:44:46"}
|
| 94 |
+
{"current_steps": 1820, "total_steps": 6572, "loss": 0.0913870632648468, "lr": 4.3106177073786684e-06, "epoch": 1.1077625570776255, "percentage": 27.69, "elapsed_time": "1:02:46", "remaining_time": "2:43:53"}
|
| 95 |
+
{"current_steps": 1840, "total_steps": 6572, "loss": 0.08115516304969787, "lr": 4.293257886616318e-06, "epoch": 1.119939117199391, "percentage": 28.0, "elapsed_time": "1:03:22", "remaining_time": "2:42:59"}
|
| 96 |
+
{"current_steps": 1860, "total_steps": 6572, "loss": 0.08891176581382751, "lr": 4.275718101390975e-06, "epoch": 1.1321156773211567, "percentage": 28.3, "elapsed_time": "1:03:59", "remaining_time": "2:42:07"}
|
| 97 |
+
{"current_steps": 1880, "total_steps": 6572, "loss": 0.07950961589813232, "lr": 4.25800011192801e-06, "epoch": 1.1442922374429223, "percentage": 28.61, "elapsed_time": "1:04:37", "remaining_time": "2:41:16"}
|
| 98 |
+
{"current_steps": 1900, "total_steps": 6572, "loss": 0.08310645222663879, "lr": 4.240105696336687e-06, "epoch": 1.156468797564688, "percentage": 28.91, "elapsed_time": "1:05:13", "remaining_time": "2:40:22"}
|
| 99 |
+
{"current_steps": 1920, "total_steps": 6572, "loss": 0.07682961225509644, "lr": 4.222036650431715e-06, "epoch": 1.1686453576864535, "percentage": 29.21, "elapsed_time": "1:05:49", "remaining_time": "2:39:29"}
|
| 100 |
+
{"current_steps": 1940, "total_steps": 6572, "loss": 0.07520227432250977, "lr": 4.203794787553032e-06, "epoch": 1.180821917808219, "percentage": 29.52, "elapsed_time": "1:06:26", "remaining_time": "2:38:37"}
|
| 101 |
+
{"current_steps": 1960, "total_steps": 6572, "loss": 0.0754019558429718, "lr": 4.185381938383821e-06, "epoch": 1.1929984779299847, "percentage": 29.82, "elapsed_time": "1:07:02", "remaining_time": "2:37:44"}
|
| 102 |
+
{"current_steps": 1980, "total_steps": 6572, "loss": 0.08085885643959045, "lr": 4.166799950766793e-06, "epoch": 1.2051750380517503, "percentage": 30.13, "elapsed_time": "1:07:38", "remaining_time": "2:36:51"}
|
| 103 |
+
{"current_steps": 2000, "total_steps": 6572, "loss": 0.0884653627872467, "lr": 4.14805068951874e-06, "epoch": 1.217351598173516, "percentage": 30.43, "elapsed_time": "1:08:14", "remaining_time": "2:36:00"}
|
| 104 |
+
{"current_steps": 2000, "total_steps": 6572, "eval_loss": 0.2661186456680298, "epoch": 1.217351598173516, "percentage": 30.43, "elapsed_time": "1:09:01", "remaining_time": "2:37:47"}
|
| 105 |
+
{"current_steps": 2020, "total_steps": 6572, "loss": 0.06684748530387878, "lr": 4.1291360362433965e-06, "epoch": 1.2295281582952815, "percentage": 30.74, "elapsed_time": "1:11:15", "remaining_time": "2:40:34"}
|
| 106 |
+
{"current_steps": 2040, "total_steps": 6572, "loss": 0.0720324158668518, "lr": 4.110057889142601e-06, "epoch": 1.241704718417047, "percentage": 31.04, "elapsed_time": "1:11:52", "remaining_time": "2:39:40"}
|
| 107 |
+
{"current_steps": 2060, "total_steps": 6572, "loss": 0.08799988031387329, "lr": 4.090818162825804e-06, "epoch": 1.2538812785388127, "percentage": 31.35, "elapsed_time": "1:12:29", "remaining_time": "2:38:47"}
|
| 108 |
+
{"current_steps": 2080, "total_steps": 6572, "loss": 0.09275985956192016, "lr": 4.071418788117926e-06, "epoch": 1.2660578386605783, "percentage": 31.65, "elapsed_time": "1:13:07", "remaining_time": "2:37:55"}
|
| 109 |
+
{"current_steps": 2100, "total_steps": 6572, "loss": 0.08431113958358764, "lr": 4.0518617118655845e-06, "epoch": 1.278234398782344, "percentage": 31.95, "elapsed_time": "1:13:43", "remaining_time": "2:37:00"}
|
| 110 |
+
{"current_steps": 2120, "total_steps": 6572, "loss": 0.09995608925819396, "lr": 4.032148896741717e-06, "epoch": 1.2904109589041095, "percentage": 32.26, "elapsed_time": "1:14:20", "remaining_time": "2:36:07"}
|
| 111 |
+
{"current_steps": 2140, "total_steps": 6572, "loss": 0.07387629747390748, "lr": 4.012282321048618e-06, "epoch": 1.302587519025875, "percentage": 32.56, "elapsed_time": "1:14:57", "remaining_time": "2:35:14"}
|
| 112 |
+
{"current_steps": 2160, "total_steps": 6572, "loss": 0.07667248249053955, "lr": 3.992263978519398e-06, "epoch": 1.3147640791476407, "percentage": 32.87, "elapsed_time": "1:15:34", "remaining_time": "2:34:22"}
|
| 113 |
+
{"current_steps": 2180, "total_steps": 6572, "loss": 0.09203824400901794, "lr": 3.972095878117904e-06, "epoch": 1.3269406392694063, "percentage": 33.17, "elapsed_time": "1:16:11", "remaining_time": "2:33:30"}
|
| 114 |
+
{"current_steps": 2200, "total_steps": 6572, "loss": 0.07835246920585633, "lr": 3.951780043837107e-06, "epoch": 1.339117199391172, "percentage": 33.48, "elapsed_time": "1:16:48", "remaining_time": "2:32:37"}
|
| 115 |
+
{"current_steps": 2220, "total_steps": 6572, "loss": 0.08577624559402466, "lr": 3.9313185144959835e-06, "epoch": 1.3512937595129375, "percentage": 33.78, "elapsed_time": "1:17:25", "remaining_time": "2:31:46"}
|
| 116 |
+
{"current_steps": 2240, "total_steps": 6572, "loss": 0.0789969801902771, "lr": 3.9107133435349025e-06, "epoch": 1.363470319634703, "percentage": 34.08, "elapsed_time": "1:18:01", "remaining_time": "2:30:53"}
|
| 117 |
+
{"current_steps": 2260, "total_steps": 6572, "loss": 0.07151145935058593, "lr": 3.889966598809557e-06, "epoch": 1.3756468797564687, "percentage": 34.39, "elapsed_time": "1:18:38", "remaining_time": "2:30:02"}
|
| 118 |
+
{"current_steps": 2280, "total_steps": 6572, "loss": 0.09204544425010681, "lr": 3.869080362383437e-06, "epoch": 1.3878234398782343, "percentage": 34.69, "elapsed_time": "1:19:14", "remaining_time": "2:29:10"}
|
| 119 |
+
{"current_steps": 2300, "total_steps": 6572, "loss": 0.11079612970352173, "lr": 3.848056730318881e-06, "epoch": 1.4, "percentage": 35.0, "elapsed_time": "1:19:54", "remaining_time": "2:28:25"}
|
| 120 |
+
{"current_steps": 2320, "total_steps": 6572, "loss": 0.06770140528678895, "lr": 3.826897812466728e-06, "epoch": 1.4121765601217655, "percentage": 35.3, "elapsed_time": "1:20:30", "remaining_time": "2:27:32"}
|
| 121 |
+
{"current_steps": 2340, "total_steps": 6572, "loss": 0.08210510611534119, "lr": 3.8056057322545763e-06, "epoch": 1.4243531202435311, "percentage": 35.61, "elapsed_time": "1:21:07", "remaining_time": "2:26:42"}
|
| 122 |
+
{"current_steps": 2360, "total_steps": 6572, "loss": 0.09583572745323181, "lr": 3.7841826264736888e-06, "epoch": 1.4365296803652967, "percentage": 35.91, "elapsed_time": "1:21:43", "remaining_time": "2:25:51"}
|
| 123 |
+
{"current_steps": 2380, "total_steps": 6572, "loss": 0.09235450625419617, "lr": 3.762630645064547e-06, "epoch": 1.4487062404870623, "percentage": 36.21, "elapsed_time": "1:22:20", "remaining_time": "2:25:01"}
|
| 124 |
+
{"current_steps": 2400, "total_steps": 6572, "loss": 0.08658097982406616, "lr": 3.7409519509010985e-06, "epoch": 1.460882800608828, "percentage": 36.52, "elapsed_time": "1:22:56", "remaining_time": "2:24:11"}
|
| 125 |
+
{"current_steps": 2420, "total_steps": 6572, "loss": 0.08892765045166015, "lr": 3.7191487195736915e-06, "epoch": 1.4730593607305935, "percentage": 36.82, "elapsed_time": "1:23:32", "remaining_time": "2:23:20"}
|
| 126 |
+
{"current_steps": 2440, "total_steps": 6572, "loss": 0.07849371433258057, "lr": 3.697223139170748e-06, "epoch": 1.4852359208523591, "percentage": 37.13, "elapsed_time": "1:24:09", "remaining_time": "2:22:30"}
|
| 127 |
+
{"current_steps": 2460, "total_steps": 6572, "loss": 0.07469035387039184, "lr": 3.6751774100591716e-06, "epoch": 1.4974124809741247, "percentage": 37.43, "elapsed_time": "1:24:45", "remaining_time": "2:21:40"}
|
| 128 |
+
{"current_steps": 2480, "total_steps": 6572, "loss": 0.0782626211643219, "lr": 3.6530137446635265e-06, "epoch": 1.5095890410958903, "percentage": 37.74, "elapsed_time": "1:25:20", "remaining_time": "2:20:49"}
|
| 129 |
+
{"current_steps": 2500, "total_steps": 6572, "loss": 0.08304058909416198, "lr": 3.630734367244012e-06, "epoch": 1.521765601217656, "percentage": 38.04, "elapsed_time": "1:25:57", "remaining_time": "2:20:00"}
|
| 130 |
+
{"current_steps": 2500, "total_steps": 6572, "eval_loss": 0.2771773338317871, "epoch": 1.521765601217656, "percentage": 38.04, "elapsed_time": "1:26:44", "remaining_time": "2:21:17"}
|
| 131 |
+
{"current_steps": 2520, "total_steps": 6572, "loss": 0.08037537932395936, "lr": 3.6083415136732374e-06, "epoch": 1.5339421613394215, "percentage": 38.34, "elapsed_time": "1:28:46", "remaining_time": "2:22:44"}
|
| 132 |
+
{"current_steps": 2540, "total_steps": 6572, "loss": 0.08990358114242554, "lr": 3.585837431211845e-06, "epoch": 1.5461187214611871, "percentage": 38.65, "elapsed_time": "1:29:23", "remaining_time": "2:21:53"}
|
| 133 |
+
{"current_steps": 2560, "total_steps": 6572, "loss": 0.0773526132106781, "lr": 3.563224378282978e-06, "epoch": 1.5582952815829527, "percentage": 38.95, "elapsed_time": "1:29:59", "remaining_time": "2:21:02"}
|
| 134 |
+
{"current_steps": 2580, "total_steps": 6572, "loss": 0.0777865469455719, "lr": 3.5405046242456396e-06, "epoch": 1.5704718417047183, "percentage": 39.26, "elapsed_time": "1:30:36", "remaining_time": "2:20:11"}
|
| 135 |
+
{"current_steps": 2600, "total_steps": 6572, "loss": 0.08037815093994141, "lr": 3.517680449166943e-06, "epoch": 1.582648401826484, "percentage": 39.56, "elapsed_time": "1:31:11", "remaining_time": "2:19:18"}
|
| 136 |
+
{"current_steps": 2620, "total_steps": 6572, "loss": 0.08837634325027466, "lr": 3.4947541435932976e-06, "epoch": 1.5948249619482495, "percentage": 39.87, "elapsed_time": "1:31:49", "remaining_time": "2:18:30"}
|
| 137 |
+
{"current_steps": 2640, "total_steps": 6572, "loss": 0.08201563358306885, "lr": 3.471728008320532e-06, "epoch": 1.6070015220700151, "percentage": 40.17, "elapsed_time": "1:32:26", "remaining_time": "2:17:41"}
|
| 138 |
+
{"current_steps": 2660, "total_steps": 6572, "loss": 0.07379403114318847, "lr": 3.4486043541630066e-06, "epoch": 1.6191780821917807, "percentage": 40.47, "elapsed_time": "1:33:03", "remaining_time": "2:16:51"}
|
| 139 |
+
{"current_steps": 2680, "total_steps": 6572, "loss": 0.08871785402297974, "lr": 3.425385501721696e-06, "epoch": 1.6313546423135463, "percentage": 40.78, "elapsed_time": "1:33:39", "remaining_time": "2:16:00"}
|
| 140 |
+
{"current_steps": 2700, "total_steps": 6572, "loss": 0.07757498621940613, "lr": 3.4020737811513107e-06, "epoch": 1.643531202435312, "percentage": 41.08, "elapsed_time": "1:34:16", "remaining_time": "2:15:11"}
|
| 141 |
+
{"current_steps": 2720, "total_steps": 6572, "loss": 0.08565697669982911, "lr": 3.3786715319264483e-06, "epoch": 1.6557077625570775, "percentage": 41.39, "elapsed_time": "1:34:52", "remaining_time": "2:14:21"}
|
| 142 |
+
{"current_steps": 2740, "total_steps": 6572, "loss": 0.08129348754882812, "lr": 3.355181102606816e-06, "epoch": 1.6678843226788431, "percentage": 41.69, "elapsed_time": "1:35:28", "remaining_time": "2:13:31"}
|
| 143 |
+
{"current_steps": 2760, "total_steps": 6572, "loss": 0.07875375747680664, "lr": 3.331604850601533e-06, "epoch": 1.6800608828006087, "percentage": 42.0, "elapsed_time": "1:36:06", "remaining_time": "2:12:43"}
|
| 144 |
+
{"current_steps": 2780, "total_steps": 6572, "loss": 0.08989614248275757, "lr": 3.307945141932556e-06, "epoch": 1.6922374429223743, "percentage": 42.3, "elapsed_time": "1:36:41", "remaining_time": "2:11:53"}
|
| 145 |
+
{"current_steps": 2800, "total_steps": 6572, "loss": 0.08251298069953919, "lr": 3.2842043509972294e-06, "epoch": 1.70441400304414, "percentage": 42.6, "elapsed_time": "1:37:18", "remaining_time": "2:11:05"}
|
| 146 |
+
{"current_steps": 2820, "total_steps": 6572, "loss": 0.07760271430015564, "lr": 3.2603848603300026e-06, "epoch": 1.7165905631659055, "percentage": 42.91, "elapsed_time": "1:37:56", "remaining_time": "2:10:18"}
|
| 147 |
+
{"current_steps": 2840, "total_steps": 6572, "loss": 0.07395396232604981, "lr": 3.236489060363329e-06, "epoch": 1.7287671232876711, "percentage": 43.21, "elapsed_time": "1:38:33", "remaining_time": "2:09:31"}
|
| 148 |
+
{"current_steps": 2860, "total_steps": 6572, "loss": 0.07028600573539734, "lr": 3.212519349187766e-06, "epoch": 1.7409436834094367, "percentage": 43.52, "elapsed_time": "1:39:10", "remaining_time": "2:08:42"}
|
| 149 |
+
{"current_steps": 2880, "total_steps": 6572, "loss": 0.08469281196594239, "lr": 3.188478132311319e-06, "epoch": 1.7531202435312023, "percentage": 43.82, "elapsed_time": "1:39:46", "remaining_time": "2:07:54"}
|
| 150 |
+
{"current_steps": 2900, "total_steps": 6572, "loss": 0.09567424058914184, "lr": 3.164367822418029e-06, "epoch": 1.765296803652968, "percentage": 44.13, "elapsed_time": "1:40:22", "remaining_time": "2:07:05"}
|
| 151 |
+
{"current_steps": 2920, "total_steps": 6572, "loss": 0.07239987254142762, "lr": 3.1401908391258474e-06, "epoch": 1.7774733637747335, "percentage": 44.43, "elapsed_time": "1:41:00", "remaining_time": "2:06:19"}
|
| 152 |
+
{"current_steps": 2940, "total_steps": 6572, "loss": 0.0891954243183136, "lr": 3.1159496087438098e-06, "epoch": 1.7896499238964991, "percentage": 44.74, "elapsed_time": "1:41:36", "remaining_time": "2:05:31"}
|
| 153 |
+
{"current_steps": 2960, "total_steps": 6572, "loss": 0.07796849608421326, "lr": 3.0916465640285426e-06, "epoch": 1.8018264840182647, "percentage": 45.04, "elapsed_time": "1:42:12", "remaining_time": "2:04:43"}
|
| 154 |
+
{"current_steps": 2980, "total_steps": 6572, "loss": 0.08645985722541809, "lr": 3.0672841439401223e-06, "epoch": 1.8140030441400303, "percentage": 45.34, "elapsed_time": "1:42:49", "remaining_time": "2:03:55"}
|
| 155 |
+
{"current_steps": 3000, "total_steps": 6572, "loss": 0.08427774310111999, "lr": 3.0428647933973103e-06, "epoch": 1.826179604261796, "percentage": 45.65, "elapsed_time": "1:43:26", "remaining_time": "2:03:10"}
|
| 156 |
+
{"current_steps": 3000, "total_steps": 6572, "eval_loss": 0.2774485647678375, "epoch": 1.826179604261796, "percentage": 45.65, "elapsed_time": "1:44:13", "remaining_time": "2:04:05"}
|
| 157 |
+
{"current_steps": 3020, "total_steps": 6572, "loss": 0.07381275296211243, "lr": 3.0183909630321865e-06, "epoch": 1.8383561643835615, "percentage": 45.95, "elapsed_time": "1:46:17", "remaining_time": "2:05:00"}
|
| 158 |
+
{"current_steps": 3040, "total_steps": 6572, "loss": 0.07289664745330811, "lr": 2.9938651089442184e-06, "epoch": 1.8505327245053271, "percentage": 46.26, "elapsed_time": "1:46:55", "remaining_time": "2:04:14"}
|
| 159 |
+
{"current_steps": 3060, "total_steps": 6572, "loss": 0.07124295830726624, "lr": 2.969289692453773e-06, "epoch": 1.8627092846270927, "percentage": 46.56, "elapsed_time": "1:47:32", "remaining_time": "2:03:25"}
|
| 160 |
+
{"current_steps": 3080, "total_steps": 6572, "loss": 0.08125877976417542, "lr": 2.944667179855109e-06, "epoch": 1.8748858447488583, "percentage": 46.87, "elapsed_time": "1:48:09", "remaining_time": "2:02:37"}
|
| 161 |
+
{"current_steps": 3100, "total_steps": 6572, "loss": 0.0724608838558197, "lr": 2.920000042168871e-06, "epoch": 1.887062404870624, "percentage": 47.17, "elapsed_time": "1:48:47", "remaining_time": "2:01:51"}
|
| 162 |
+
{"current_steps": 3120, "total_steps": 6572, "loss": 0.07104775309562683, "lr": 2.8952907548941057e-06, "epoch": 1.8992389649923895, "percentage": 47.47, "elapsed_time": "1:49:23", "remaining_time": "2:01:01"}
|
| 163 |
+
{"current_steps": 3140, "total_steps": 6572, "loss": 0.0677955150604248, "lr": 2.8705417977598277e-06, "epoch": 1.9114155251141551, "percentage": 47.78, "elapsed_time": "1:50:00", "remaining_time": "2:00:14"}
|
| 164 |
+
{"current_steps": 3160, "total_steps": 6572, "loss": 0.07164496779441834, "lr": 2.8457556544761687e-06, "epoch": 1.9235920852359207, "percentage": 48.08, "elapsed_time": "1:50:36", "remaining_time": "1:59:25"}
|
| 165 |
+
{"current_steps": 3180, "total_steps": 6572, "loss": 0.071807599067688, "lr": 2.8209348124851187e-06, "epoch": 1.9357686453576863, "percentage": 48.39, "elapsed_time": "1:51:13", "remaining_time": "1:58:38"}
|
| 166 |
+
{"current_steps": 3200, "total_steps": 6572, "loss": 0.095755535364151, "lr": 2.7960817627108965e-06, "epoch": 1.947945205479452, "percentage": 48.69, "elapsed_time": "1:51:50", "remaining_time": "1:57:50"}
|
| 167 |
+
{"current_steps": 3220, "total_steps": 6572, "loss": 0.07055851817131042, "lr": 2.77119899930997e-06, "epoch": 1.9601217656012175, "percentage": 49.0, "elapsed_time": "1:52:26", "remaining_time": "1:57:03"}
|
| 168 |
+
{"current_steps": 3240, "total_steps": 6572, "loss": 0.07278798818588257, "lr": 2.7462890194207513e-06, "epoch": 1.9722983257229831, "percentage": 49.3, "elapsed_time": "1:53:03", "remaining_time": "1:56:16"}
|
| 169 |
+
{"current_steps": 3260, "total_steps": 6572, "loss": 0.07153088450431824, "lr": 2.7213543229129956e-06, "epoch": 1.9844748858447487, "percentage": 49.6, "elapsed_time": "1:53:40", "remaining_time": "1:55:28"}
|
| 170 |
+
{"current_steps": 3280, "total_steps": 6572, "loss": 0.07440360188484192, "lr": 2.6963974121369242e-06, "epoch": 1.9966514459665143, "percentage": 49.91, "elapsed_time": "1:54:16", "remaining_time": "1:54:41"}
|
| 171 |
+
{"current_steps": 3300, "total_steps": 6572, "loss": 0.0517767608165741, "lr": 2.671420791672093e-06, "epoch": 2.008523592085236, "percentage": 50.21, "elapsed_time": "1:54:51", "remaining_time": "1:53:53"}
|
| 172 |
+
