Training in progress, epoch 2, checkpoint
Browse files- checkpoint-363/README.md +202 -0
- checkpoint-363/adapter_config.json +37 -0
- checkpoint-363/adapter_model.safetensors +3 -0
- checkpoint-363/added_tokens.json +4 -0
- checkpoint-363/optimizer.pt +3 -0
- checkpoint-363/rng_state.pth +3 -0
- checkpoint-363/scheduler.pt +3 -0
- checkpoint-363/special_tokens_map.json +30 -0
- checkpoint-363/tokenizer.model +3 -0
- checkpoint-363/tokenizer_config.json +59 -0
- checkpoint-363/trainer_state.json +2622 -0
- checkpoint-363/training_args.bin +3 -0
checkpoint-363/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: NousResearch/Llama-2-7b-hf
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.11.1
|
checkpoint-363/adapter_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"embed_tokens",
|
| 19 |
+
"lm_head"
|
| 20 |
+
],
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"q_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"v_proj"
|
| 33 |
+
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
+
}
|
checkpoint-363/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c14c739e99cda1cb887844f4670cb6fb9b40fc5842cad300609f304c0c1262fd
|
| 3 |
+
size 1892839096
|
checkpoint-363/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[/INST]": 32001,
|
| 3 |
+
"[INST]": 32000
|
| 4 |
+
}
|
checkpoint-363/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c63d34ac2c57ad38d03f48209794da0730ba6f3dd10dc623bddaed2215a7a62a
|
| 3 |
+
size 686083612
|
checkpoint-363/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91eacfb251a5cb0f6676f9ad63e2177c620ed0ae6166eebbf1f92beed9de4710
|
| 3 |
+
size 14244
|
checkpoint-363/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03b66f79cab0e63cf08301118e3f23fa5306f8f40fe9d921423b026a74a621ef
|
| 3 |
+
size 1064
|
checkpoint-363/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-363/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-363/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[INST]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "[/INST]",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"bos_token": "<s>",
|
| 48 |
+
"clean_up_tokenization_spaces": false,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"legacy": false,
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<unk>",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 56 |
+
"unk_token": "<unk>",
|
| 57 |
+
"use_default_system_prompt": false,
|
| 58 |
+
"use_fast": true
|
| 59 |
+
}
|
checkpoint-363/trainer_state.json
ADDED
|
@@ -0,0 +1,2622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.97319587628866,
|
| 5 |
+
"eval_steps": 61,
|
| 6 |
+
"global_step": 363,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008247422680412371,
|
| 13 |
+
"grad_norm": 2.2737574577331543,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 1.0155,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008247422680412371,
|
| 20 |
+
"eval_loss": 1.2302311658859253,
|
| 21 |
+
"eval_runtime": 295.4772,
|
| 22 |
+
"eval_samples_per_second": 2.031,
|
| 23 |
+
"eval_steps_per_second": 1.015,
|
| 24 |
+
"step": 1
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.016494845360824743,
|
| 28 |
+
"grad_norm": 2.203125476837158,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 1.1137,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.024742268041237112,
|
| 35 |
+
"grad_norm": 1.7233558893203735,
|
| 36 |
+
"learning_rate": 6e-05,
|
| 37 |
+
"loss": 0.9453,
|
| 38 |
+
"step": 3
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.032989690721649485,
|
| 42 |
+
"grad_norm": 2.38301420211792,
|
| 43 |
+
"learning_rate": 8e-05,
|
| 44 |
+
"loss": 1.1091,
|
| 45 |
+
"step": 4
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.041237113402061855,
|
| 49 |
+
"grad_norm": 1.6754157543182373,
|
| 50 |
+
"learning_rate": 0.0001,
|
| 51 |
+
"loss": 0.9209,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.049484536082474224,
|
| 56 |
+
"grad_norm": 1.6663925647735596,
|
| 57 |
+
"learning_rate": 0.00012,
|
| 58 |
+
"loss": 0.9145,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0577319587628866,
|
| 63 |
+
"grad_norm": 1.6516679525375366,
|
| 64 |
+
"learning_rate": 0.00014,
|
| 65 |
+
"loss": 0.8456,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06597938144329897,
|
| 70 |
+
"grad_norm": 1.4858132600784302,
|
| 71 |
+
"learning_rate": 0.00016,
|
| 72 |
+
"loss": 0.8257,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07422680412371134,
|
| 77 |
+
"grad_norm": 1.2829698324203491,
|
| 78 |
+
"learning_rate": 0.00018,
|
| 79 |
+
"loss": 0.7396,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08247422680412371,
|
| 84 |
+
"grad_norm": 0.8841626644134521,
|
| 85 |
+
"learning_rate": 0.0002,
|
| 86 |
+
"loss": 0.6599,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09072164948453608,
|
| 91 |
+
"grad_norm": 0.6680086255073547,
|
| 92 |
+
"learning_rate": 0.0001999960397967811,
|
| 93 |
+
"loss": 0.6368,
|
| 94 |
+
"step": 11
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.09896907216494845,
|
| 98 |
+
"grad_norm": 0.9510122537612915,
|
| 99 |
+
"learning_rate": 0.00019998415950078858,
|
| 100 |
+
"loss": 0.7061,
|
| 101 |
+
"step": 12
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.10721649484536082,
|
| 105 |
+
"grad_norm": 0.8464949131011963,
|
| 106 |
+
"learning_rate": 0.00019996436005299012,
|
| 107 |
+
"loss": 0.6674,
|
| 108 |
+
"step": 13
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1154639175257732,
|
| 112 |
+
"grad_norm": 0.8255585432052612,
|
| 113 |
+
"learning_rate": 0.00019993664302158255,
|
| 114 |
+
"loss": 0.6971,
|
| 115 |
+
"step": 14
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12371134020618557,
|
| 119 |
+
"grad_norm": 0.7613081932067871,
|
| 120 |
+
"learning_rate": 0.00019990101060186733,
|
| 121 |
+
"loss": 0.6621,
|
| 122 |
+
"step": 15
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.13195876288659794,
|
| 126 |
+
"grad_norm": 0.6413361430168152,
|
| 127 |
+
"learning_rate": 0.00019985746561607698,
|
| 128 |
+
"loss": 0.6336,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1402061855670103,
|
| 133 |
+
"grad_norm": 0.7216547727584839,
|
| 134 |
+
"learning_rate": 0.0001998060115131513,
|
| 135 |
+
"loss": 0.7165,
|
| 136 |
+
"step": 17
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14845360824742268,
|
| 140 |
+
"grad_norm": 0.7801871299743652,
|
| 141 |
+
"learning_rate": 0.00019974665236846442,
|
| 142 |
+
"loss": 0.7449,
|
| 143 |
+
"step": 18
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.15670103092783505,
|
| 147 |
+
"grad_norm": 0.6427637338638306,
|
| 148 |
+
"learning_rate": 0.00019967939288350182,
|
| 149 |
+
"loss": 0.6344,
|
| 150 |
+
"step": 19
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.16494845360824742,
|
| 154 |
+
"grad_norm": 0.6753759980201721,
|
| 155 |
+
"learning_rate": 0.00019960423838548814,
|
| 156 |
+
"loss": 0.735,
|
| 157 |
+
"step": 20
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.1731958762886598,
|
| 161 |
+
"grad_norm": 0.6213053464889526,
|
| 162 |
+
"learning_rate": 0.00019952119482696503,
|
| 163 |
+
"loss": 0.6675,
|
| 164 |
+
"step": 21
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18144329896907216,
|
| 168 |
+