{"current_steps": 3320, "total_steps": 6572, "loss": 0.03812239170074463, "lr": 2.646426968076052e-06, "epoch": 2.0207001522070014, "percentage": 50.52, "elapsed_time": "1:55:27", "remaining_time": "1:53:06"}
|
| 173 |
+
{"current_steps": 3340, "total_steps": 6572, "loss": 0.04107579588890076, "lr": 2.6214184496327865e-06, "epoch": 2.032876712328767, "percentage": 50.82, "elapsed_time": "1:56:05", "remaining_time": "1:52:19"}
|
| 174 |
+
{"current_steps": 3360, "total_steps": 6572, "loss": 0.04673115909099579, "lr": 2.5963977461010022e-06, "epoch": 2.0450532724505326, "percentage": 51.13, "elapsed_time": "1:56:41", "remaining_time": "1:51:33"}
|
| 175 |
+
{"current_steps": 3380, "total_steps": 6572, "loss": 0.03674449622631073, "lr": 2.5713673684622524e-06, "epoch": 2.057229832572298, "percentage": 51.43, "elapsed_time": "1:57:17", "remaining_time": "1:50:46"}
|
| 176 |
+
{"current_steps": 3400, "total_steps": 6572, "loss": 0.03422380387783051, "lr": 2.546329828668949e-06, "epoch": 2.069406392694064, "percentage": 51.73, "elapsed_time": "1:57:53", "remaining_time": "1:49:59"}
|
| 177 |
+
{"current_steps": 3420, "total_steps": 6572, "loss": 0.035878732800483704, "lr": 2.5212876393922657e-06, "epoch": 2.0815829528158294, "percentage": 52.04, "elapsed_time": "1:58:29", "remaining_time": "1:49:12"}
|
| 178 |
+
{"current_steps": 3440, "total_steps": 6572, "loss": 0.03577531576156616, "lr": 2.496243313769986e-06, "epoch": 2.093759512937595, "percentage": 52.34, "elapsed_time": "1:59:06", "remaining_time": "1:48:27"}
|
| 179 |
+
{"current_steps": 3460, "total_steps": 6572, "loss": 0.04281675517559051, "lr": 2.471199365154283e-06, "epoch": 2.1059360730593606, "percentage": 52.65, "elapsed_time": "1:59:42", "remaining_time": "1:47:40"}
|
| 180 |
+
{"current_steps": 3480, "total_steps": 6572, "loss": 0.042955422401428224, "lr": 2.4461583068595014e-06, "epoch": 2.118112633181126, "percentage": 52.95, "elapsed_time": "2:00:20", "remaining_time": "1:46:55"}
|
| 181 |
+
{"current_steps": 3500, "total_steps": 6572, "loss": 0.04432957172393799, "lr": 2.421122651909918e-06, "epoch": 2.130289193302892, "percentage": 53.26, "elapsed_time": "2:00:56", "remaining_time": "1:46:09"}
|
| 182 |
+
{"current_steps": 3500, "total_steps": 6572, "eval_loss": 0.3123805522918701, "epoch": 2.130289193302892, "percentage": 53.26, "elapsed_time": "2:01:42", "remaining_time": "1:46:49"}
|
| 183 |
+
{"current_steps": 3520, "total_steps": 6572, "loss": 0.03356837034225464, "lr": 2.3960949127875556e-06, "epoch": 2.1424657534246574, "percentage": 53.56, "elapsed_time": "2:03:47", "remaining_time": "1:47:19"}
|
| 184 |
+
{"current_steps": 3540, "total_steps": 6572, "loss": 0.036935809254646304, "lr": 2.371077601180031e-06, "epoch": 2.154642313546423, "percentage": 53.86, "elapsed_time": "2:04:23", "remaining_time": "1:46:32"}
|
| 185 |
+
{"current_steps": 3560, "total_steps": 6572, "loss": 0.0395690768957138, "lr": 2.3460732277284994e-06, "epoch": 2.1668188736681886, "percentage": 54.17, "elapsed_time": "2:05:01", "remaining_time": "1:45:46"}
|
| 186 |
+
{"current_steps": 3580, "total_steps": 6572, "loss": 0.044693085551261905, "lr": 2.321084301775689e-06, "epoch": 2.178995433789954, "percentage": 54.47, "elapsed_time": "2:05:39", "remaining_time": "1:45:01"}
|
| 187 |
+
{"current_steps": 3600, "total_steps": 6572, "loss": 0.03243565857410431, "lr": 2.29611333111408e-06, "epoch": 2.19117199391172, "percentage": 54.78, "elapsed_time": "2:06:17", "remaining_time": "1:44:15"}
|
| 188 |
+
{"current_steps": 3620, "total_steps": 6572, "loss": 0.04325798749923706, "lr": 2.271162821734225e-06, "epoch": 2.2033485540334854, "percentage": 55.08, "elapsed_time": "2:06:56", "remaining_time": "1:43:30"}
|
| 189 |
+
{"current_steps": 3640, "total_steps": 6572, "loss": 0.03856868743896484, "lr": 2.2462352775732653e-06, "epoch": 2.215525114155251, "percentage": 55.39, "elapsed_time": "2:07:33", "remaining_time": "1:42:45"}
|
| 190 |
+
{"current_steps": 3660, "total_steps": 6572, "loss": 0.041602414846420285, "lr": 2.221333200263637e-06, "epoch": 2.2277016742770166, "percentage": 55.69, "elapsed_time": "2:08:11", "remaining_time": "1:41:59"}
|
| 191 |
+
{"current_steps": 3680, "total_steps": 6572, "loss": 0.04286134541034699, "lr": 2.1964590888820233e-06, "epoch": 2.239878234398782, "percentage": 56.0, "elapsed_time": "2:08:48", "remaining_time": "1:41:13"}
|
| 192 |
+
{"current_steps": 3700, "total_steps": 6572, "loss": 0.041756758093833925, "lr": 2.1716154396985526e-06, "epoch": 2.252054794520548, "percentage": 56.3, "elapsed_time": "2:09:25", "remaining_time": "1:40:28"}
|
| 193 |
+
{"current_steps": 3720, "total_steps": 6572, "loss": 0.0359495222568512, "lr": 2.1468047459262882e-06, "epoch": 2.2642313546423134, "percentage": 56.6, "elapsed_time": "2:10:03", "remaining_time": "1:39:42"}
|
| 194 |
+
{"current_steps": 3740, "total_steps": 6572, "loss": 0.04322676360607147, "lr": 2.12202949747101e-06, "epoch": 2.276407914764079, "percentage": 56.91, "elapsed_time": "2:10:41", "remaining_time": "1:38:57"}
|
| 195 |
+
{"current_steps": 3760, "total_steps": 6572, "loss": 0.04191597998142242, "lr": 2.0972921806813468e-06, "epoch": 2.2885844748858446, "percentage": 57.21, "elapsed_time": "2:11:19", "remaining_time": "1:38:13"}
|
| 196 |
+
{"current_steps": 3780, "total_steps": 6572, "loss": 0.041278204321861266, "lr": 2.072595278099247e-06, "epoch": 2.30076103500761, "percentage": 57.52, "elapsed_time": "2:11:58", "remaining_time": "1:37:28"}
|
| 197 |
+
{"current_steps": 3800, "total_steps": 6572, "loss": 0.04312986135482788, "lr": 2.047941268210849e-06, "epoch": 2.312937595129376, "percentage": 57.82, "elapsed_time": "2:12:35", "remaining_time": "1:36:43"}
|
| 198 |
+
{"current_steps": 3820, "total_steps": 6572, "loss": 0.04236046075820923, "lr": 2.0233326251977426e-06, "epoch": 2.3251141552511414, "percentage": 58.13, "elapsed_time": "2:13:14", "remaining_time": "1:35:59"}
|
| 199 |
+
{"current_steps": 3840, "total_steps": 6572, "loss": 0.04433901011943817, "lr": 1.9987718186886724e-06, "epoch": 2.337290715372907, "percentage": 58.43, "elapsed_time": "2:13:52", "remaining_time": "1:35:14"}
|
| 200 |
+
{"current_steps": 3860, "total_steps": 6572, "loss": 0.04127628207206726, "lr": 1.9742613135116986e-06, "epoch": 2.3494672754946726, "percentage": 58.73, "elapsed_time": "2:14:29", "remaining_time": "1:34:29"}
|
| 201 |
+
{"current_steps": 3880, "total_steps": 6572, "loss": 0.04586326479911804, "lr": 1.949803569446828e-06, "epoch": 2.361643835616438, "percentage": 59.04, "elapsed_time": "2:15:07", "remaining_time": "1:33:45"}
|
| 202 |
+
{"current_steps": 3900, "total_steps": 6572, "loss": 0.03624185025691986, "lr": 1.925401040979171e-06, "epoch": 2.373820395738204, "percentage": 59.34, "elapsed_time": "2:15:44", "remaining_time": "1:33:00"}
|
| 203 |
+
{"current_steps": 3920, "total_steps": 6572, "loss": 0.035064518451690674, "lr": 1.9010561770526076e-06, "epoch": 2.3859969558599694, "percentage": 59.65, "elapsed_time": "2:16:21", "remaining_time": "1:32:15"}
|
| 204 |
+
{"current_steps": 3940, "total_steps": 6572, "loss": 0.042050021886825564, "lr": 1.8767714208240312e-06, "epoch": 2.398173515981735, "percentage": 59.95, "elapsed_time": "2:16:59", "remaining_time": "1:31:30"}
|
| 205 |
+
{"current_steps": 3960, "total_steps": 6572, "loss": 0.038166466355323794, "lr": 1.852549209418154e-06, "epoch": 2.4103500761035006, "percentage": 60.26, "elapsed_time": "2:17:37", "remaining_time": "1:30:46"}
|
| 206 |
+
{"current_steps": 3980, "total_steps": 6572, "loss": 0.040885674953460696, "lr": 1.8283919736829332e-06, "epoch": 2.422526636225266, "percentage": 60.56, "elapsed_time": "2:18:15", "remaining_time": "1:30:02"}
|
| 207 |
+
{"current_steps": 4000, "total_steps": 6572, "loss": 0.040162667632102966, "lr": 1.804302137945614e-06, "epoch": 2.434703196347032, "percentage": 60.86, "elapsed_time": "2:18:51", "remaining_time": "1:29:17"}
|
| 208 |
+
{"current_steps": 4000, "total_steps": 6572, "eval_loss": 0.31583163142204285, "epoch": 2.434703196347032, "percentage": 60.86, "elapsed_time": "2:19:38", "remaining_time": "1:29:47"}
|
| 209 |
+
{"current_steps": 4020, "total_steps": 6572, "loss": 0.04170995056629181, "lr": 1.7802821197694426e-06, "epoch": 2.4468797564687974, "percentage": 61.17, "elapsed_time": "2:21:49", "remaining_time": "1:30:02"}
|
| 210 |
+
{"current_steps": 4040, "total_steps": 6572, "loss": 0.03834344446659088, "lr": 1.7563343297110375e-06, "epoch": 2.459056316590563, "percentage": 61.47, "elapsed_time": "2:22:25", "remaining_time": "1:29:15"}
|
| 211 |
+
{"current_steps": 4060, "total_steps": 6572, "loss": 0.03928310573101044, "lr": 1.732461171078486e-06, "epoch": 2.4712328767123286, "percentage": 61.78, "elapsed_time": "2:23:01", "remaining_time": "1:28:29"}
|
| 212 |
+
{"current_steps": 4080, "total_steps": 6572, "loss": 0.03358933925628662, "lr": 1.7086650396901489e-06, "epoch": 2.483409436834094, "percentage": 62.08, "elapsed_time": "2:23:37", "remaining_time": "1:27:43"}
|
| 213 |
+
{"current_steps": 4100, "total_steps": 6572, "loss": 0.03547535240650177, "lr": 1.6849483236342322e-06, "epoch": 2.49558599695586, "percentage": 62.39, "elapsed_time": "2:24:14", "remaining_time": "1:26:58"}
|
| 214 |
+
{"current_steps": 4120, "total_steps": 6572, "loss": 0.03600102663040161, "lr": 1.6613134030291217e-06, "epoch": 2.5077625570776254, "percentage": 62.69, "elapsed_time": "2:24:51", "remaining_time": "1:26:12"}
|
| 215 |
+
{"current_steps": 4140, "total_steps": 6572, "loss": 0.04347077012062073, "lr": 1.6377626497845278e-06, "epoch": 2.519939117199391, "percentage": 62.99, "elapsed_time": "2:25:27", "remaining_time": "1:25:27"}
|
| 216 |
+
{"current_steps": 4160, "total_steps": 6572, "loss": 0.02908192276954651, "lr": 1.6142984273634505e-06, "epoch": 2.5321156773211566, "percentage": 63.3, "elapsed_time": "2:26:04", "remaining_time": "1:24:41"}
|
| 217 |
+
{"current_steps": 4180, "total_steps": 6572, "loss": 0.03611198365688324, "lr": 1.5909230905449846e-06, "epoch": 2.544292237442922, "percentage": 63.6, "elapsed_time": "2:26:40", "remaining_time": "1:23:56"}
|
| 218 |
+
{"current_steps": 4200, "total_steps": 6572, "loss": 0.03758668601512909, "lr": 1.567638985188012e-06, "epoch": 2.556468797564688, "percentage": 63.91, "elapsed_time": "2:27:17", "remaining_time": "1:23:10"}
|
| 219 |
+
{"current_steps": 4220, "total_steps": 6572, "loss": 0.033633843064308167, "lr": 1.544448447995773e-06, "epoch": 2.5686453576864534, "percentage": 64.21, "elapsed_time": "2:27:53", "remaining_time": "1:22:25"}
|
| 220 |
+
{"current_steps": 4240, "total_steps": 6572, "loss": 0.036797890067100526, "lr": 1.52135380628137e-06, "epoch": 2.580821917808219, "percentage": 64.52, "elapsed_time": "2:28:29", "remaining_time": "1:21:40"}
|
| 221 |
+
{"current_steps": 4260, "total_steps": 6572, "loss": 0.039166563749313356, "lr": 1.498357377734201e-06, "epoch": 2.5929984779299846, "percentage": 64.82, "elapsed_time": "2:29:07", "remaining_time": "1:20:55"}
|
| 222 |
+
{"current_steps": 4280, "total_steps": 6572, "loss": 0.03717599511146545, "lr": 1.4754614701873703e-06, "epoch": 2.60517503805175, "percentage": 65.12, "elapsed_time": "2:29:44", "remaining_time": "1:20:11"}
|
| 223 |
+
{"current_steps": 4300, "total_steps": 6572, "loss": 0.03962793946266174, "lr": 1.4526683813860792e-06, "epoch": 2.6173515981735163, "percentage": 65.43, "elapsed_time": "2:30:20", "remaining_time": "1:19:26"}
|
| 224 |
+
{"current_steps": 4320, "total_steps": 6572, "loss": 0.035475924611091614, "lr": 1.4299803987570396e-06, "epoch": 2.6295281582952814, "percentage": 65.73, "elapsed_time": "2:30:57", "remaining_time": "1:18:41"}
|
| 225 |
+
{"current_steps": 4340, "total_steps": 6572, "loss": 0.03256964683532715, "lr": 1.4073997991789078e-06, "epoch": 2.6417047184170475, "percentage": 66.04, "elapsed_time": "2:31:35", "remaining_time": "1:17:57"}
|
| 226 |
+
{"current_steps": 4360, "total_steps": 6572, "loss": 0.03712306022644043, "lr": 1.384928848753792e-06, "epoch": 2.6538812785388126, "percentage": 66.34, "elapsed_time": "2:32:10", "remaining_time": "1:17:12"}
|
| 227 |
+
{"current_steps": 4380, "total_steps": 6572, "loss": 0.041410398483276364, "lr": 1.3625698025798322e-06, "epoch": 2.6660578386605787, "percentage": 66.65, "elapsed_time": "2:32:47", "remaining_time": "1:16:27"}
|
| 228 |
+
{"current_steps": 4400, "total_steps": 6572, "loss": 0.03158504366874695, "lr": 1.3403249045248907e-06, "epoch": 2.678234398782344, "percentage": 66.95, "elapsed_time": "2:33:23", "remaining_time": "1:15:43"}
|
| 229 |
+
{"current_steps": 4420, "total_steps": 6572, "loss": 0.03525224924087524, "lr": 1.3181963870013604e-06, "epoch": 2.69041095890411, "percentage": 67.26, "elapsed_time": "2:33:59", "remaining_time": "1:14:58"}
|
| 230 |
+
{"current_steps": 4440, "total_steps": 6572, "loss": 0.03239959478378296, "lr": 1.2961864707421345e-06, "epoch": 2.702587519025875, "percentage": 67.56, "elapsed_time": "2:34:36", "remaining_time": "1:14:14"}
|
| 231 |
+
{"current_steps": 4460, "total_steps": 6572, "loss": 0.031032082438468934, "lr": 1.2742973645777394e-06, "epoch": 2.714764079147641, "percentage": 67.86, "elapsed_time": "2:35:13", "remaining_time": "1:13:30"}
|
| 232 |
+
{"current_steps": 4480, "total_steps": 6572, "loss": 0.030566230416297913, "lr": 1.252531265214662e-06, "epoch": 2.726940639269406, "percentage": 68.17, "elapsed_time": "2:35:48", "remaining_time": "1:12:45"}
|
| 233 |
+
{"current_steps": 4500, "total_steps": 6572, "loss": 0.041362547874450685, "lr": 1.2308903570149048e-06, "epoch": 2.7391171993911723, "percentage": 68.47, "elapsed_time": "2:36:23", "remaining_time": "1:12:00"}
|
| 234 |
+
{"current_steps": 4500, "total_steps": 6572, "eval_loss": 0.3391737937927246, "epoch": 2.7391171993911723, "percentage": 68.47, "elapsed_time": "2:37:10", "remaining_time": "1:12:22"}
|
| 235 |
+
{"current_steps": 4520, "total_steps": 6572, "loss": 0.0388390064239502, "lr": 1.2093768117767613e-06, "epoch": 2.7512937595129374, "percentage": 68.78, "elapsed_time": "2:39:12", "remaining_time": "1:12:16"}
|
| 236 |
+
{"current_steps": 4540, "total_steps": 6572, "loss": 0.032555675506591795, "lr": 1.1879927885168733e-06, "epoch": 2.7634703196347035, "percentage": 69.08, "elapsed_time": "2:39:48", "remaining_time": "1:11:31"}
|
| 237 |
+
{"current_steps": 4560, "total_steps": 6572, "loss": 0.03606459796428681, "lr": 1.1667404332535504e-06, "epoch": 2.7756468797564686, "percentage": 69.39, "elapsed_time": "2:40:25", "remaining_time": "1:10:47"}
|
| 238 |
+
{"current_steps": 4580, "total_steps": 6572, "loss": 0.032086309790611264, "lr": 1.1456218787914128e-06, "epoch": 2.7878234398782347, "percentage": 69.69, "elapsed_time": "2:41:01", "remaining_time": "1:10:02"}
|
| 239 |
+
{"current_steps": 4600, "total_steps": 6572, "loss": 0.033362787961959836, "lr": 1.1246392445073438e-06, "epoch": 2.8, "percentage": 69.99, "elapsed_time": "2:41:36", "remaining_time": "1:09:16"}
|
| 240 |
+
{"current_steps": 4620, "total_steps": 6572, "loss": 0.03638745844364166, "lr": 1.1037946361378027e-06, "epoch": 2.812176560121766, "percentage": 70.3, "elapsed_time": "2:42:12", "remaining_time": "1:08:32"}
|
| 241 |
+
{"current_steps": 4640, "total_steps": 6572, "loss": 0.030933958292007447, "lr": 1.0830901455674977e-06, "epoch": 2.824353120243531, "percentage": 70.6, "elapsed_time": "2:42:49", "remaining_time": "1:07:47"}
|
| 242 |
+
{"current_steps": 4660, "total_steps": 6572, "loss": 0.02879139482975006, "lr": 1.0625278506194538e-06, "epoch": 2.836529680365297, "percentage": 70.91, "elapsed_time": "2:43:26", "remaining_time": "1:07:03"}
|
| 243 |
+
{"current_steps": 4680, "total_steps": 6572, "loss": 0.03345020413398743, "lr": 1.04210981484649e-06, "epoch": 2.8487062404870622, "percentage": 71.21, "elapsed_time": "2:44:01", "remaining_time": "1:06:18"}
|
| 244 |
+
{"current_steps": 4700, "total_steps": 6572, "loss": 0.02593054175376892, "lr": 1.0218380873241314e-06, "epoch": 2.8608828006088283, "percentage": 71.52, "elapsed_time": "2:44:38", "remaining_time": "1:05:34"}
|
| 245 |
+
{"current_steps": 4720, "total_steps": 6572, "loss": 0.03906567096710205, "lr": 1.0017147024449674e-06, "epoch": 2.8730593607305934, "percentage": 71.82, "elapsed_time": "2:45:15", "remaining_time": "1:04:50"}
|
| 246 |
+
{"current_steps": 4740, "total_steps": 6572, "loss": 0.03371626436710358, "lr": 9.81741679714493e-07, "epoch": 2.8852359208523595, "percentage": 72.12, "elapsed_time": "2:45:52", "remaining_time": "1:04:06"}
|
| 247 |
+
{"current_steps": 4760, "total_steps": 6572, "loss": 0.03090968132019043, "lr": 9.619210235484333e-07, "epoch": 2.8974124809741246, "percentage": 72.43, "elapsed_time": "2:46:29", "remaining_time": "1:03:22"}
|
| 248 |
+
{"current_steps": 4780, "total_steps": 6572, "loss": 0.0322105199098587, "lr": 9.422547230715931e-07, "epoch": 2.9095890410958907, "percentage": 72.73, "elapsed_time": "2:47:05", "remaining_time": "1:02:38"}
|
| 249 |
+
{"current_steps": 4800, "total_steps": 6572, "loss": 0.035210177302360535, "lr": 9.227447519182353e-07, "epoch": 2.921765601217656, "percentage": 73.04, "elapsed_time": "2:47:42", "remaining_time": "1:01:54"}
|
| 250 |
+
{"current_steps": 4820, "total_steps": 6572, "loss": 0.026842504739761353, "lr": 9.033930680340097e-07, "epoch": 2.933942161339422, "percentage": 73.34, "elapsed_time": "2:48:18", "remaining_time": "1:01:10"}
|
| 251 |
+
{"current_steps": 4840, "total_steps": 6572, "loss": 0.03439584076404571, "lr": 8.842016134794682e-07, "epoch": 2.946118721461187, "percentage": 73.65, "elapsed_time": "2:48:55", "remaining_time": "1:00:27"}
|
| 252 |
+
{"current_steps": 4860, "total_steps": 6572, "loss": 0.04011322855949402, "lr": 8.651723142351603e-07, "epoch": 2.958295281582953, "percentage": 73.95, "elapsed_time": "2:49:32", "remaining_time": "0:59:43"}
|
| 253 |
+
{"current_steps": 4880, "total_steps": 6572, "loss": 0.03800423145294189, "lr": 8.463070800083562e-07, "epoch": 2.9704718417047182, "percentage": 74.25, "elapsed_time": "2:50:10", "remaining_time": "0:59:00"}
|
| 254 |
+
{"current_steps": 4900, "total_steps": 6572, "loss": 0.03839131891727447, "lr": 8.276078040413879e-07, "epoch": 2.9826484018264843, "percentage": 74.56, "elapsed_time": "2:50:47", "remaining_time": "0:58:16"}
|
| 255 |
+
{"current_steps": 4920, "total_steps": 6572, "loss": 0.02721840739250183, "lr": 8.090763629216589e-07, "epoch": 2.9948249619482494, "percentage": 74.86, "elapsed_time": "2:51:25", "remaining_time": "0:57:33"}
|
| 256 |
+
{"current_steps": 4940, "total_steps": 6572, "loss": 0.023991990089416503, "lr": 7.907146163933102e-07, "epoch": 3.006697108066971, "percentage": 75.17, "elapsed_time": "2:52:02", "remaining_time": "0:56:50"}
|
| 257 |
+
{"current_steps": 4960, "total_steps": 6572, "loss": 0.01451514959335327, "lr": 7.725244071705871e-07, "epoch": 3.0188736681887365, "percentage": 75.47, "elapsed_time": "2:52:40", "remaining_time": "0:56:07"}
|
| 258 |
+
{"current_steps": 4980, "total_steps": 6572, "loss": 0.014327619969844819, "lr": 7.545075607529104e-07, "epoch": 3.031050228310502, "percentage": 75.78, "elapsed_time": "2:53:20", "remaining_time": "0:55:24"}
|
| 259 |
+
{"current_steps": 5000, "total_steps": 6572, "loss": 0.017832010984420776, "lr": 7.366658852416788e-07, "epoch": 3.0432267884322677, "percentage": 76.08, "elapsed_time": "2:53:56", "remaining_time": "0:54:41"}
|
| 260 |
+
{"current_steps": 5000, "total_steps": 6572, "eval_loss": 0.39115142822265625, "epoch": 3.0432267884322677, "percentage": 76.08, "elapsed_time": "2:54:44", "remaining_time": "0:54:56"}
|
| 261 |
+
{"current_steps": 5020, "total_steps": 6572, "loss": 0.011674411594867706, "lr": 7.190011711588101e-07, "epoch": 3.0554033485540333, "percentage": 76.38, "elapsed_time": "2:56:57", "remaining_time": "0:54:42"}
|
| 262 |
+
{"current_steps": 5040, "total_steps": 6572, "loss": 0.013690856099128724, "lr": 7.015151912670562e-07, "epoch": 3.067579908675799, "percentage": 76.69, "elapsed_time": "2:57:34", "remaining_time": "0:53:58"}
|
| 263 |
+
{"current_steps": 5060, "total_steps": 6572, "loss": 0.011978642642498016, "lr": 6.842097003920903e-07, "epoch": 3.0797564687975645, "percentage": 76.99, "elapsed_time": "2:58:10", "remaining_time": "0:53:14"}
|
| 264 |
+
{"current_steps": 5080, "total_steps": 6572, "loss": 0.013893941044807434, "lr": 6.67086435246406e-07, "epoch": 3.09193302891933, "percentage": 77.3, "elapsed_time": "2:58:46", "remaining_time": "0:52:30"}
|
| 265 |
+
{"current_steps": 5100, "total_steps": 6572, "loss": 0.009910025447607041, "lr": 6.501471142550194e-07, "epoch": 3.1041095890410957, "percentage": 77.6, "elapsed_time": "2:59:23", "remaining_time": "0:51:46"}
|
| 266 |
+
{"current_steps": 5120, "total_steps": 6572, "loss": 0.008863755315542222, "lr": 6.333934373830222e-07, "epoch": 3.1162861491628613, "percentage": 77.91, "elapsed_time": "2:59:59", "remaining_time": "0:51:02"}
|
| 267 |
+
{"current_steps": 5140, "total_steps": 6572, "loss": 0.010502541810274124, "lr": 6.168270859649761e-07, "epoch": 3.128462709284627, "percentage": 78.21, "elapsed_time": "3:00:37", "remaining_time": "0:50:19"}
|
| 268 |
+
{"current_steps": 5160, "total_steps": 6572, "loss": 0.012096930295228958, "lr": 6.004497225361786e-07, "epoch": 3.1406392694063925, "percentage": 78.51, "elapsed_time": "3:01:13", "remaining_time": "0:49:35"}
|
| 269 |
+
{"current_steps": 5180, "total_steps": 6572, "loss": 0.013278065621852875, "lr": 5.842629906658226e-07, "epoch": 3.1528158295281585, "percentage": 78.82, "elapsed_time": "3:01:52", "remaining_time": "0:48:52"}
|
| 270 |
+
{"current_steps": 5200, "total_steps": 6572, "loss": 0.013548998534679413, "lr": 5.682685147920481e-07, "epoch": 3.1649923896499237, "percentage": 79.12, "elapsed_time": "3:02:28", "remaining_time": "0:48:08"}
|
| 271 |
+
{"current_steps": 5220, "total_steps": 6572, "loss": 0.013736458122730255, "lr": 5.524679000589256e-07, "epoch": 3.1771689497716897, "percentage": 79.43, "elapsed_time": "3:03:05", "remaining_time": "0:47:25"}
|
| 272 |
+
{"current_steps": 5240, "total_steps": 6572, "loss": 0.013177134096622467, "lr": 5.36862732155366e-07, "epoch": 3.189345509893455, "percentage": 79.73, "elapsed_time": "3:03:42", "remaining_time": "0:46:41"}
|
| 273 |
+
{"current_steps": 5260, "total_steps": 6572, "loss": 0.011971819400787353, "lr": 5.214545771559879e-07, "epoch": 3.201522070015221, "percentage": 80.04, "elapsed_time": "3:04:17", "remaining_time": "0:45:58"}
|
| 274 |
+
{"current_steps": 5280, "total_steps": 6572, "loss": 0.014422819018363953, "lr": 5.062449813639528e-07, "epoch": 3.213698630136986, "percentage": 80.34, "elapsed_time": "3:04:53", "remaining_time": "0:45:14"}
|
| 275 |
+
{"current_steps": 5300, "total_steps": 6572, "loss": 0.010663678497076034, "lr": 4.912354711557856e-07, "epoch": 3.225875190258752, "percentage": 80.65, "elapsed_time": "3:05:29", "remaining_time": "0:44:31"}
|
| 276 |
+
{"current_steps": 5320, "total_steps": 6572, "loss": 0.011400717496871948, "lr": 4.764275528281892e-07, "epoch": 3.2380517503805173, "percentage": 80.95, "elapsed_time": "3:06:07", "remaining_time": "0:43:48"}
|
| 277 |
+
{"current_steps": 5340, "total_steps": 6572, "loss": 0.008456526696681977, "lr": 4.6182271244688355e-07, "epoch": 3.2502283105022833, "percentage": 81.25, "elapsed_time": "3:06:44", "remaining_time": "0:43:04"}
|
| 278 |
+
{"current_steps": 5360, "total_steps": 6572, "loss": 0.014539115130901337, "lr": 4.4742241569746407e-07, "epoch": 3.2624048706240485, "percentage": 81.56, "elapsed_time": "3:07:22", "remaining_time": "0:42:22"}
|
| 279 |
+
{"current_steps": 5380, "total_steps": 6572, "loss": 0.017625690996646882, "lr": 4.332281077383177e-07, "epoch": 3.2745814307458145, "percentage": 81.86, "elapsed_time": "3:07:58", "remaining_time": "0:41:38"}
|
| 280 |
+
{"current_steps": 5400, "total_steps": 6572, "loss": 0.007641100138425827, "lr": 4.1924121305558563e-07, "epoch": 3.2867579908675797, "percentage": 82.17, "elapsed_time": "3:08:37", "remaining_time": "0:40:56"}
|
| 281 |
+
{"current_steps": 5420, "total_steps": 6572, "loss": 0.011799700558185577, "lr": 4.054631353202121e-07, "epoch": 3.2989345509893457, "percentage": 82.47, "elapsed_time": "3:09:14", "remaining_time": "0:40:13"}
|
| 282 |
+
{"current_steps": 5440, "total_steps": 6572, "loss": 0.011455408483743667, "lr": 3.9189525724707634e-07, "epoch": 3.311111111111111, "percentage": 82.78, "elapsed_time": "3:09:51", "remaining_time": "0:39:30"}
|
| 283 |
+
{"current_steps": 5460, "total_steps": 6572, "loss": 0.012499115616083144, "lr": 3.785389404562259e-07, "epoch": 3.323287671232877, "percentage": 83.08, "elapsed_time": "3:10:28", "remaining_time": "0:38:47"}
|
| 284 |
+
{"current_steps": 5480, "total_steps": 6572, "loss": 0.01148865669965744, "lr": 3.653955253362351e-07, "epoch": 3.335464231354642, "percentage": 83.38, "elapsed_time": "3:11:03", "remaining_time": "0:38:04"}
|
| 285 |
+
{"current_steps": 5500, "total_steps": 6572, "loss": 0.012819178402423859, "lr": 3.5246633090968205e-07, "epoch": 3.347640791476408, "percentage": 83.69, "elapsed_time": "3:11:39", "remaining_time": "0:37:21"}
|
| 286 |
+
{"current_steps": 5500, "total_steps": 6572, "eval_loss": 0.43404534459114075, "epoch": 3.347640791476408, "percentage": 83.69, "elapsed_time": "3:12:26", "remaining_time": "0:37:30"}
|
| 287 |
+
{"current_steps": 5520, "total_steps": 6572, "loss": 0.013325585424900055, "lr": 3.397526547007832e-07, "epoch": 3.3598173515981733, "percentage": 83.99, "elapsed_time": "3:14:26", "remaining_time": "0:37:03"}
|
| 288 |
+
{"current_steps": 5540, "total_steps": 6572, "loss": 0.011712662875652313, "lr": 3.2725577260517396e-07, "epoch": 3.3719939117199393, "percentage": 84.3, "elapsed_time": "3:15:02", "remaining_time": "0:36:19"}
|
| 289 |
+
{"current_steps": 5560, "total_steps": 6572, "loss": 0.01580573171377182, "lr": 3.14976938761867e-07, "epoch": 3.3841704718417045, "percentage": 84.6, "elapsed_time": "3:15:38", "remaining_time": "0:35:36"}
|
| 290 |
+
{"current_steps": 5580, "total_steps": 6572, "loss": 0.012312603741884231, "lr": 3.029173854273909e-07, "epoch": 3.3963470319634705, "percentage": 84.91, "elapsed_time": "3:16:16", "remaining_time": "0:34:53"}
|
| 291 |
+
{"current_steps": 5600, "total_steps": 6572, "loss": 0.011797953397035599, "lr": 2.910783228521269e-07, "epoch": 3.4085235920852357, "percentage": 85.21, "elapsed_time": "3:16:54", "remaining_time": "0:34:10"}
|
| 292 |
+
{"current_steps": 5620, "total_steps": 6572, "loss": 0.012182456254959107, "lr": 2.794609391588504e-07, "epoch": 3.4207001522070017, "percentage": 85.51, "elapsed_time": "3:17:32", "remaining_time": "0:33:27"}
|
| 293 |
+
{"current_steps": 5640, "total_steps": 6572, "loss": 0.013599888980388641, "lr": 2.6806640022349897e-07, "epoch": 3.432876712328767, "percentage": 85.82, "elapsed_time": "3:18:08", "remaining_time": "0:32:44"}
|
| 294 |
+
{"current_steps": 5660, "total_steps": 6572, "loss": 0.009272868931293487, "lr": 2.5689584955816497e-07, "epoch": 3.445053272450533, "percentage": 86.12, "elapsed_time": "3:18:45", "remaining_time": "0:32:01"}
|
| 295 |
+
{"current_steps": 5680, "total_steps": 6572, "loss": 0.008165979385375976, "lr": 2.459504081963421e-07, "epoch": 3.457229832572298, "percentage": 86.43, "elapsed_time": "3:19:21", "remaining_time": "0:31:18"}
|
| 296 |
+
{"current_steps": 5700, "total_steps": 6572, "loss": 0.009182130545377731, "lr": 2.3523117458041865e-07, "epoch": 3.469406392694064, "percentage": 86.73, "elapsed_time": "3:19:56", "remaining_time": "0:30:35"}
|
| 297 |
+
{"current_steps": 5720, "total_steps": 6572, "loss": 0.0107998326420784, "lr": 2.2473922445144485e-07, "epoch": 3.4815829528158293, "percentage": 87.04, "elapsed_time": "3:20:34", "remaining_time": "0:29:52"}
|
| 298 |
+
{"current_steps": 5740, "total_steps": 6572, "loss": 0.014469687640666962, "lr": 2.144756107411733e-07, "epoch": 3.4937595129375953, "percentage": 87.34, "elapsed_time": "3:21:11", "remaining_time": "0:29:09"}
|
| 299 |
+
{"current_steps": 5760, "total_steps": 6572, "loss": 0.0121701680123806, "lr": 2.0444136346639333e-07, "epoch": 3.5059360730593605, "percentage": 87.64, "elapsed_time": "3:21:48", "remaining_time": "0:28:26"}
|
| 300 |
+
{"current_steps": 5780, "total_steps": 6572, "loss": 0.014668506383895875, "lr": 1.9463748962556096e-07, "epoch": 3.5181126331811265, "percentage": 87.95, "elapsed_time": "3:22:25", "remaining_time": "0:27:44"}
|
| 301 |
+
{"current_steps": 5800, "total_steps": 6572, "loss": 0.010488402843475342, "lr": 1.8506497309773885e-07, "epoch": 3.5302891933028917, "percentage": 88.25, "elapsed_time": "3:23:02", "remaining_time": "0:27:01"}
|
| 302 |
+
{"current_steps": 5820, "total_steps": 6572, "loss": 0.010667071491479874, "lr": 1.7572477454386257e-07, "epoch": 3.5424657534246577, "percentage": 88.56, "elapsed_time": "3:23:37", "remaining_time": "0:26:18"}
|
| 303 |
+
{"current_steps": 5840, "total_steps": 6572, "loss": 0.011079683899879456, "lr": 1.6661783131032726e-07, "epoch": 3.554642313546423, "percentage": 88.86, "elapsed_time": "3:24:14", "remaining_time": "0:25:35"}
|
| 304 |
+
{"current_steps": 5860, "total_steps": 6572, "loss": 0.009308797866106033, "lr": 1.5774505733492263e-07, "epoch": 3.566818873668189, "percentage": 89.17, "elapsed_time": "3:24:50", "remaining_time": "0:24:53"}
|
| 305 |
+
{"current_steps": 5880, "total_steps": 6572, "loss": 0.012319787591695785, "lr": 1.49107343055111e-07, "epoch": 3.578995433789954, "percentage": 89.47, "elapsed_time": "3:25:27", "remaining_time": "0:24:10"}
|
| 306 |
+
{"current_steps": 5900, "total_steps": 6572, "loss": 0.00843576118350029, "lr": 1.407055553186701e-07, "epoch": 3.59117199391172, "percentage": 89.77, "elapsed_time": "3:26:04", "remaining_time": "0:23:28"}
|
| 307 |
+
{"current_steps": 5920, "total_steps": 6572, "loss": 0.00938587412238121, "lr": 1.3254053729669564e-07, "epoch": 3.6033485540334853, "percentage": 90.08, "elapsed_time": "3:26:41", "remaining_time": "0:22:45"}
|
| 308 |
+
{"current_steps": 5940, "total_steps": 6572, "loss": 0.011934128403663636, "lr": 1.2461310839898656e-07, "epoch": 3.6155251141552514, "percentage": 90.38, "elapsed_time": "3:27:17", "remaining_time": "0:22:03"}
|
| 309 |
+
{"current_steps": 5960, "total_steps": 6572, "loss": 0.013170333206653595, "lr": 1.169240641918104e-07, "epoch": 3.6277016742770165, "percentage": 90.69, "elapsed_time": "3:27:54", "remaining_time": "0:21:20"}
|
| 310 |
+
{"current_steps": 5980, "total_steps": 6572, "loss": 0.014534834027290344, "lr": 1.0947417631806539e-07, "epoch": 3.6398782343987826, "percentage": 90.99, "elapsed_time": "3:28:31", "remaining_time": "0:20:38"}
|
| 311 |
+
{"current_steps": 6000, "total_steps": 6572, "loss": 0.011021688580513, "lr": 1.0226419241983865e-07, "epoch": 3.6520547945205477, "percentage": 91.3, "elapsed_time": "3:29:07", "remaining_time": "0:19:56"}
|
| 312 |
+
{"current_steps": 6000, "total_steps": 6572, "eval_loss": 0.44063475728034973, "epoch": 3.6520547945205477, "percentage": 91.3, "elapsed_time": "3:29:53", "remaining_time": "0:20:00"}
|
| 313 |
+
{"current_steps": 6020, "total_steps": 6572, "loss": 0.010764393210411071, "lr": 9.529483606337902e-08, "epoch": 3.6642313546423138, "percentage": 91.6, "elapsed_time": "3:31:58", "remaining_time": "0:19:26"}
|
| 314 |
+
{"current_steps": 6040, "total_steps": 6572, "loss": 0.012128306180238723, "lr": 8.856680666647882e-08, "epoch": 3.676407914764079, "percentage": 91.91, "elapsed_time": "3:32:33", "remaining_time": "0:18:43"}
|
| 315 |
+
{"current_steps": 6060, "total_steps": 6572, "loss": 0.011729901283979416, "lr": 8.208077942828713e-08, "epoch": 3.688584474885845, "percentage": 92.21, "elapsed_time": "3:33:10", "remaining_time": "0:18:00"}
|
| 316 |
+
{"current_steps": 6080, "total_steps": 6572, "loss": 0.009119105339050294, "lr": 7.58374052615457e-08, "epoch": 3.70076103500761, "percentage": 92.51, "elapsed_time": "3:33:46", "remaining_time": "0:17:17"}
|
| 317 |
+
{"current_steps": 6100, "total_steps": 6572, "loss": 0.017101363837718965, "lr": 6.983731072726818e-08, "epoch": 3.712937595129376, "percentage": 92.82, "elapsed_time": "3:34:23", "remaining_time": "0:16:35"}
|
| 318 |
+
{"current_steps": 6120, "total_steps": 6572, "loss": 0.012368235737085342, "lr": 6.408109797186118e-08, "epoch": 3.7251141552511413, "percentage": 93.12, "elapsed_time": "3:34:59", "remaining_time": "0:15:52"}
|
| 319 |
+
{"current_steps": 6140, "total_steps": 6572, "loss": 0.008782628178596496, "lr": 5.856934466669212e-08, "epoch": 3.7372907153729074, "percentage": 93.43, "elapsed_time": "3:35:36", "remaining_time": "0:15:10"}
|
| 320 |
+
{"current_steps": 6160, "total_steps": 6572, "loss": 0.008994438499212266, "lr": 5.3302603950119994e-08, "epoch": 3.7494672754946725, "percentage": 93.73, "elapsed_time": "3:36:13", "remaining_time": "0:14:27"}
|
| 321 |
+
{"current_steps": 6180, "total_steps": 6572, "loss": 0.011286454647779465, "lr": 4.8281404371981755e-08, "epoch": 3.7616438356164386, "percentage": 94.04, "elapsed_time": "3:36:50", "remaining_time": "0:13:45"}
|
| 322 |
+
{"current_steps": 6200, "total_steps": 6572, "loss": 0.011785905063152313, "lr": 4.350624984055196e-08, "epoch": 3.7738203957382037, "percentage": 94.34, "elapsed_time": "3:37:26", "remaining_time": "0:13:02"}
|
| 323 |
+
{"current_steps": 6220, "total_steps": 6572, "loss": 0.013624191284179688, "lr": 3.897761957196877e-08, "epoch": 3.7859969558599698, "percentage": 94.64, "elapsed_time": "3:38:01", "remaining_time": "0:12:20"}
|
| 324 |
+
{"current_steps": 6240, "total_steps": 6572, "loss": 0.011700452119112015, "lr": 3.469596804214548e-08, "epoch": 3.798173515981735, "percentage": 94.95, "elapsed_time": "3:38:37", "remaining_time": "0:11:37"}
|
| 325 |
+
{"current_steps": 6260, "total_steps": 6572, "loss": 0.011029987037181855, "lr": 3.06617249411581e-08, "epoch": 3.810350076103501, "percentage": 95.25, "elapsed_time": "3:39:12", "remaining_time": "0:10:55"}
|
| 326 |
+
{"current_steps": 6280, "total_steps": 6572, "loss": 0.010965974628925323, "lr": 2.687529513012488e-08, "epoch": 3.822526636225266, "percentage": 95.56, "elapsed_time": "3:39:49", "remaining_time": "0:10:13"}
|
| 327 |
+
{"current_steps": 6300, "total_steps": 6572, "loss": 0.012378603965044022, "lr": 2.3337058600575722e-08, "epoch": 3.834703196347032, "percentage": 95.86, "elapsed_time": "3:40:25", "remaining_time": "0:09:30"}
|
| 328 |
+
{"current_steps": 6320, "total_steps": 6572, "loss": 0.011792077124118805, "lr": 2.0047370436317437e-08, "epoch": 3.8468797564687973, "percentage": 96.17, "elapsed_time": "3:41:00", "remaining_time": "0:08:48"}
|
| 329 |
+
{"current_steps": 6340, "total_steps": 6572, "loss": 0.01145942509174347, "lr": 1.7006560777798608e-08, "epoch": 3.8590563165905634, "percentage": 96.47, "elapsed_time": "3:41:35", "remaining_time": "0:08:06"}
|
| 330 |
+
{"current_steps": 6360, "total_steps": 6572, "loss": 0.011088228970766067, "lr": 1.421493478897945e-08, "epoch": 3.8712328767123285, "percentage": 96.77, "elapsed_time": "3:42:11", "remaining_time": "0:07:24"}
|
| 331 |
+
{"current_steps": 6380, "total_steps": 6572, "loss": 0.010828402638435364, "lr": 1.1672772626704909e-08, "epoch": 3.8834094368340946, "percentage": 97.08, "elapsed_time": "3:42:47", "remaining_time": "0:06:42"}
|
| 332 |
+
{"current_steps": 6400, "total_steps": 6572, "loss": 0.01165580153465271, "lr": 9.38032941258965e-09, "epoch": 3.8955859969558597, "percentage": 97.38, "elapsed_time": "3:43:22", "remaining_time": "0:06:00"}
|
| 333 |
+
{"current_steps": 6420, "total_steps": 6572, "loss": 0.010783226788043975, "lr": 7.3378352074163215e-09, "epoch": 3.9077625570776258, "percentage": 97.69, "elapsed_time": "3:43:58", "remaining_time": "0:05:18"}
|
| 334 |
+
{"current_steps": 6440, "total_steps": 6572, "loss": 0.011295531690120698, "lr": 5.545494988045963e-09, "epoch": 3.919939117199391, "percentage": 97.99, "elapsed_time": "3:44:33", "remaining_time": "0:04:36"}
|
| 335 |
+
{"current_steps": 6460, "total_steps": 6572, "loss": 0.013613662123680115, "lr": 4.003488626848073e-09, "epoch": 3.932115677321157, "percentage": 98.3, "elapsed_time": "3:45:10", "remaining_time": "0:03:54"}
|
| 336 |
+
{"current_steps": 6480, "total_steps": 6572, "loss": 0.011696261167526246, "lr": 2.7119708736486615e-09, "epoch": 3.944292237442922, "percentage": 98.6, "elapsed_time": "3:45:47", "remaining_time": "0:03:12"}
|
| 337 |
+
{"current_steps": 6500, "total_steps": 6572, "loss": 0.010873865336179733, "lr": 1.6710713402015577e-09, "epoch": 3.956468797564688, "percentage": 98.9, "elapsed_time": "3:46:23", "remaining_time": "0:02:30"}
|
| 338 |
+
{"current_steps": 6500, "total_steps": 6572, "eval_loss": 0.441041499376297, "epoch": 3.956468797564688, "percentage": 98.9, "elapsed_time": "3:47:09", "remaining_time": "0:02:30"}
|
| 339 |
+
{"current_steps": 6520, "total_steps": 6572, "loss": 0.012961818277835846, "lr": 8.80894487179651e-10, "epoch": 3.9686453576864533, "percentage": 99.21, "elapsed_time": "3:49:12", "remaining_time": "0:01:49"}
|
| 340 |
+
{"current_steps": 6540, "total_steps": 6572, "loss": 0.01224210560321808, "lr": 3.4151961369188745e-10, "epoch": 3.9808219178082194, "percentage": 99.51, "elapsed_time": "3:49:48", "remaining_time": "0:01:07"}
|
| 341 |
+
{"current_steps": 6560, "total_steps": 6572, "loss": 0.010245455056428909, "lr": 5.300084932574612e-11, "epoch": 3.9929984779299845, "percentage": 99.82, "elapsed_time": "3:50:24", "remaining_time": "0:00:25"}
|
| 342 |
+
{"current_steps": 6572, "total_steps": 6572, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "3:52:13", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2443 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1000,
|
| 3 |
+
"best_metric": 0.24901165068149567,
|
| 4 |
+
"best_model_checkpoint": "/root/workspace/finetune/checkpoints/train_run_06_qwen3_4b_formal/checkpoint-1000",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 6572,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0121765601217656,
|
| 14 |
+
"grad_norm": 2.8322572708129883,
|
| 15 |
+
"learning_rate": 3.166666666666667e-07,
|
| 16 |
+
"loss": 1.119423007965088,
|
| 17 |
+
"step": 20
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0243531202435312,
|
| 21 |
+
"grad_norm": 2.00534987449646,
|
| 22 |
+
"learning_rate": 6.5e-07,
|
| 23 |
+
"loss": 0.8098940849304199,
|
| 24 |
+
"step": 40
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0365296803652968,
|
| 28 |
+
"grad_norm": 1.4319002628326416,
|
| 29 |
+
"learning_rate": 9.833333333333334e-07,
|
| 30 |
+
"loss": 0.6310151576995849,
|
| 31 |
+
"step": 60
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0487062404870624,
|
| 35 |
+
"grad_norm": 1.3265702724456787,
|
| 36 |
+
"learning_rate": 1.3166666666666666e-06,
|
| 37 |
+
"loss": 0.5526751518249512,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.060882800608828,
|
| 42 |
+
"grad_norm": 0.8091968297958374,
|
| 43 |
+
"learning_rate": 1.6500000000000003e-06,
|
| 44 |
+
"loss": 0.4834024906158447,
|
| 45 |
+
"step": 100
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0730593607305936,
|
| 49 |
+
"grad_norm": 0.8584772348403931,
|
| 50 |
+
"learning_rate": 1.9833333333333335e-06,
|
| 51 |
+
"loss": 0.44873433113098143,
|
| 52 |
+
"step": 120
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0852359208523592,
|
| 56 |
+
"grad_norm": 0.9426456093788147,
|
| 57 |
+
"learning_rate": 2.316666666666667e-06,
|
| 58 |
+
"loss": 0.38286705017089845,
|
| 59 |
+
"step": 140
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0974124809741248,
|
| 63 |
+
"grad_norm": 0.939085066318512,
|
| 64 |
+
"learning_rate": 2.6500000000000005e-06,
|
| 65 |
+
"loss": 0.38465352058410646,
|
| 66 |
+
"step": 160
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1095890410958904,
|
| 70 |
+
"grad_norm": 0.8642272353172302,
|
| 71 |
+
"learning_rate": 2.9833333333333337e-06,
|
| 72 |
+
"loss": 0.3305965900421143,
|
| 73 |
+
"step": 180
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.121765601217656,
|
| 77 |
+
"grad_norm": 0.7353930473327637,
|
| 78 |
+
"learning_rate": 3.316666666666667e-06,
|
| 79 |
+
"loss": 0.2875316619873047,
|
| 80 |
+
"step": 200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1339421613394216,
|
| 84 |
+
"grad_norm": 0.7686158418655396,
|
| 85 |
+
"learning_rate": 3.65e-06,
|
| 86 |
+
"loss": 0.3140716075897217,
|
| 87 |
+
"step": 220
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1461187214611872,
|
| 91 |
+
"grad_norm": 1.153424859046936,
|
| 92 |
+
"learning_rate": 3.983333333333334e-06,
|
| 93 |
+
"loss": 0.2985520839691162,
|
| 94 |
+
"step": 240
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1582952815829528,
|
| 98 |
+
"grad_norm": 0.7382195591926575,
|
| 99 |
+
"learning_rate": 4.316666666666667e-06,
|
| 100 |
+
"loss": 0.2449601411819458,
|
| 101 |
+
"step": 260
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1704718417047184,
|
| 105 |
+
"grad_norm": 0.7017386555671692,
|
| 106 |
+
"learning_rate": 4.65e-06,
|
| 107 |
+
"loss": 0.24566495418548584,
|
| 108 |
+
"step": 280
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.182648401826484,
|
| 112 |
+
"grad_norm": 1.0982152223587036,
|
| 113 |
+
"learning_rate": 4.983333333333334e-06,
|
| 114 |
+
"loss": 0.20863604545593262,
|
| 115 |
+
"step": 300
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1948249619482496,
|
| 119 |
+
"grad_norm": 0.6582516431808472,
|
| 120 |
+
"learning_rate": 4.9998867856224845e-06,
|
| 121 |
+
"loss": 0.19693111181259154,
|
| 122 |
+
"step": 320
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2070015220700152,
|
| 126 |
+
"grad_norm": 0.6201784610748291,
|
| 127 |
+
"learning_rate": 4.999523005839606e-06,
|
| 128 |
+
"loss": 0.21833207607269287,
|
| 129 |
+
"step": 340
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2191780821917808,
|
| 133 |
+
"grad_norm": 0.7551426887512207,
|
| 134 |
+
"learning_rate": 4.998908383543311e-06,
|
| 135 |
+
"loss": 0.2382877826690674,
|
| 136 |
+
"step": 360
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2313546423135464,
|
| 140 |
+
"grad_norm": 0.6009605526924133,
|
| 141 |
+
"learning_rate": 4.9980429804147276e-06,
|
| 142 |
+
"loss": 0.21118538379669188,
|
| 143 |
+
"step": 380
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.243531202435312,
|
| 147 |
+
"grad_norm": 0.7086856365203857,
|
| 148 |
+
"learning_rate": 4.996926883302385e-06,
|
| 149 |
+
"loss": 0.18367968797683715,
|
| 150 |
+
"step": 400
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2557077625570776,
|
| 154 |
+
"grad_norm": 0.964198648929596,
|
| 155 |
+
"learning_rate": 4.995560204213496e-06,
|
| 156 |
+
"loss": 0.22483460903167723,
|
| 157 |
+
"step": 420
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2678843226788432,
|
| 161 |
+
"grad_norm": 0.6596850156784058,
|
| 162 |
+
"learning_rate": 4.993943080302715e-06,
|
| 163 |
+
"loss": 0.22673561573028564,
|
| 164 |
+
"step": 440
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2800608828006088,
|
| 168 |
+
"grad_norm": 0.5922938585281372,
|
| 169 |
+
"learning_rate": 4.992075673858379e-06,
|
| 170 |
+
"loss": 0.185296630859375,
|
| 171 |
+
"step": 460
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2922374429223744,
|
| 175 |
+
"grad_norm": 0.6671269536018372,
|
| 176 |
+
"learning_rate": 4.989958172286214e-06,
|
| 177 |
+
"loss": 0.18437937498092652,
|
| 178 |
+
"step": 480
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.30441400304414,
|
| 182 |
+
"grad_norm": 0.7064187526702881,
|
| 183 |
+
"learning_rate": 4.987590788090533e-06,
|
| 184 |
+
"loss": 0.1850834846496582,
|
| 185 |
+
"step": 500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.30441400304414,
|
| 189 |
+
"eval_loss": 0.2562323212623596,
|
| 190 |
+
"eval_runtime": 47.3626,
|
| 191 |
+
"eval_samples_per_second": 18.58,
|
| 192 |
+
"eval_steps_per_second": 18.58,
|
| 193 |
+
"step": 500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.3165905631659056,
|
| 197 |
+
"grad_norm": 0.7698928117752075,
|
| 198 |
+
"learning_rate": 4.984973758852904e-06,
|
| 199 |
+
"loss": 0.16346561908721924,
|
| 200 |
+
"step": 520
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.3287671232876712,
|
| 204 |
+
"grad_norm": 0.4859939515590668,
|
| 205 |
+
"learning_rate": 4.982107347208317e-06,
|
| 206 |
+
"loss": 0.18838067054748536,
|
| 207 |
+
"step": 540
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.3409436834094368,
|
| 211 |
+
"grad_norm": 0.5321416854858398,
|
| 212 |
+
"learning_rate": 4.978991840818816e-06,
|
| 213 |
+
"loss": 0.177593994140625,
|
| 214 |
+
"step": 560
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.3531202435312024,
|
| 218 |
+
"grad_norm": 0.593889594078064,
|
| 219 |
+
"learning_rate": 4.975627552344638e-06,
|
| 220 |
+
"loss": 0.20775914192199707,
|
| 221 |
+
"step": 580
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.365296803652968,
|
| 225 |
+
"grad_norm": 0.7926055192947388,
|
| 226 |
+
"learning_rate": 4.97201481941283e-06,
|
| 227 |
+
"loss": 0.16498700380325318,
|
| 228 |
+
"step": 600
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.3774733637747336,
|
| 232 |
+
"grad_norm": 0.2909524440765381,
|
| 233 |
+
"learning_rate": 4.968154004583374e-06,
|
| 234 |
+
"loss": 0.17565951347351075,
|
| 235 |
+
"step": 620
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.3896499238964992,
|
| 239 |
+
"grad_norm": 0.4575704038143158,
|
| 240 |
+
"learning_rate": 4.964045495312794e-06,
|
| 241 |
+
"loss": 0.16204673051834106,
|
| 242 |
+
"step": 640
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.4018264840182648,
|
| 246 |
+
"grad_norm": 0.5366008281707764,
|
| 247 |
+
"learning_rate": 4.959689703915272e-06,
|
| 248 |
+
"loss": 0.17068564891815186,
|
| 249 |
+
"step": 660
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.4140030441400304,
|
| 253 |
+
"grad_norm": 0.5129569172859192,
|
| 254 |
+
"learning_rate": 4.95508706752128e-06,
|
| 255 |
+
"loss": 0.1589680790901184,
|
| 256 |
+
"step": 680
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.426179604261796,
|
| 260 |
+
"grad_norm": 0.4709528684616089,
|
| 261 |
+
"learning_rate": 4.9502380480337e-06,
|
| 262 |
+
"loss": 0.17568455934524535,
|
| 263 |
+
"step": 700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.4383561643835616,
|
| 267 |
+
"grad_norm": 0.6092886328697205,
|
| 268 |
+
"learning_rate": 4.9451431320814715e-06,
|
| 269 |
+
"loss": 0.16204804182052612,
|
| 270 |
+
"step": 720
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.4505327245053272,
|
| 274 |
+
"grad_norm": 0.5957323908805847,
|
| 275 |
+
"learning_rate": 4.939802830970762e-06,
|
| 276 |
+
"loss": 0.16562143564224244,
|
| 277 |
+
"step": 740
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.4627092846270928,
|
| 281 |
+
"grad_norm": 0.4758240580558777,
|
| 282 |
+
"learning_rate": 4.934217680633646e-06,
|
| 283 |
+
"loss": 0.17697544097900392,
|
| 284 |
+
"step": 760
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.4748858447488584,
|
| 288 |
+
"grad_norm": 0.865627646446228,
|
| 289 |
+
"learning_rate": 4.928388241574327e-06,
|
| 290 |
+
"loss": 0.1649466037750244,
|
| 291 |
+
"step": 780
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.487062404870624,
|
| 295 |
+
"grad_norm": 0.466294527053833,
|
| 296 |
+
"learning_rate": 4.922315098812883e-06,
|
| 297 |
+
"loss": 0.1602837324142456,
|
| 298 |
+
"step": 800
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.4992389649923896,
|
| 302 |
+
"grad_norm": 0.6357060670852661,
|
| 303 |
+
"learning_rate": 4.9159988618265585e-06,
|
| 304 |
+
"loss": 0.142719042301178,
|
| 305 |
+
"step": 820
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.5114155251141552,
|
| 309 |
+
"grad_norm": 0.6055647730827332,
|
| 310 |
+
"learning_rate": 4.9094401644886e-06,
|
| 311 |
+
"loss": 0.14508233070373536,
|
| 312 |
+
"step": 840
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.5235920852359208,
|
| 316 |
+
"grad_norm": 0.45214834809303284,
|
| 317 |
+
"learning_rate": 4.902639665004641e-06,
|
| 318 |
+
"loss": 0.1821539044380188,
|
| 319 |
+
"step": 860
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.5357686453576864,
|
| 323 |
+
"grad_norm": 0.5735688805580139,
|
| 324 |
+
"learning_rate": 4.89559804584665e-06,
|
| 325 |
+
"loss": 0.16131887435913086,
|
| 326 |
+
"step": 880
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.547945205479452,
|
| 330 |
+
"grad_norm": 0.6279348731040955,
|
| 331 |
+
"learning_rate": 4.888316013684435e-06,
|
| 332 |
+
"loss": 0.17404688596725465,
|
| 333 |
+
"step": 900
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.5601217656012176,
|
| 337 |
+
"grad_norm": 0.6474089026451111,
|
| 338 |
+
"learning_rate": 4.880794299314732e-06,
|
| 339 |
+
"loss": 0.14134640693664552,
|
| 340 |
+
"step": 920
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.5722983257229832,
|
| 344 |
+
"grad_norm": 0.5808464884757996,
|
| 345 |
+
"learning_rate": 4.87303365758786e-06,
|
| 346 |
+
"loss": 0.14891813993453978,
|
| 347 |
+
"step": 940
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.5844748858447488,
|
| 351 |
+
"grad_norm": 0.5440990328788757,
|
| 352 |
+
"learning_rate": 4.865034867331967e-06,
|
| 353 |
+
"loss": 0.1696299910545349,
|
| 354 |
+
"step": 960
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.5966514459665144,
|
| 358 |
+
"grad_norm": 0.6859214901924133,
|
| 359 |
+
"learning_rate": 4.856798731274874e-06,
|
| 360 |
+
"loss": 0.14085158109664916,
|
| 361 |
+
"step": 980
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.60882800608828,
|
| 365 |
+
"grad_norm": 0.3178713619709015,
|
| 366 |
+
"learning_rate": 4.84832607596351e-06,
|
| 367 |
+
"loss": 0.133053982257843,
|
| 368 |
+
"step": 1000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.60882800608828,
|
| 372 |
+
"eval_loss": 0.24901165068149567,
|
| 373 |
+
"eval_runtime": 46.6976,
|
| 374 |
+
"eval_samples_per_second": 18.845,
|
| 375 |
+
"eval_steps_per_second": 18.845,
|
| 376 |
+
"step": 1000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.6210045662100456,
|
| 380 |
+
"grad_norm": 0.3812738358974457,
|
| 381 |
+
"learning_rate": 4.8396177516809695e-06,
|
| 382 |
+
"loss": 0.12680984735488893,
|
| 383 |
+
"step": 1020
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.6331811263318112,
|
| 387 |
+
"grad_norm": 0.5174199342727661,
|
| 388 |
+
"learning_rate": 4.830674632361178e-06,
|
| 389 |
+
"loss": 0.14880582094192504,
|
| 390 |
+
"step": 1040
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.6453576864535768,
|
| 394 |
+
"grad_norm": 0.4705193042755127,
|
| 395 |
+
"learning_rate": 4.821497615501186e-06,
|
| 396 |
+
"loss": 0.1447562575340271,
|
| 397 |
+
"step": 1060
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.6575342465753424,
|
| 401 |
+
"grad_norm": 0.42298850417137146,
|
| 402 |
+
"learning_rate": 4.812087622071104e-06,
|
| 403 |
+
"loss": 0.15530819892883302,
|
| 404 |
+
"step": 1080
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.669710806697108,
|
| 408 |
+
"grad_norm": 0.30658382177352905,
|
| 409 |
+
"learning_rate": 4.80244559642167e-06,
|
| 410 |
+
"loss": 0.14426586627960206,
|
| 411 |
+
"step": 1100
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.6818873668188736,
|
| 415 |
+
"grad_norm": 0.4838867783546448,
|
| 416 |
+
"learning_rate": 4.792572506189489e-06,
|
| 417 |
+
"loss": 0.15436025857925414,
|
| 418 |
+
"step": 1120
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.6940639269406392,
|
| 422 |
+
"grad_norm": 0.716833770275116,
|
| 423 |
+
"learning_rate": 4.782469342199915e-06,
|
| 424 |
+
"loss": 0.14860854148864747,
|
| 425 |
+
"step": 1140
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.7062404870624048,
|
| 429 |
+
"grad_norm": 0.36538004875183105,
|
| 430 |
+
"learning_rate": 4.7721371183676205e-06,
|
| 431 |
+
"loss": 0.1313084125518799,
|
| 432 |
+
"step": 1160
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.7184170471841704,
|
| 436 |
+
"grad_norm": 0.5409316420555115,
|
| 437 |
+
"learning_rate": 4.761576871594841e-06,
|
| 438 |
+
"loss": 0.150812029838562,
|
| 439 |
+
"step": 1180
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.730593607305936,
|
| 443 |
+
"grad_norm": 0.5275493264198303,
|
| 444 |
+
"learning_rate": 4.750789661667318e-06,
|
| 445 |
+
"loss": 0.13278884887695314,
|
| 446 |
+
"step": 1200
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7427701674277016,
|
| 450 |
+
"grad_norm": 0.5485584735870361,
|
| 451 |
+
"learning_rate": 4.739776571147943e-06,
|
| 452 |
+
"loss": 0.1612934350967407,
|
| 453 |
+
"step": 1220
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.7549467275494672,
|
| 457 |
+
"grad_norm": 0.5949460864067078,
|
| 458 |
+
"learning_rate": 4.728538705268116e-06,
|
| 459 |
+
"loss": 0.16211290359497071,
|
| 460 |
+
"step": 1240
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.7671232876712328,
|
| 464 |
+
"grad_norm": 0.43323376774787903,
|
| 465 |
+
"learning_rate": 4.717077191816824e-06,
|
| 466 |
+
"loss": 0.14386119842529296,
|
| 467 |
+
"step": 1260
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.7792998477929984,
|
| 471 |
+
"grad_norm": 0.6409174799919128,
|
| 472 |
+
"learning_rate": 4.705393181027463e-06,
|
| 473 |
+
"loss": 0.12942540645599365,
|
| 474 |
+
"step": 1280
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.791476407914764,
|
| 478 |
+
"grad_norm": 0.4871342182159424,
|
| 479 |
+
"learning_rate": 4.693487845462413e-06,
|
| 480 |
+
"loss": 0.14771063327789308,
|
| 481 |
+
"step": 1300
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.8036529680365296,
|
| 485 |
+
"grad_norm": 0.5108008980751038,
|
| 486 |
+
"learning_rate": 4.681362379895349e-06,
|
| 487 |
+
"loss": 0.1276724100112915,
|
| 488 |
+
"step": 1320
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.8158295281582952,
|
| 492 |
+
"grad_norm": 0.915285587310791,
|
| 493 |
+
"learning_rate": 4.6690180011913524e-06,
|
| 494 |
+
"loss": 0.1319241166114807,
|
| 495 |
+
"step": 1340
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.8280060882800608,
|
| 499 |
+
"grad_norm": 0.5282526612281799,
|
| 500 |
+
"learning_rate": 4.6564559481847795e-06,
|
| 501 |
+
"loss": 0.1557891011238098,
|
| 502 |
+
"step": 1360
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.8401826484018264,
|
| 506 |
+
"grad_norm": 0.46745216846466064,
|
| 507 |
+
"learning_rate": 4.643677481554947e-06,
|
| 508 |
+
"loss": 0.11075855493545532,
|
| 509 |
+
"step": 1380
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.852359208523592,
|
| 513 |
+
"grad_norm": 0.40246087312698364,
|
| 514 |
+
"learning_rate": 4.630683883699607e-06,
|
| 515 |
+
"loss": 0.1580789566040039,
|
| 516 |
+
"step": 1400
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.8645357686453576,
|
| 520 |
+
"grad_norm": 0.3718211352825165,
|
| 521 |
+
"learning_rate": 4.6174764586062556e-06,
|
| 522 |
+
"loss": 0.16006500720977784,
|
| 523 |
+
"step": 1420
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.8767123287671232,
|
| 527 |
+
"grad_norm": 0.4359384775161743,
|
| 528 |
+
"learning_rate": 4.6040565317212685e-06,
|
| 529 |
+
"loss": 0.1462727189064026,
|
| 530 |
+
"step": 1440
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.8888888888888888,
|
| 534 |
+
"grad_norm": 0.3503302037715912,
|
| 535 |
+
"learning_rate": 4.59042544981688e-06,
|
| 536 |
+
"loss": 0.14725338220596312,
|
| 537 |
+
"step": 1460
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.9010654490106544,
|
| 541 |
+
"grad_norm": 0.3662220537662506,
|
| 542 |
+
"learning_rate": 4.5765845808560334e-06,
|
| 543 |
+
"loss": 0.1304166793823242,
|
| 544 |
+
"step": 1480
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.91324200913242,
|
| 548 |
+
"grad_norm": 0.45357516407966614,
|
| 549 |
+
"learning_rate": 4.562535313855094e-06,
|
| 550 |
+
"loss": 0.1293134570121765,
|
| 551 |
+
"step": 1500
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.91324200913242,
|
| 555 |
+
"eval_loss": 0.25538697838783264,
|
| 556 |
+
"eval_runtime": 47.0026,
|
| 557 |
+
"eval_samples_per_second": 18.722,
|
| 558 |
+
"eval_steps_per_second": 18.722,
|
| 559 |
+
"step": 1500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.9254185692541856,
|
| 563 |
+
"grad_norm": 0.31984779238700867,
|
| 564 |
+
"learning_rate": 4.548279058744451e-06,
|
| 565 |
+
"loss": 0.11359381675720215,
|
| 566 |
+
"step": 1520
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.9375951293759512,
|
| 570 |
+
"grad_norm": 0.6947388052940369,
|
| 571 |
+
"learning_rate": 4.533817246227024e-06,
|
| 572 |
+
"loss": 0.15145074129104613,
|
| 573 |
+
"step": 1540
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.9497716894977168,
|
| 577 |
+
"grad_norm": 0.5685822367668152,
|
| 578 |
+
"learning_rate": 4.519151327634685e-06,
|
| 579 |
+
"loss": 0.11953675746917725,
|
| 580 |
+
"step": 1560
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.9619482496194824,
|
| 584 |
+
"grad_norm": 0.2805669903755188,
|
| 585 |
+
"learning_rate": 4.504282774782605e-06,
|
| 586 |
+
"loss": 0.13977375030517578,
|
| 587 |
+
"step": 1580
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.974124809741248,
|
| 591 |
+
"grad_norm": 0.333103746175766,
|
| 592 |
+
"learning_rate": 4.489213079821551e-06,
|
| 593 |
+
"loss": 0.1338045358657837,
|
| 594 |
+
"step": 1600
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.9863013698630136,
|
| 598 |
+
"grad_norm": 0.5493115782737732,
|
| 599 |
+
"learning_rate": 4.4739437550881355e-06,
|
| 600 |
+
"loss": 0.11776142120361328,
|
| 601 |
+
"step": 1620
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.9984779299847792,
|
| 605 |
+
"grad_norm": 0.4903205931186676,
|
| 606 |
+
"learning_rate": 4.458476332953051e-06,
|
| 607 |
+
"loss": 0.12504475116729735,
|
| 608 |
+
"step": 1640
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.0103500761035007,
|
| 612 |
+
"grad_norm": 0.2682284712791443,
|
| 613 |
+
"learning_rate": 4.442812365667281e-06,
|
| 614 |
+
"loss": 0.08379222154617309,
|
| 615 |
+
"step": 1660
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.0225266362252663,
|
| 619 |
+
"grad_norm": 0.34869125485420227,
|
| 620 |
+
"learning_rate": 4.426953425206322e-06,
|
| 621 |
+
"loss": 0.08407147526741028,
|
| 622 |
+
"step": 1680
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.034703196347032,
|
| 626 |
+
"grad_norm": 0.38522422313690186,
|
| 627 |
+
"learning_rate": 4.410901103112434e-06,
|
| 628 |
+
"loss": 0.08041079640388489,
|
| 629 |
+
"step": 1700
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.0468797564687975,
|
| 633 |
+
"grad_norm": 0.4700411856174469,
|
| 634 |
+
"learning_rate": 4.394657010334908e-06,
|
| 635 |
+
"loss": 0.07876392006874085,
|
| 636 |
+
"step": 1720
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.059056316590563,
|
| 640 |
+
"grad_norm": 0.3719494938850403,
|
| 641 |
+
"learning_rate": 4.378222777068406e-06,
|
| 642 |
+
"loss": 0.10302903652191162,
|
| 643 |
+
"step": 1740
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.0712328767123287,
|
| 647 |
+
"grad_norm": 0.406753808259964,
|
| 648 |
+
"learning_rate": 4.361600052589358e-06,
|
| 649 |
+
"loss": 0.08733606934547425,
|
| 650 |
+
"step": 1760
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.0834094368340943,
|
| 654 |
+
"grad_norm": 0.19822958111763,
|
| 655 |
+
"learning_rate": 4.344790505090447e-06,
|
| 656 |
+
"loss": 0.08532609939575195,
|
| 657 |
+
"step": 1780
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.09558599695586,
|
| 661 |
+
"grad_norm": 0.3569728434085846,
|
| 662 |
+
"learning_rate": 4.327795821513195e-06,
|
| 663 |
+
"loss": 0.08734336495399475,
|
| 664 |
+
"step": 1800
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.1077625570776255,
|
| 668 |
+
"grad_norm": 0.4549162685871124,
|
| 669 |
+
"learning_rate": 4.3106177073786684e-06,
|
| 670 |
+
"loss": 0.0913870632648468,
|
| 671 |
+
"step": 1820
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.119939117199391,
|
| 675 |
+
"grad_norm": 0.5802178978919983,
|
| 676 |
+
"learning_rate": 4.293257886616318e-06,
|
| 677 |
+
"loss": 0.08115516304969787,
|
| 678 |
+
"step": 1840
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.1321156773211567,
|
| 682 |
+
"grad_norm": 0.30524641275405884,
|
| 683 |
+
"learning_rate": 4.275718101390975e-06,
|
| 684 |
+
"loss": 0.08891176581382751,
|
| 685 |
+
"step": 1860
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.1442922374429223,
|
| 689 |
+
"grad_norm": 0.33804091811180115,
|
| 690 |
+
"learning_rate": 4.25800011192801e-06,
|
| 691 |
+
"loss": 0.07950961589813232,
|
| 692 |
+
"step": 1880
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.156468797564688,
|
| 696 |
+
"grad_norm": 0.33472684025764465,
|
| 697 |
+
"learning_rate": 4.240105696336687e-06,
|
| 698 |
+
"loss": 0.08310645222663879,
|
| 699 |
+
"step": 1900
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.1686453576864535,
|
| 703 |
+
"grad_norm": 0.3032575845718384,
|
| 704 |
+
"learning_rate": 4.222036650431715e-06,
|
| 705 |
+
"loss": 0.07682961225509644,
|
| 706 |
+
"step": 1920
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.180821917808219,
|
| 710 |
+
"grad_norm": 0.47542238235473633,
|
| 711 |
+
"learning_rate": 4.203794787553032e-06,
|
| 712 |
+
"loss": 0.07520227432250977,
|
| 713 |
+
"step": 1940
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.1929984779299847,
|
| 717 |
+
"grad_norm": 0.39914897084236145,
|
| 718 |
+
"learning_rate": 4.185381938383821e-06,
|
| 719 |
+
"loss": 0.0754019558429718,
|
| 720 |
+
"step": 1960
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.2051750380517503,
|
| 724 |
+
"grad_norm": 0.4697635769844055,
|
| 725 |
+
"learning_rate": 4.166799950766793e-06,
|
| 726 |
+
"loss": 0.08085885643959045,
|
| 727 |
+
"step": 1980
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.217351598173516,
|
| 731 |
+
"grad_norm": 0.28078529238700867,
|
| 732 |
+
"learning_rate": 4.14805068951874e-06,
|
| 733 |
+
"loss": 0.0884653627872467,
|
| 734 |
+
"step": 2000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.217351598173516,
|
| 738 |
+
"eval_loss": 0.2661186456680298,
|
| 739 |
+
"eval_runtime": 46.548,
|
| 740 |
+
"eval_samples_per_second": 18.905,
|
| 741 |
+
"eval_steps_per_second": 18.905,
|
| 742 |
+
"step": 2000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.2295281582952815,
|
| 746 |
+
"grad_norm": 0.2885560989379883,
|
| 747 |
+
"learning_rate": 4.1291360362433965e-06,
|
| 748 |
+
"loss": 0.06684748530387878,
|
| 749 |
+
"step": 2020
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.241704718417047,
|
| 753 |
+
"grad_norm": 0.24163688719272614,
|
| 754 |
+
"learning_rate": 4.110057889142601e-06,
|
| 755 |
+
"loss": 0.0720324158668518,
|
| 756 |
+
"step": 2040
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.2538812785388127,
|
| 760 |
+
"grad_norm": 0.52589350938797,
|
| 761 |
+
"learning_rate": 4.090818162825804e-06,
|
| 762 |
+
"loss": 0.08799988031387329,
|
| 763 |
+
"step": 2060
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 1.2660578386605783,
|
| 767 |
+
"grad_norm": 0.35164448618888855,
|
| 768 |
+
"learning_rate": 4.071418788117926e-06,
|
| 769 |
+
"loss": 0.09275985956192016,
|
| 770 |
+
"step": 2080
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.278234398782344,
|
| 774 |
+
"grad_norm": 0.4981421232223511,
|
| 775 |
+
"learning_rate": 4.0518617118655845e-06,
|
| 776 |
+
"loss": 0.08431113958358764,
|
| 777 |
+
"step": 2100
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.2904109589041095,
|
| 781 |
+
"grad_norm": 0.2867731750011444,
|
| 782 |
+
"learning_rate": 4.032148896741717e-06,
|
| 783 |
+
"loss": 0.09995608925819396,
|
| 784 |
+
"step": 2120
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.302587519025875,
|
| 788 |
+
"grad_norm": 0.5612165331840515,
|
| 789 |
+
"learning_rate": 4.012282321048618e-06,
|
| 790 |
+
"loss": 0.07387629747390748,
|
| 791 |
+
"step": 2140
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.3147640791476407,
|
| 795 |
+
"grad_norm": 0.4880141317844391,
|
| 796 |
+
"learning_rate": 3.992263978519398e-06,
|
| 797 |
+
"loss": 0.07667248249053955,
|
| 798 |
+
"step": 2160
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.3269406392694063,
|
| 802 |
+
"grad_norm": 0.3143049478530884,
|
| 803 |
+
"learning_rate": 3.972095878117904e-06,
|
| 804 |
+
"loss": 0.09203824400901794,
|
| 805 |
+
"step": 2180
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 1.339117199391172,
|
| 809 |
+
"grad_norm": 0.47859013080596924,
|
| 810 |
+
"learning_rate": 3.951780043837107e-06,
|
| 811 |
+
"loss": 0.07835246920585633,
|
| 812 |
+
"step": 2200
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 1.3512937595129375,
|
| 816 |
+
"grad_norm": 0.28448912501335144,
|
| 817 |
+
"learning_rate": 3.9313185144959835e-06,
|
| 818 |
+
"loss": 0.08577624559402466,
|
| 819 |
+
"step": 2220
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.363470319634703,
|
| 823 |
+
"grad_norm": 0.32139304280281067,
|
| 824 |
+
"learning_rate": 3.9107133435349025e-06,
|
| 825 |
+
"loss": 0.0789969801902771,
|
| 826 |
+
"step": 2240
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.3756468797564687,
|
| 830 |
+
"grad_norm": 0.4797567129135132,
|
| 831 |
+
"learning_rate": 3.889966598809557e-06,
|
| 832 |
+
"loss": 0.07151145935058593,
|
| 833 |
+
"step": 2260
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.3878234398782343,
|
| 837 |
+
"grad_norm": 0.2404891699552536,
|
| 838 |
+
"learning_rate": 3.869080362383437e-06,
|
| 839 |
+
"loss": 0.09204544425010681,
|
| 840 |
+
"step": 2280
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.4,
|
| 844 |
+
"grad_norm": 0.328392893075943,
|
| 845 |
+
"learning_rate": 3.848056730318881e-06,
|
| 846 |
+
"loss": 0.11079612970352173,
|
| 847 |
+
"step": 2300
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.4121765601217655,
|
| 851 |
+
"grad_norm": 0.2993980646133423,
|
| 852 |
+
"learning_rate": 3.826897812466728e-06,
|
| 853 |
+
"loss": 0.06770140528678895,
|
| 854 |
+
"step": 2320
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.4243531202435311,
|
| 858 |
+
"grad_norm": 0.47816380858421326,
|
| 859 |
+
"learning_rate": 3.8056057322545763e-06,
|
| 860 |
+
"loss": 0.08210510611534119,
|
| 861 |
+
"step": 2340
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.4365296803652967,
|
| 865 |
+
"grad_norm": 0.38082119822502136,
|
| 866 |
+
"learning_rate": 3.7841826264736888e-06,
|
| 867 |
+
"loss": 0.09583572745323181,
|
| 868 |
+
"step": 2360
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.4487062404870623,
|
| 872 |
+
"grad_norm": 0.3811774253845215,
|
| 873 |
+
"learning_rate": 3.762630645064547e-06,
|
| 874 |
+
"loss": 0.09235450625419617,
|
| 875 |
+
"step": 2380
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.460882800608828,
|
| 879 |
+
"grad_norm": 0.3869916498661041,
|
| 880 |
+
"learning_rate": 3.7409519509010985e-06,
|
| 881 |
+
"loss": 0.08658097982406616,
|
| 882 |
+
"step": 2400
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.4730593607305935,
|
| 886 |
+
"grad_norm": 0.5042543411254883,
|
| 887 |
+
"learning_rate": 3.7191487195736915e-06,
|
| 888 |
+
"loss": 0.08892765045166015,
|
| 889 |
+
"step": 2420
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.4852359208523591,
|
| 893 |
+
"grad_norm": 0.4064173996448517,
|
| 894 |
+
"learning_rate": 3.697223139170748e-06,
|
| 895 |
+
"loss": 0.07849371433258057,
|
| 896 |
+
"step": 2440
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.4974124809741247,
|
| 900 |
+
"grad_norm": 0.3958194851875305,
|
| 901 |
+
"learning_rate": 3.6751774100591716e-06,
|
| 902 |
+
"loss": 0.07469035387039184,
|
| 903 |
+
"step": 2460
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.5095890410958903,
|
| 907 |
+
"grad_norm": 0.39424121379852295,
|
| 908 |
+
"learning_rate": 3.6530137446635265e-06,
|
| 909 |
+
"loss": 0.0782626211643219,
|
| 910 |
+
"step": 2480
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.521765601217656,
|
| 914 |
+
"grad_norm": 0.46179333329200745,
|
| 915 |
+
"learning_rate": 3.630734367244012e-06,
|
| 916 |
+
"loss": 0.08304058909416198,
|
| 917 |
+
"step": 2500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.521765601217656,
|
| 921 |
+
"eval_loss": 0.2771773338317871,
|
| 922 |
+
"eval_runtime": 46.9989,
|
| 923 |
+
"eval_samples_per_second": 18.724,
|
| 924 |
+
"eval_steps_per_second": 18.724,
|
| 925 |
+
"step": 2500
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.5339421613394215,
|
| 929 |
+
"grad_norm": 0.3447970151901245,
|
| 930 |
+
"learning_rate": 3.6083415136732374e-06,
|
| 931 |
+
"loss": 0.08037537932395936,
|
| 932 |
+
"step": 2520
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.5461187214611871,
|
| 936 |
+
"grad_norm": 0.544224202632904,
|
| 937 |
+
"learning_rate": 3.585837431211845e-06,
|
| 938 |
+
"loss": 0.08990358114242554,
|
| 939 |
+
"step": 2540
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.5582952815829527,
|
| 943 |
+
"grad_norm": 0.2808915376663208,
|
| 944 |
+
"learning_rate": 3.563224378282978e-06,
|
| 945 |
+
"loss": 0.0773526132106781,
|
| 946 |
+
"step": 2560
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.5704718417047183,
|
| 950 |
+
"grad_norm": 0.27800413966178894,
|
| 951 |
+
"learning_rate": 3.5405046242456396e-06,
|
| 952 |
+
"loss": 0.0777865469455719,
|
| 953 |
+
"step": 2580
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.582648401826484,
|
| 957 |
+
"grad_norm": 0.4247933328151703,
|
| 958 |
+
"learning_rate": 3.517680449166943e-06,
|
| 959 |
+
"loss": 0.08037815093994141,
|
| 960 |
+
"step": 2600
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.5948249619482495,
|
| 964 |
+
"grad_norm": 0.748912513256073,
|
| 965 |
+
"learning_rate": 3.4947541435932976e-06,
|
| 966 |
+
"loss": 0.08837634325027466,
|
| 967 |
+
"step": 2620
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.6070015220700151,
|
| 971 |
+
"grad_norm": 0.29709526896476746,
|
| 972 |
+
"learning_rate": 3.471728008320532e-06,
|
| 973 |
+
"loss": 0.08201563358306885,
|
| 974 |
+
"step": 2640
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.6191780821917807,
|
| 978 |
+
"grad_norm": 0.3287765681743622,
|
| 979 |
+
"learning_rate": 3.4486043541630066e-06,
|
| 980 |
+
"loss": 0.07379403114318847,
|
| 981 |
+
"step": 2660
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.6313546423135463,
|
| 985 |
+
"grad_norm": 0.4224306643009186,
|
| 986 |
+
"learning_rate": 3.425385501721696e-06,
|
| 987 |
+
"loss": 0.08871785402297974,
|
| 988 |
+
"step": 2680
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.643531202435312,
|
| 992 |
+
"grad_norm": 0.5213542580604553,
|
| 993 |
+
"learning_rate": 3.4020737811513107e-06,
|
| 994 |
+
"loss": 0.07757498621940613,
|
| 995 |
+
"step": 2700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.6557077625570775,
|
| 999 |
+
"grad_norm": 0.21830426156520844,
|
| 1000 |
+
"learning_rate": 3.3786715319264483e-06,
|
| 1001 |
+
"loss": 0.08565697669982911,
|
| 1002 |
+
"step": 2720
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.6678843226788431,
|
| 1006 |
+
"grad_norm": 0.30557703971862793,
|
| 1007 |
+
"learning_rate": 3.355181102606816e-06,
|
| 1008 |
+
"loss": 0.08129348754882812,
|
| 1009 |
+
"step": 2740
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.6800608828006087,
|
| 1013 |
+
"grad_norm": 0.453703910112381,
|
| 1014 |
+
"learning_rate": 3.331604850601533e-06,
|
| 1015 |
+
"loss": 0.07875375747680664,
|
| 1016 |
+
"step": 2760
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.6922374429223743,
|
| 1020 |
+
"grad_norm": 0.33889397978782654,
|
| 1021 |
+
"learning_rate": 3.307945141932556e-06,
|
| 1022 |
+
"loss": 0.08989614248275757,
|
| 1023 |
+
"step": 2780
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.70441400304414,
|
| 1027 |
+
"grad_norm": 0.21036894619464874,
|
| 1028 |
+
"learning_rate": 3.2842043509972294e-06,
|
| 1029 |
+
"loss": 0.08251298069953919,
|
| 1030 |
+
"step": 2800
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.7165905631659055,
|
| 1034 |
+
"grad_norm": 0.2764931321144104,
|
| 1035 |
+
"learning_rate": 3.2603848603300026e-06,
|
| 1036 |
+
"loss": 0.07760271430015564,
|
| 1037 |
+
"step": 2820
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.7287671232876711,
|
| 1041 |
+
"grad_norm": 0.3566988706588745,
|
| 1042 |
+
"learning_rate": 3.236489060363329e-06,
|
| 1043 |
+
"loss": 0.07395396232604981,
|
| 1044 |
+
"step": 2840
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.7409436834094367,
|
| 1048 |
+
"grad_norm": 0.3616081476211548,
|
| 1049 |
+
"learning_rate": 3.212519349187766e-06,
|
| 1050 |
+
"loss": 0.07028600573539734,
|
| 1051 |
+
"step": 2860
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.7531202435312023,
|
| 1055 |
+
"grad_norm": 0.41925984621047974,
|
| 1056 |
+
"learning_rate": 3.188478132311319e-06,
|
| 1057 |
+
"loss": 0.08469281196594239,
|
| 1058 |
+
"step": 2880
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.765296803652968,
|
| 1062 |
+
"grad_norm": 0.4866960346698761,
|
| 1063 |
+
"learning_rate": 3.164367822418029e-06,
|
| 1064 |
+
"loss": 0.09567424058914184,
|
| 1065 |
+
"step": 2900
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.7774733637747335,
|
| 1069 |
+
"grad_norm": 0.2977049648761749,
|
| 1070 |
+
"learning_rate": 3.1401908391258474e-06,
|
| 1071 |
+
"loss": 0.07239987254142762,
|
| 1072 |
+
"step": 2920
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.7896499238964991,
|
| 1076 |
+
"grad_norm": 0.3723915219306946,
|
| 1077 |
+
"learning_rate": 3.1159496087438098e-06,
|
| 1078 |
+
"loss": 0.0891954243183136,
|
| 1079 |
+
"step": 2940
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.8018264840182647,
|
| 1083 |
+
"grad_norm": 0.22685140371322632,
|
| 1084 |
+
"learning_rate": 3.0916465640285426e-06,
|
| 1085 |
+
"loss": 0.07796849608421326,
|
| 1086 |
+
"step": 2960
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.8140030441400303,
|
| 1090 |
+
"grad_norm": 0.23534800112247467,
|
| 1091 |
+
"learning_rate": 3.0672841439401223e-06,
|
| 1092 |
+
"loss": 0.08645985722541809,
|
| 1093 |
+
"step": 2980
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.826179604261796,
|
| 1097 |
+
"grad_norm": 0.40188542008399963,
|
| 1098 |
+
"learning_rate": 3.0428647933973103e-06,
|
| 1099 |
+
"loss": 0.08427774310111999,
|
| 1100 |
+
"step": 3000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.826179604261796,
|
| 1104 |
+
"eval_loss": 0.2774485647678375,
|
| 1105 |
+
"eval_runtime": 46.6449,
|
| 1106 |
+
"eval_samples_per_second": 18.866,
|
| 1107 |
+
"eval_steps_per_second": 18.866,
|
| 1108 |
+
"step": 3000
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.8383561643835615,
|
| 1112 |
+
"grad_norm": 0.35732510685920715,
|
| 1113 |
+
"learning_rate": 3.0183909630321865e-06,
|
| 1114 |
+
"loss": 0.07381275296211243,
|
| 1115 |
+
"step": 3020
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.8505327245053271,
|
| 1119 |
+
"grad_norm": 0.3167949914932251,
|
| 1120 |
+
"learning_rate": 2.9938651089442184e-06,
|
| 1121 |
+
"loss": 0.07289664745330811,
|
| 1122 |
+
"step": 3040
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.8627092846270927,
|
| 1126 |
+
"grad_norm": 0.4893674850463867,
|
| 1127 |
+
"learning_rate": 2.969289692453773e-06,
|
| 1128 |
+
"loss": 0.07124295830726624,
|
| 1129 |
+
"step": 3060
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.8748858447488583,
|
| 1133 |
+
"grad_norm": 0.3017306327819824,
|
| 1134 |
+
"learning_rate": 2.944667179855109e-06,
|
| 1135 |
+
"loss": 0.08125877976417542,
|
| 1136 |
+
"step": 3080
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.887062404870624,
|
| 1140 |
+
"grad_norm": 0.3442900776863098,
|
| 1141 |
+
"learning_rate": 2.920000042168871e-06,
|
| 1142 |
+
"loss": 0.0724608838558197,
|
| 1143 |
+
"step": 3100
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.8992389649923895,
|
| 1147 |
+
"grad_norm": 0.27901750802993774,
|
| 1148 |
+
"learning_rate": 2.8952907548941057e-06,
|
| 1149 |
+
"loss": 0.07104775309562683,
|
| 1150 |
+
"step": 3120
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.9114155251141551,
|
| 1154 |
+
"grad_norm": 0.35838621854782104,
|
| 1155 |
+
"learning_rate": 2.8705417977598277e-06,
|
| 1156 |
+
"loss": 0.0677955150604248,
|
| 1157 |
+
"step": 3140
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.9235920852359207,
|
| 1161 |
+
"grad_norm": 0.3615752160549164,
|
| 1162 |
+
"learning_rate": 2.8457556544761687e-06,
|
| 1163 |
+
"loss": 0.07164496779441834,
|
| 1164 |
+
"step": 3160
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.9357686453576863,
|
| 1168 |
+
"grad_norm": 0.5117827653884888,
|
| 1169 |
+
"learning_rate": 2.8209348124851187e-06,
|
| 1170 |
+
"loss": 0.071807599067688,
|
| 1171 |
+
"step": 3180
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.947945205479452,
|
| 1175 |
+
"grad_norm": 0.36082401871681213,
|
| 1176 |
+
"learning_rate": 2.7960817627108965e-06,
|
| 1177 |
+
"loss": 0.095755535364151,
|
| 1178 |
+
"step": 3200
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.9601217656012175,
|
| 1182 |
+
"grad_norm": 0.27905145287513733,
|
| 1183 |
+
"learning_rate": 2.77119899930997e-06,
|
| 1184 |
+
"loss": 0.07055851817131042,
|
| 1185 |
+
"step": 3220
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.9722983257229831,
|
| 1189 |
+
"grad_norm": 0.5642575621604919,
|
| 1190 |
+
"learning_rate": 2.7462890194207513e-06,
|
| 1191 |
+
"loss": 0.07278798818588257,
|
| 1192 |
+
"step": 3240
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.9844748858447487,
|
| 1196 |
+
"grad_norm": 0.2286670207977295,
|
| 1197 |
+
"learning_rate": 2.7213543229129956e-06,
|
| 1198 |
+
"loss": 0.07153088450431824,
|
| 1199 |
+
"step": 3260
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.9966514459665143,
|
| 1203 |
+
"grad_norm": 0.3228706121444702,
|
| 1204 |
+
"learning_rate": 2.6963974121369242e-06,
|
| 1205 |
+
"loss": 0.07440360188484192,
|
| 1206 |
+
"step": 3280
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.008523592085236,
|
| 1210 |
+
"grad_norm": 0.21613839268684387,
|
| 1211 |
+
"learning_rate": 2.671420791672093e-06,
|
| 1212 |
+
"loss": 0.0517767608165741,
|
| 1213 |
+
"step": 3300
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.0207001522070014,
|
| 1217 |
+
"grad_norm": 0.19271881878376007,
|
| 1218 |
+
"learning_rate": 2.646426968076052e-06,
|
| 1219 |
+
"loss": 0.03812239170074463,
|
| 1220 |
+
"step": 3320
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.032876712328767,
|
| 1224 |
+
"grad_norm": 0.12863056361675262,
|
| 1225 |
+
"learning_rate": 2.6214184496327865e-06,
|
| 1226 |
+
"loss": 0.04107579588890076,
|
| 1227 |
+
"step": 3340
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.0450532724505326,
|
| 1231 |
+
"grad_norm": 0.26679477095603943,
|
| 1232 |
+
"learning_rate": 2.5963977461010022e-06,
|
| 1233 |
+
"loss": 0.04673115909099579,
|
| 1234 |
+
"step": 3360
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.057229832572298,
|
| 1238 |
+
"grad_norm": 0.2743483781814575,
|
| 1239 |
+
"learning_rate": 2.5713673684622524e-06,
|
| 1240 |
+
"loss": 0.03674449622631073,
|
| 1241 |
+
"step": 3380
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.069406392694064,
|
| 1245 |
+
"grad_norm": 0.16999909281730652,
|
| 1246 |
+
"learning_rate": 2.546329828668949e-06,
|
| 1247 |
+
"loss": 0.03422380387783051,
|
| 1248 |
+
"step": 3400
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.0815829528158294,
|
| 1252 |
+
"grad_norm": 0.2931291460990906,
|
| 1253 |
+
"learning_rate": 2.5212876393922657e-06,
|
| 1254 |
+
"loss": 0.035878732800483704,
|
| 1255 |
+
"step": 3420
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.093759512937595,
|
| 1259 |
+
"grad_norm": 0.34781521558761597,
|
| 1260 |
+
"learning_rate": 2.496243313769986e-06,
|
| 1261 |
+
"loss": 0.03577531576156616,
|
| 1262 |
+
"step": 3440
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.1059360730593606,
|
| 1266 |
+
"grad_norm": 0.472351998090744,
|
| 1267 |
+
"learning_rate": 2.471199365154283e-06,
|
| 1268 |
+
"loss": 0.04281675517559051,
|
| 1269 |
+
"step": 3460
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.118112633181126,
|
| 1273 |
+
"grad_norm": 0.38320988416671753,
|
| 1274 |
+
"learning_rate": 2.4461583068595014e-06,
|
| 1275 |
+
"loss": 0.042955422401428224,
|
| 1276 |
+
"step": 3480
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.130289193302892,
|
| 1280 |
+
"grad_norm": 0.12197626382112503,
|
| 1281 |
+
"learning_rate": 2.421122651909918e-06,
|
| 1282 |
+
"loss": 0.04432957172393799,
|
| 1283 |
+
"step": 3500
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.130289193302892,
|
| 1287 |
+
"eval_loss": 0.3123805522918701,
|
| 1288 |
+
"eval_runtime": 46.5258,
|
| 1289 |
+
"eval_samples_per_second": 18.914,
|
| 1290 |
+
"eval_steps_per_second": 18.914,
|
| 1291 |
+
"step": 3500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.1424657534246574,
|
| 1295 |
+
"grad_norm": 0.21291697025299072,
|
| 1296 |
+
"learning_rate": 2.3960949127875556e-06,
|
| 1297 |
+
"loss": 0.03356837034225464,
|
| 1298 |
+
"step": 3520
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.154642313546423,
|
| 1302 |
+
"grad_norm": 0.44130077958106995,
|
| 1303 |
+
"learning_rate": 2.371077601180031e-06,
|
| 1304 |
+
"loss": 0.036935809254646304,
|
| 1305 |
+
"step": 3540
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.1668188736681886,
|
| 1309 |
+
"grad_norm": 0.49069875478744507,
|
| 1310 |
+
"learning_rate": 2.3460732277284994e-06,
|
| 1311 |
+
"loss": 0.0395690768957138,
|
| 1312 |
+
"step": 3560
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.178995433789954,
|
| 1316 |
+
"grad_norm": 0.2824937701225281,
|
| 1317 |
+
"learning_rate": 2.321084301775689e-06,
|
| 1318 |
+
"loss": 0.044693085551261905,
|
| 1319 |
+
"step": 3580
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.19117199391172,
|
| 1323 |
+
"grad_norm": 0.35114097595214844,
|
| 1324 |
+
"learning_rate": 2.29611333111408e-06,
|
| 1325 |
+
"loss": 0.03243565857410431,
|
| 1326 |
+
"step": 3600
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.2033485540334854,
|
| 1330 |
+
"grad_norm": 0.47931790351867676,
|
| 1331 |
+
"learning_rate": 2.271162821734225e-06,
|
| 1332 |
+
"loss": 0.04325798749923706,
|
| 1333 |
+
"step": 3620
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.215525114155251,
|
| 1337 |
+
"grad_norm": 0.12716218829154968,
|
| 1338 |
+
"learning_rate": 2.2462352775732653e-06,
|
| 1339 |
+
"loss": 0.03856868743896484,
|
| 1340 |
+
"step": 3640
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.2277016742770166,
|
| 1344 |
+
"grad_norm": 0.3522437512874603,
|
| 1345 |
+
"learning_rate": 2.221333200263637e-06,
|
| 1346 |
+
"loss": 0.041602414846420285,
|
| 1347 |
+
"step": 3660
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.239878234398782,
|
| 1351 |
+
"grad_norm": 0.234590083360672,
|
| 1352 |
+
"learning_rate": 2.1964590888820233e-06,
|
| 1353 |
+
"loss": 0.04286134541034699,
|
| 1354 |
+
"step": 3680
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.252054794520548,
|
| 1358 |
+
"grad_norm": 0.2972453534603119,
|
| 1359 |
+
"learning_rate": 2.1716154396985526e-06,
|
| 1360 |
+
"loss": 0.041756758093833925,
|
| 1361 |
+
"step": 3700
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.2642313546423134,
|
| 1365 |
+
"grad_norm": 0.3236760199069977,
|
| 1366 |
+
"learning_rate": 2.1468047459262882e-06,
|
| 1367 |
+
"loss": 0.0359495222568512,
|
| 1368 |
+
"step": 3720
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.276407914764079,
|
| 1372 |
+
"grad_norm": 0.32255831360816956,
|
| 1373 |
+
"learning_rate": 2.12202949747101e-06,
|
| 1374 |
+
"loss": 0.04322676360607147,
|
| 1375 |
+
"step": 3740
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.2885844748858446,
|
| 1379 |
+
"grad_norm": 0.2753404378890991,
|
| 1380 |
+
"learning_rate": 2.0972921806813468e-06,
|
| 1381 |
+
"loss": 0.04191597998142242,
|
| 1382 |
+
"step": 3760
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.30076103500761,
|
| 1386 |
+
"grad_norm": 0.23182159662246704,
|
| 1387 |
+
"learning_rate": 2.072595278099247e-06,
|
| 1388 |
+
"loss": 0.041278204321861266,
|
| 1389 |
+
"step": 3780
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.312937595129376,
|
| 1393 |
+
"grad_norm": 0.25987961888313293,
|
| 1394 |
+
"learning_rate": 2.047941268210849e-06,
|
| 1395 |
+
"loss": 0.04312986135482788,
|
| 1396 |
+
"step": 3800
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.3251141552511414,
|
| 1400 |
+
"grad_norm": 0.3683331310749054,
|
| 1401 |
+
"learning_rate": 2.0233326251977426e-06,
|
| 1402 |
+
"loss": 0.04236046075820923,
|
| 1403 |
+
"step": 3820
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.337290715372907,
|
| 1407 |
+
"grad_norm": 0.2520082890987396,
|
| 1408 |
+
"learning_rate": 1.9987718186886724e-06,
|
| 1409 |
+
"loss": 0.04433901011943817,
|
| 1410 |
+
"step": 3840
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.3494672754946726,
|
| 1414 |
+
"grad_norm": 0.16200299561023712,
|
| 1415 |
+
"learning_rate": 1.9742613135116986e-06,
|
| 1416 |
+
"loss": 0.04127628207206726,
|
| 1417 |
+
"step": 3860
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.361643835616438,
|
| 1421 |
+
"grad_norm": 0.37064701318740845,
|
| 1422 |
+
"learning_rate": 1.949803569446828e-06,
|
| 1423 |
+
"loss": 0.04586326479911804,
|
| 1424 |
+
"step": 3880
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.373820395738204,
|
| 1428 |
+
"grad_norm": 0.416020005941391,
|
| 1429 |
+
"learning_rate": 1.925401040979171e-06,
|
| 1430 |
+
"loss": 0.03624185025691986,
|
| 1431 |
+
"step": 3900
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.3859969558599694,
|
| 1435 |
+
"grad_norm": 0.17131179571151733,
|
| 1436 |
+
"learning_rate": 1.9010561770526076e-06,
|
| 1437 |
+
"loss": 0.035064518451690674,
|
| 1438 |
+
"step": 3920
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.398173515981735,
|
| 1442 |
+
"grad_norm": 0.5188226103782654,
|
| 1443 |
+
"learning_rate": 1.8767714208240312e-06,
|
| 1444 |
+
"loss": 0.042050021886825564,
|
| 1445 |
+
"step": 3940
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.4103500761035006,
|
| 1449 |
+
"grad_norm": 0.3398009240627289,
|
| 1450 |
+
"learning_rate": 1.852549209418154e-06,
|
| 1451 |
+
"loss": 0.038166466355323794,
|
| 1452 |
+
"step": 3960
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.422526636225266,
|
| 1456 |
+
"grad_norm": 0.2541758418083191,
|
| 1457 |
+
"learning_rate": 1.8283919736829332e-06,
|
| 1458 |
+
"loss": 0.040885674953460696,
|
| 1459 |
+
"step": 3980
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.434703196347032,
|
| 1463 |
+
"grad_norm": 0.4074256122112274,
|
| 1464 |
+
"learning_rate": 1.804302137945614e-06,
|
| 1465 |
+
"loss": 0.040162667632102966,
|
| 1466 |
+
"step": 4000
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.434703196347032,
|
| 1470 |
+
"eval_loss": 0.31583163142204285,
|
| 1471 |
+
"eval_runtime": 47.319,
|
| 1472 |
+
"eval_samples_per_second": 18.597,
|
| 1473 |
+
"eval_steps_per_second": 18.597,
|
| 1474 |
+
"step": 4000
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 2.4468797564687974,
|
| 1478 |
+
"grad_norm": 0.2724802494049072,
|
| 1479 |
+
"learning_rate": 1.7802821197694426e-06,
|
| 1480 |
+
"loss": 0.04170995056629181,
|
| 1481 |
+
"step": 4020
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.459056316590563,
|
| 1485 |
+
"grad_norm": 0.21376508474349976,
|
| 1486 |
+
"learning_rate": 1.7563343297110375e-06,
|
| 1487 |
+
"loss": 0.03834344446659088,
|
| 1488 |
+
"step": 4040
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.4712328767123286,
|
| 1492 |
+
"grad_norm": 0.2933412492275238,
|
| 1493 |
+
"learning_rate": 1.732461171078486e-06,
|
| 1494 |
+
"loss": 0.03928310573101044,
|
| 1495 |
+
"step": 4060
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.483409436834094,
|
| 1499 |
+
"grad_norm": 0.46805083751678467,
|
| 1500 |
+
"learning_rate": 1.7086650396901489e-06,
|
| 1501 |
+
"loss": 0.03358933925628662,
|
| 1502 |
+
"step": 4080
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.49558599695586,
|
| 1506 |
+
"grad_norm": 0.45667552947998047,
|
| 1507 |
+
"learning_rate": 1.6849483236342322e-06,
|
| 1508 |
+
"loss": 0.03547535240650177,
|
| 1509 |
+
"step": 4100
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.5077625570776254,
|
| 1513 |
+
"grad_norm": 0.24512450397014618,
|
| 1514 |
+
"learning_rate": 1.6613134030291217e-06,
|
| 1515 |
+
"loss": 0.03600102663040161,
|
| 1516 |
+
"step": 4120
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.519939117199391,
|
| 1520 |
+
"grad_norm": 0.20636337995529175,
|
| 1521 |
+
"learning_rate": 1.6377626497845278e-06,
|
| 1522 |
+
"loss": 0.04347077012062073,
|
| 1523 |
+
"step": 4140
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.5321156773211566,
|
| 1527 |
+
"grad_norm": 0.4584953486919403,
|
| 1528 |
+
"learning_rate": 1.6142984273634505e-06,
|
| 1529 |
+
"loss": 0.02908192276954651,
|
| 1530 |
+
"step": 4160
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.544292237442922,
|
| 1534 |
+
"grad_norm": 0.26193487644195557,
|
| 1535 |
+
"learning_rate": 1.5909230905449846e-06,
|
| 1536 |
+
"loss": 0.03611198365688324,
|
| 1537 |
+
"step": 4180
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.556468797564688,
|
| 1541 |
+
"grad_norm": 0.20813828706741333,
|
| 1542 |
+
"learning_rate": 1.567638985188012e-06,
|
| 1543 |
+
"loss": 0.03758668601512909,
|
| 1544 |
+
"step": 4200
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.5686453576864534,
|
| 1548 |
+
"grad_norm": 0.3395022749900818,
|
| 1549 |
+
"learning_rate": 1.544448447995773e-06,
|
| 1550 |
+
"loss": 0.033633843064308167,
|
| 1551 |
+
"step": 4220
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.580821917808219,
|
| 1555 |
+
"grad_norm": 0.1472434103488922,
|
| 1556 |
+
"learning_rate": 1.52135380628137e-06,
|
| 1557 |
+
"loss": 0.036797890067100526,
|
| 1558 |
+
"step": 4240
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.5929984779299846,
|
| 1562 |
+
"grad_norm": 0.5788060426712036,
|
| 1563 |
+
"learning_rate": 1.498357377734201e-06,
|
| 1564 |
+
"loss": 0.039166563749313356,
|
| 1565 |
+
"step": 4260
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.60517503805175,
|
| 1569 |
+
"grad_norm": 0.7623679637908936,
|
| 1570 |
+
"learning_rate": 1.4754614701873703e-06,
|
| 1571 |
+
"loss": 0.03717599511146545,
|
| 1572 |
+
"step": 4280
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.6173515981735163,
|
| 1576 |
+
"grad_norm": 0.16205403208732605,
|
| 1577 |
+
"learning_rate": 1.4526683813860792e-06,
|
| 1578 |
+
"loss": 0.03962793946266174,
|
| 1579 |
+
"step": 4300
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.6295281582952814,
|
| 1583 |
+
"grad_norm": 0.11986076086759567,
|
| 1584 |
+
"learning_rate": 1.4299803987570396e-06,
|
| 1585 |
+
"loss": 0.035475924611091614,
|
| 1586 |
+
"step": 4320
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.6417047184170475,
|
| 1590 |
+
"grad_norm": 0.15573006868362427,
|
| 1591 |
+
"learning_rate": 1.4073997991789078e-06,
|
| 1592 |
+
"loss": 0.03256964683532715,
|
| 1593 |
+
"step": 4340
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.6538812785388126,
|
| 1597 |
+
"grad_norm": 0.25151512026786804,
|
| 1598 |
+
"learning_rate": 1.384928848753792e-06,
|
| 1599 |
+
"loss": 0.03712306022644043,
|
| 1600 |
+
"step": 4360
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.6660578386605787,
|
| 1604 |
+
"grad_norm": 0.20408153533935547,
|
| 1605 |
+
"learning_rate": 1.3625698025798322e-06,
|
| 1606 |
+
"loss": 0.041410398483276364,
|
| 1607 |
+
"step": 4380
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.678234398782344,
|
| 1611 |
+
"grad_norm": 0.3156696856021881,
|
| 1612 |
+
"learning_rate": 1.3403249045248907e-06,
|
| 1613 |
+
"loss": 0.03158504366874695,
|
| 1614 |
+
"step": 4400
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.69041095890411,
|
| 1618 |
+
"grad_norm": 0.3835665285587311,
|
| 1619 |
+
"learning_rate": 1.3181963870013604e-06,
|
| 1620 |
+
"loss": 0.03525224924087524,
|
| 1621 |
+
"step": 4420
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.702587519025875,
|
| 1625 |
+
"grad_norm": 0.45423486828804016,
|
| 1626 |
+
"learning_rate": 1.2961864707421345e-06,
|
| 1627 |
+
"loss": 0.03239959478378296,
|
| 1628 |
+
"step": 4440
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.714764079147641,
|
| 1632 |
+
"grad_norm": 0.15982766449451447,
|
| 1633 |
+
"learning_rate": 1.2742973645777394e-06,
|
| 1634 |
+
"loss": 0.031032082438468934,
|
| 1635 |
+
"step": 4460
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.726940639269406,
|
| 1639 |
+
"grad_norm": 0.2770426869392395,
|
| 1640 |
+
"learning_rate": 1.252531265214662e-06,
|
| 1641 |
+
"loss": 0.030566230416297913,
|
| 1642 |
+
"step": 4480
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.7391171993911723,
|
| 1646 |
+
"grad_norm": 0.3693839907646179,
|
| 1647 |
+
"learning_rate": 1.2308903570149048e-06,
|
| 1648 |
+
"loss": 0.041362547874450685,
|
| 1649 |
+
"step": 4500
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.7391171993911723,
|
| 1653 |
+
"eval_loss": 0.3391737937927246,
|
| 1654 |
+
"eval_runtime": 46.9306,
|
| 1655 |
+
"eval_samples_per_second": 18.751,
|
| 1656 |
+
"eval_steps_per_second": 18.751,
|
| 1657 |
+
"step": 4500
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 2.7512937595129374,
|
| 1661 |
+
"grad_norm": 0.3229275643825531,
|
| 1662 |
+
"learning_rate": 1.2093768117767613e-06,
|
| 1663 |
+
"loss": 0.0388390064239502,
|
| 1664 |
+
"step": 4520
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 2.7634703196347035,
|
| 1668 |
+
"grad_norm": 0.6786078214645386,
|
| 1669 |
+
"learning_rate": 1.1879927885168733e-06,
|
| 1670 |
+
"loss": 0.032555675506591795,
|
| 1671 |
+
"step": 4540
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.7756468797564686,
|
| 1675 |
+
"grad_norm": 0.32371029257774353,
|
| 1676 |
+
"learning_rate": 1.1667404332535504e-06,
|
| 1677 |
+
"loss": 0.03606459796428681,
|
| 1678 |
+
"step": 4560
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.7878234398782347,
|
| 1682 |
+
"grad_norm": 0.44066882133483887,
|
| 1683 |
+
"learning_rate": 1.1456218787914128e-06,
|
| 1684 |
+
"loss": 0.032086309790611264,
|
| 1685 |
+
"step": 4580
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 2.8,
|
| 1689 |
+
"grad_norm": 0.5005165338516235,
|
| 1690 |
+
"learning_rate": 1.1246392445073438e-06,
|
| 1691 |
+
"loss": 0.033362787961959836,
|
| 1692 |
+
"step": 4600
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 2.812176560121766,
|
| 1696 |
+
"grad_norm": 0.22586822509765625,
|
| 1697 |
+
"learning_rate": 1.1037946361378027e-06,
|
| 1698 |
+
"loss": 0.03638745844364166,
|
| 1699 |
+
"step": 4620
|
| 1700 |
+
},
|
| 1701 |
+
{
|
| 1702 |
+
"epoch": 2.824353120243531,
|
| 1703 |
+
"grad_norm": 0.2905796766281128,
|
| 1704 |
+
"learning_rate": 1.0830901455674977e-06,
|
| 1705 |
+
"loss": 0.030933958292007447,
|
| 1706 |
+
"step": 4640
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 2.836529680365297,
|
| 1710 |
+
"grad_norm": 0.10796497762203217,
|
| 1711 |
+
"learning_rate": 1.0625278506194538e-06,
|
| 1712 |
+
"loss": 0.02879139482975006,
|
| 1713 |
+
"step": 4660
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 2.8487062404870622,
|
| 1717 |
+
"grad_norm": 0.2545916438102722,
|
| 1718 |
+
"learning_rate": 1.04210981484649e-06,
|
| 1719 |
+
"loss": 0.03345020413398743,
|
| 1720 |
+
"step": 4680
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 2.8608828006088283,
|
| 1724 |
+
"grad_norm": 0.2986568808555603,
|
| 1725 |
+
"learning_rate": 1.0218380873241314e-06,
|
| 1726 |
+
"loss": 0.02593054175376892,
|
| 1727 |
+
"step": 4700
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 2.8730593607305934,
|
| 1731 |
+
"grad_norm": 0.1755756139755249,
|
| 1732 |
+
"learning_rate": 1.0017147024449674e-06,
|
| 1733 |
+
"loss": 0.03906567096710205,
|
| 1734 |
+
"step": 4720
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 2.8852359208523595,
|
| 1738 |
+
"grad_norm": 0.18288888037204742,
|
| 1739 |
+
"learning_rate": 9.81741679714493e-07,
|
| 1740 |
+
"loss": 0.03371626436710358,
|
| 1741 |
+
"step": 4740
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 2.8974124809741246,
|
| 1745 |
+
"grad_norm": 0.368429958820343,
|
| 1746 |
+
"learning_rate": 9.619210235484333e-07,
|
| 1747 |
+
"loss": 0.03090968132019043,
|
| 1748 |
+
"step": 4760
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 2.9095890410958907,
|
| 1752 |
+
"grad_norm": 0.17118144035339355,
|
| 1753 |
+
"learning_rate": 9.422547230715931e-07,
|
| 1754 |
+
"loss": 0.0322105199098587,
|
| 1755 |
+
"step": 4780
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 2.921765601217656,
|
| 1759 |
+
"grad_norm": 0.41911277174949646,
|
| 1760 |
+
"learning_rate": 9.227447519182353e-07,
|
| 1761 |
+
"loss": 0.035210177302360535,
|
| 1762 |
+
"step": 4800
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 2.933942161339422,
|
| 1766 |
+
"grad_norm": 0.3521968722343445,
|
| 1767 |
+
"learning_rate": 9.033930680340097e-07,
|
| 1768 |
+
"loss": 0.026842504739761353,
|
| 1769 |
+
"step": 4820
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.946118721461187,
|
| 1773 |
+
"grad_norm": 0.20812013745307922,
|
| 1774 |
+
"learning_rate": 8.842016134794682e-07,
|
| 1775 |
+
"loss": 0.03439584076404571,
|
| 1776 |
+
"step": 4840
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 2.958295281582953,
|
| 1780 |
+
"grad_norm": 0.2796875834465027,
|
| 1781 |
+
"learning_rate": 8.651723142351603e-07,
|
| 1782 |
+
"loss": 0.04011322855949402,
|
| 1783 |
+
"step": 4860
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 2.9704718417047182,
|
| 1787 |
+
"grad_norm": 0.20960687100887299,
|
| 1788 |
+
"learning_rate": 8.463070800083562e-07,
|
| 1789 |
+
"loss": 0.03800423145294189,
|
| 1790 |
+
"step": 4880
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.9826484018264843,
|
| 1794 |
+
"grad_norm": 0.2586495876312256,
|
| 1795 |
+
"learning_rate": 8.276078040413879e-07,
|
| 1796 |
+
"loss": 0.03839131891727447,
|
| 1797 |
+
"step": 4900
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 2.9948249619482494,
|
| 1801 |
+
"grad_norm": 0.37137141823768616,
|
| 1802 |
+
"learning_rate": 8.090763629216589e-07,
|
| 1803 |
+
"loss": 0.02721840739250183,
|
| 1804 |
+
"step": 4920
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 3.006697108066971,
|
| 1808 |
+
"grad_norm": 0.3677407503128052,
|
| 1809 |
+
"learning_rate": 7.907146163933102e-07,
|
| 1810 |
+
"loss": 0.023991990089416503,
|
| 1811 |
+
"step": 4940
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 3.0188736681887365,
|
| 1815 |
+
"grad_norm": 0.11811063438653946,
|
| 1816 |
+
"learning_rate": 7.725244071705871e-07,
|
| 1817 |
+
"loss": 0.01451514959335327,
|
| 1818 |
+
"step": 4960
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 3.031050228310502,
|
| 1822 |
+
"grad_norm": 0.3449067771434784,
|
| 1823 |
+
"learning_rate": 7.545075607529104e-07,
|
| 1824 |
+
"loss": 0.014327619969844819,
|
| 1825 |
+
"step": 4980
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 3.0432267884322677,
|
| 1829 |
+
"grad_norm": 0.3237353265285492,
|
| 1830 |
+
"learning_rate": 7.366658852416788e-07,
|
| 1831 |
+
"loss": 0.017832010984420776,
|
| 1832 |
+
"step": 5000
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 3.0432267884322677,
|
| 1836 |
+
"eval_loss": 0.39115142822265625,
|
| 1837 |
+
"eval_runtime": 47.6431,
|
| 1838 |
+
"eval_samples_per_second": 18.471,
|
| 1839 |
+
"eval_steps_per_second": 18.471,
|
| 1840 |
+
"step": 5000
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 3.0554033485540333,
|
| 1844 |
+
"grad_norm": 0.2226281613111496,
|
| 1845 |
+
"learning_rate": 7.190011711588101e-07,
|
| 1846 |
+
"loss": 0.011674411594867706,
|
| 1847 |
+
"step": 5020
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 3.067579908675799,
|
| 1851 |
+
"grad_norm": 0.08729376643896103,
|
| 1852 |
+
"learning_rate": 7.015151912670562e-07,
|
| 1853 |
+
"loss": 0.013690856099128724,
|
| 1854 |
+
"step": 5040
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 3.0797564687975645,
|
| 1858 |
+
"grad_norm": 0.2745465636253357,
|
| 1859 |
+
"learning_rate": 6.842097003920903e-07,
|
| 1860 |
+
"loss": 0.011978642642498016,
|
| 1861 |
+
"step": 5060
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 3.09193302891933,
|
| 1865 |
+
"grad_norm": 0.06905842572450638,
|
| 1866 |
+
"learning_rate": 6.67086435246406e-07,
|
| 1867 |
+
"loss": 0.013893941044807434,
|
| 1868 |
+
"step": 5080
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 3.1041095890410957,
|
| 1872 |
+
"grad_norm": 0.07840315997600555,
|
| 1873 |
+
"learning_rate": 6.501471142550194e-07,
|
| 1874 |
+
"loss": 0.009910025447607041,
|
| 1875 |
+
"step": 5100
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 3.1162861491628613,
|
| 1879 |
+
"grad_norm": 0.19672124087810516,
|
| 1880 |
+
"learning_rate": 6.333934373830222e-07,
|
| 1881 |
+
"loss": 0.008863755315542222,
|
| 1882 |
+
"step": 5120
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 3.128462709284627,
|
| 1886 |
+
"grad_norm": 0.37645605206489563,
|
| 1887 |
+
"learning_rate": 6.168270859649761e-07,
|
| 1888 |
+
"loss": 0.010502541810274124,
|
| 1889 |
+
"step": 5140
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 3.1406392694063925,
|
| 1893 |
+
"grad_norm": 0.2069159746170044,
|
| 1894 |
+
"learning_rate": 6.004497225361786e-07,
|
| 1895 |
+
"loss": 0.012096930295228958,
|
| 1896 |
+
"step": 5160
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 3.1528158295281585,
|
| 1900 |
+
"grad_norm": 0.2584017217159271,
|
| 1901 |
+
"learning_rate": 5.842629906658226e-07,
|
| 1902 |
+
"loss": 0.013278065621852875,
|
| 1903 |
+
"step": 5180
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 3.1649923896499237,
|
| 1907 |
+
"grad_norm": 0.2050527036190033,
|
| 1908 |
+
"learning_rate": 5.682685147920481e-07,
|
| 1909 |
+
"loss": 0.013548998534679413,
|
| 1910 |
+
"step": 5200
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 3.1771689497716897,
|
| 1914 |
+
"grad_norm": 0.13838107883930206,
|
| 1915 |
+
"learning_rate": 5.524679000589256e-07,
|
| 1916 |
+
"loss": 0.013736458122730255,
|
| 1917 |
+
"step": 5220
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 3.189345509893455,
|
| 1921 |
+
"grad_norm": 0.06378225982189178,
|
| 1922 |
+
"learning_rate": 5.36862732155366e-07,
|
| 1923 |
+
"loss": 0.013177134096622467,
|
| 1924 |
+
"step": 5240
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 3.201522070015221,
|
| 1928 |
+
"grad_norm": 0.27431613206863403,
|
| 1929 |
+
"learning_rate": 5.214545771559879e-07,
|
| 1930 |
+
"loss": 0.011971819400787353,
|
| 1931 |
+
"step": 5260
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 3.213698630136986,
|
| 1935 |
+
"grad_norm": 0.529901921749115,
|
| 1936 |
+
"learning_rate": 5.062449813639528e-07,
|
| 1937 |
+
"loss": 0.014422819018363953,
|
| 1938 |
+
"step": 5280
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 3.225875190258752,
|
| 1942 |
+
"grad_norm": 0.19417761266231537,
|
| 1943 |
+
"learning_rate": 4.912354711557856e-07,
|
| 1944 |
+
"loss": 0.010663678497076034,
|
| 1945 |
+
"step": 5300
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 3.2380517503805173,
|
| 1949 |
+
"grad_norm": 0.044735077768564224,
|
| 1950 |
+
"learning_rate": 4.764275528281892e-07,
|
| 1951 |
+
"loss": 0.011400717496871948,
|
| 1952 |
+
"step": 5320
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 3.2502283105022833,
|
| 1956 |
+
"grad_norm": 0.057179443538188934,
|
| 1957 |
+
"learning_rate": 4.6182271244688355e-07,
|
| 1958 |
+
"loss": 0.008456526696681977,
|
| 1959 |
+
"step": 5340
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 3.2624048706240485,
|
| 1963 |
+
"grad_norm": 0.10396906733512878,
|
| 1964 |
+
"learning_rate": 4.4742241569746407e-07,
|
| 1965 |
+
"loss": 0.014539115130901337,
|
| 1966 |
+
"step": 5360
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 3.2745814307458145,
|
| 1970 |
+
"grad_norm": 0.32904428243637085,
|
| 1971 |
+
"learning_rate": 4.332281077383177e-07,
|
| 1972 |
+
"loss": 0.017625690996646882,
|
| 1973 |
+
"step": 5380
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 3.2867579908675797,
|
| 1977 |
+
"grad_norm": 0.20823979377746582,
|
| 1978 |
+
"learning_rate": 4.1924121305558563e-07,
|
| 1979 |
+
"loss": 0.007641100138425827,
|
| 1980 |
+
"step": 5400
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 3.2989345509893457,
|
| 1984 |
+
"grad_norm": 0.25470009446144104,
|
| 1985 |
+
"learning_rate": 4.054631353202121e-07,
|
| 1986 |
+
"loss": 0.011799700558185577,
|
| 1987 |
+
"step": 5420
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 3.311111111111111,
|
| 1991 |
+
"grad_norm": 0.3968588709831238,
|
| 1992 |
+
"learning_rate": 3.9189525724707634e-07,
|
| 1993 |
+
"loss": 0.011455408483743667,
|
| 1994 |
+
"step": 5440
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 3.323287671232877,
|
| 1998 |
+
"grad_norm": 0.10818332433700562,
|
| 1999 |
+
"learning_rate": 3.785389404562259e-07,
|
| 2000 |
+
"loss": 0.012499115616083144,
|
| 2001 |
+
"step": 5460
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 3.335464231354642,
|
| 2005 |
+
"grad_norm": 0.1818460375070572,
|
| 2006 |
+
"learning_rate": 3.653955253362351e-07,
|
| 2007 |
+
"loss": 0.01148865669965744,
|
| 2008 |
+
"step": 5480
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 3.347640791476408,
|
| 2012 |
+
"grad_norm": 0.3504088521003723,
|
| 2013 |
+
"learning_rate": 3.5246633090968205e-07,
|
| 2014 |
+
"loss": 0.012819178402423859,
|
| 2015 |
+
"step": 5500
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 3.347640791476408,
|
| 2019 |
+
"eval_loss": 0.43404534459114075,
|
| 2020 |
+
"eval_runtime": 46.4882,
|
| 2021 |
+
"eval_samples_per_second": 18.93,
|
| 2022 |
+
"eval_steps_per_second": 18.93,
|
| 2023 |
+
"step": 5500
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 3.3598173515981733,
|
| 2027 |
+
"grad_norm": 0.4551874101161957,
|
| 2028 |
+
"learning_rate": 3.397526547007832e-07,
|
| 2029 |
+
"loss": 0.013325585424900055,
|
| 2030 |
+
"step": 5520
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 3.3719939117199393,
|
| 2034 |
+
"grad_norm": 0.35187825560569763,
|
| 2035 |
+
"learning_rate": 3.2725577260517396e-07,
|
| 2036 |
+
"loss": 0.011712662875652313,
|
| 2037 |
+
"step": 5540
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 3.3841704718417045,
|
| 2041 |
+
"grad_norm": 0.6071529984474182,
|
| 2042 |
+
"learning_rate": 3.14976938761867e-07,
|
| 2043 |
+
"loss": 0.01580573171377182,
|
| 2044 |
+
"step": 5560
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 3.3963470319634705,
|
| 2048 |
+
"grad_norm": 0.18844422698020935,
|
| 2049 |
+
"learning_rate": 3.029173854273909e-07,
|
| 2050 |
+
"loss": 0.012312603741884231,
|
| 2051 |
+
"step": 5580
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 3.4085235920852357,
|
| 2055 |
+
"grad_norm": 0.13131535053253174,
|
| 2056 |
+
"learning_rate": 2.910783228521269e-07,
|
| 2057 |
+
"loss": 0.011797953397035599,
|
| 2058 |
+
"step": 5600
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 3.4207001522070017,
|
| 2062 |
+
"grad_norm": 0.4402364492416382,
|
| 2063 |
+
"learning_rate": 2.794609391588504e-07,
|
| 2064 |
+
"loss": 0.012182456254959107,
|
| 2065 |
+
"step": 5620
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 3.432876712328767,
|
| 2069 |
+
"grad_norm": 0.3497592508792877,
|
| 2070 |
+
"learning_rate": 2.6806640022349897e-07,
|
| 2071 |
+
"loss": 0.013599888980388641,
|
| 2072 |
+
"step": 5640
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 3.445053272450533,
|
| 2076 |
+
"grad_norm": 0.2316354215145111,
|
| 2077 |
+
"learning_rate": 2.5689584955816497e-07,
|
| 2078 |
+
"loss": 0.009272868931293487,
|
| 2079 |
+
"step": 5660
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 3.457229832572298,
|
| 2083 |
+
"grad_norm": 0.3858301341533661,
|
| 2084 |
+
"learning_rate": 2.459504081963421e-07,
|
| 2085 |
+
"loss": 0.008165979385375976,
|
| 2086 |
+
"step": 5680
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 3.469406392694064,
|
| 2090 |
+
"grad_norm": 0.14734333753585815,
|
| 2091 |
+
"learning_rate": 2.3523117458041865e-07,
|
| 2092 |
+
"loss": 0.009182130545377731,
|
| 2093 |
+
"step": 5700
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 3.4815829528158293,
|
| 2097 |
+
"grad_norm": 0.03280401974916458,
|
| 2098 |
+
"learning_rate": 2.2473922445144485e-07,
|
| 2099 |
+
"loss": 0.0107998326420784,
|
| 2100 |
+
"step": 5720
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 3.4937595129375953,
|
| 2104 |
+
"grad_norm": 0.1505511999130249,
|
| 2105 |
+
"learning_rate": 2.144756107411733e-07,
|
| 2106 |
+
"loss": 0.014469687640666962,
|
| 2107 |
+
"step": 5740
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 3.5059360730593605,
|
| 2111 |
+
"grad_norm": 0.2366904318332672,
|
| 2112 |
+
"learning_rate": 2.0444136346639333e-07,
|
| 2113 |
+
"loss": 0.0121701680123806,
|
| 2114 |
+
"step": 5760
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 3.5181126331811265,
|
| 2118 |
+
"grad_norm": 0.1468425989151001,
|
| 2119 |
+
"learning_rate": 1.9463748962556096e-07,
|
| 2120 |
+
"loss": 0.014668506383895875,
|
| 2121 |
+
"step": 5780
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 3.5302891933028917,
|
| 2125 |
+
"grad_norm": 0.14534050226211548,
|
| 2126 |
+
"learning_rate": 1.8506497309773885e-07,
|
| 2127 |
+
"loss": 0.010488402843475342,
|
| 2128 |
+
"step": 5800
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 3.5424657534246577,
|
| 2132 |
+
"grad_norm": 0.15501493215560913,
|
| 2133 |
+
"learning_rate": 1.7572477454386257e-07,
|
| 2134 |
+
"loss": 0.010667071491479874,
|
| 2135 |
+
"step": 5820
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 3.554642313546423,
|
| 2139 |
+
"grad_norm": 0.26535800099372864,
|
| 2140 |
+
"learning_rate": 1.6661783131032726e-07,
|
| 2141 |
+
"loss": 0.011079683899879456,
|
| 2142 |
+
"step": 5840
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 3.566818873668189,
|
| 2146 |
+
"grad_norm": 0.24390950798988342,
|
| 2147 |
+
"learning_rate": 1.5774505733492263e-07,
|
| 2148 |
+
"loss": 0.009308797866106033,
|
| 2149 |
+
"step": 5860
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 3.578995433789954,
|
| 2153 |
+
"grad_norm": 0.3409421443939209,
|
| 2154 |
+
"learning_rate": 1.49107343055111e-07,
|
| 2155 |
+
"loss": 0.012319787591695785,
|
| 2156 |
+
"step": 5880
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 3.59117199391172,
|
| 2160 |
+
"grad_norm": 0.4800300896167755,
|
| 2161 |
+
"learning_rate": 1.407055553186701e-07,
|
| 2162 |
+
"loss": 0.00843576118350029,
|
| 2163 |
+
"step": 5900
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 3.6033485540334853,
|
| 2167 |
+
"grad_norm": 0.11663182079792023,
|
| 2168 |
+
"learning_rate": 1.3254053729669564e-07,
|
| 2169 |
+
"loss": 0.00938587412238121,
|
| 2170 |
+
"step": 5920
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 3.6155251141552514,
|
| 2174 |
+
"grad_norm": 0.29512378573417664,
|
| 2175 |
+
"learning_rate": 1.2461310839898656e-07,
|
| 2176 |
+
"loss": 0.011934128403663636,
|
| 2177 |
+
"step": 5940
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 3.6277016742770165,
|
| 2181 |
+
"grad_norm": 0.2641650140285492,
|
| 2182 |
+
"learning_rate": 1.169240641918104e-07,
|
| 2183 |
+
"loss": 0.013170333206653595,
|
| 2184 |
+
"step": 5960
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 3.6398782343987826,
|
| 2188 |
+
"grad_norm": 0.47704726457595825,
|
| 2189 |
+
"learning_rate": 1.0947417631806539e-07,
|
| 2190 |
+
"loss": 0.014534834027290344,
|
| 2191 |
+
"step": 5980
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 3.6520547945205477,
|
| 2195 |
+
"grad_norm": 0.10114685446023941,
|
| 2196 |
+
"learning_rate": 1.0226419241983865e-07,
|
| 2197 |
+
"loss": 0.011021688580513,
|
| 2198 |
+
"step": 6000
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 3.6520547945205477,
|
| 2202 |
+
"eval_loss": 0.44063475728034973,
|
| 2203 |
+
"eval_runtime": 46.1734,
|
| 2204 |
+
"eval_samples_per_second": 19.059,
|
| 2205 |
+
"eval_steps_per_second": 19.059,
|
| 2206 |
+
"step": 6000
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 3.6642313546423138,
|
| 2210 |
+
"grad_norm": 0.2619183659553528,
|
| 2211 |
+
"learning_rate": 9.529483606337902e-08,
|
| 2212 |
+
"loss": 0.010764393210411071,
|
| 2213 |
+
"step": 6020
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 3.676407914764079,
|
| 2217 |
+
"grad_norm": 0.05733129009604454,
|
| 2218 |
+
"learning_rate": 8.856680666647882e-08,
|
| 2219 |
+
"loss": 0.012128306180238723,
|
| 2220 |
+
"step": 6040
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 3.688584474885845,
|
| 2224 |
+
"grad_norm": 0.19483673572540283,
|
| 2225 |
+
"learning_rate": 8.208077942828713e-08,
|
| 2226 |
+
"loss": 0.011729901283979416,
|
| 2227 |
+
"step": 6060
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 3.70076103500761,
|
| 2231 |
+
"grad_norm": 0.2111903578042984,
|
| 2232 |
+
"learning_rate": 7.58374052615457e-08,
|
| 2233 |
+
"loss": 0.009119105339050294,
|
| 2234 |
+
"step": 6080
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 3.712937595129376,
|
| 2238 |
+
"grad_norm": 0.04995311424136162,
|
| 2239 |
+
"learning_rate": 6.983731072726818e-08,
|
| 2240 |
+
"loss": 0.017101363837718965,
|
| 2241 |
+
"step": 6100
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 3.7251141552511413,
|
| 2245 |
+
"grad_norm": 0.5839787125587463,
|
| 2246 |
+
"learning_rate": 6.408109797186118e-08,
|
| 2247 |
+
"loss": 0.012368235737085342,
|
| 2248 |
+
"step": 6120
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 3.7372907153729074,
|
| 2252 |
+
"grad_norm": 0.4685717523097992,
|
| 2253 |
+
"learning_rate": 5.856934466669212e-08,
|
| 2254 |
+
"loss": 0.008782628178596496,
|
| 2255 |
+
"step": 6140
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 3.7494672754946725,
|
| 2259 |
+
"grad_norm": 0.17204681038856506,
|
| 2260 |
+
"learning_rate": 5.3302603950119994e-08,
|
| 2261 |
+
"loss": 0.008994438499212266,
|
| 2262 |
+
"step": 6160
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 3.7616438356164386,
|
| 2266 |
+
"grad_norm": 0.07392167299985886,
|
| 2267 |
+
"learning_rate": 4.8281404371981755e-08,
|
| 2268 |
+
"loss": 0.011286454647779465,
|
| 2269 |
+
"step": 6180
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 3.7738203957382037,
|
| 2273 |
+
"grad_norm": 0.3728208541870117,
|
| 2274 |
+
"learning_rate": 4.350624984055196e-08,
|
| 2275 |
+
"loss": 0.011785905063152313,
|
| 2276 |
+
"step": 6200
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 3.7859969558599698,
|
| 2280 |
+
"grad_norm": 0.25468680262565613,
|
| 2281 |
+
"learning_rate": 3.897761957196877e-08,
|
| 2282 |
+
"loss": 0.013624191284179688,
|
| 2283 |
+
"step": 6220
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 3.798173515981735,
|
| 2287 |
+
"grad_norm": 0.09725204110145569,
|
| 2288 |
+
"learning_rate": 3.469596804214548e-08,
|
| 2289 |
+
"loss": 0.011700452119112015,
|
| 2290 |
+
"step": 6240
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 3.810350076103501,
|
| 2294 |
+
"grad_norm": 0.07126162946224213,
|
| 2295 |
+
"learning_rate": 3.06617249411581e-08,
|
| 2296 |
+
"loss": 0.011029987037181855,
|
| 2297 |
+
"step": 6260
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 3.822526636225266,
|
| 2301 |
+
"grad_norm": 0.08542267978191376,
|
| 2302 |
+
"learning_rate": 2.687529513012488e-08,
|
| 2303 |
+
"loss": 0.010965974628925323,
|
| 2304 |
+
"step": 6280
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 3.834703196347032,
|
| 2308 |
+
"grad_norm": 0.2627331018447876,
|
| 2309 |
+
"learning_rate": 2.3337058600575722e-08,
|
| 2310 |
+
"loss": 0.012378603965044022,
|
| 2311 |
+
"step": 6300
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 3.8468797564687973,
|
| 2315 |
+
"grad_norm": 0.19707690179347992,
|
| 2316 |
+
"learning_rate": 2.0047370436317437e-08,
|
| 2317 |
+
"loss": 0.011792077124118805,
|
| 2318 |
+
"step": 6320
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 3.8590563165905634,
|
| 2322 |
+
"grad_norm": 0.47547003626823425,
|
| 2323 |
+
"learning_rate": 1.7006560777798608e-08,
|
| 2324 |
+
"loss": 0.01145942509174347,
|
| 2325 |
+
"step": 6340
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 3.8712328767123285,
|
| 2329 |
+
"grad_norm": 0.3591565489768982,
|
| 2330 |
+
"learning_rate": 1.421493478897945e-08,
|
| 2331 |
+
"loss": 0.011088228970766067,
|
| 2332 |
+
"step": 6360
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 3.8834094368340946,
|
| 2336 |
+
"grad_norm": 0.20619548857212067,
|
| 2337 |
+
"learning_rate": 1.1672772626704909e-08,
|
| 2338 |
+
"loss": 0.010828402638435364,
|
| 2339 |
+
"step": 6380
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 3.8955859969558597,
|
| 2343 |
+
"grad_norm": 0.2822403311729431,
|
| 2344 |
+
"learning_rate": 9.38032941258965e-09,
|
| 2345 |
+
"loss": 0.01165580153465271,
|
| 2346 |
+
"step": 6400
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 3.9077625570776258,
|
| 2350 |
+
"grad_norm": 0.15682674944400787,
|
| 2351 |
+
"learning_rate": 7.3378352074163215e-09,
|
| 2352 |
+
"loss": 0.010783226788043975,
|
| 2353 |
+
"step": 6420
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 3.919939117199391,
|
| 2357 |
+
"grad_norm": 0.34253379702568054,
|
| 2358 |
+
"learning_rate": 5.545494988045963e-09,
|
| 2359 |
+
"loss": 0.011295531690120698,
|
| 2360 |
+
"step": 6440
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 3.932115677321157,
|
| 2364 |
+
"grad_norm": 0.27684664726257324,
|
| 2365 |
+
"learning_rate": 4.003488626848073e-09,
|
| 2366 |
+
"loss": 0.013613662123680115,
|
| 2367 |
+
"step": 6460
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 3.944292237442922,
|
| 2371 |
+
"grad_norm": 0.69688880443573,
|
| 2372 |
+
"learning_rate": 2.7119708736486615e-09,
|
| 2373 |
+
"loss": 0.011696261167526246,
|
| 2374 |
+
"step": 6480
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 3.956468797564688,
|
| 2378 |
+
"grad_norm": 0.2617769241333008,
|
| 2379 |
+
"learning_rate": 1.6710713402015577e-09,
|
| 2380 |
+
"loss": 0.010873865336179733,
|
| 2381 |
+
"step": 6500
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 3.956468797564688,
|
| 2385 |
+
"eval_loss": 0.441041499376297,
|
| 2386 |
+
"eval_runtime": 46.1946,
|
| 2387 |
+
"eval_samples_per_second": 19.05,
|
| 2388 |
+
"eval_steps_per_second": 19.05,
|
| 2389 |
+
"step": 6500
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 3.9686453576864533,
|
| 2393 |
+
"grad_norm": 0.23670868575572968,
|
| 2394 |
+
"learning_rate": 8.80894487179651e-10,
|
| 2395 |
+
"loss": 0.012961818277835846,
|
| 2396 |
+
"step": 6520
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 3.9808219178082194,
|
| 2400 |
+
"grad_norm": 1.036125659942627,
|
| 2401 |
+
"learning_rate": 3.4151961369188745e-10,
|
| 2402 |
+
"loss": 0.01224210560321808,
|
| 2403 |
+
"step": 6540
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 3.9929984779299845,
|
| 2407 |
+
"grad_norm": 0.1431870311498642,
|
| 2408 |
+
"learning_rate": 5.300084932574612e-11,
|
| 2409 |
+
"loss": 0.010245455056428909,
|
| 2410 |
+
"step": 6560
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 4.0,
|
| 2414 |
+
"step": 6572,
|
| 2415 |
+
"total_flos": 3.545203061907456e+17,
|
| 2416 |
+
"train_loss": 0.08566030774240586,
|
| 2417 |
+
"train_runtime": 13933.4985,
|
| 2418 |
+
"train_samples_per_second": 3.772,
|
| 2419 |
+
"train_steps_per_second": 0.472
|
| 2420 |
+
}
|
| 2421 |
+
],
|
| 2422 |
+
"logging_steps": 20,
|
| 2423 |
+
"max_steps": 6572,
|
| 2424 |
+
"num_input_tokens_seen": 0,
|
| 2425 |
+
"num_train_epochs": 4,
|
| 2426 |
+
"save_steps": 500,
|
| 2427 |
+
"stateful_callbacks": {
|
| 2428 |
+
"TrainerControl": {
|
| 2429 |
+
"args": {
|
| 2430 |
+
"should_epoch_stop": false,
|
| 2431 |
+
"should_evaluate": false,
|
| 2432 |
+
"should_log": false,
|
| 2433 |
+
"should_save": true,
|
| 2434 |
+
"should_training_stop": true
|
| 2435 |
+
},
|
| 2436 |
+
"attributes": {}
|
| 2437 |
+
}
|
| 2438 |
+
},
|
| 2439 |
+
"total_flos": 3.545203061907456e+17,
|
| 2440 |
+
"train_batch_size": 1,
|
| 2441 |
+
"trial_name": null,
|
| 2442 |
+
"trial_params": null
|
| 2443 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c8f0bbe96b1bd3b42d30bb419fc0c08037dc014a4a8cea153b553983982dd1
|
| 3 |
+
size 5585
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|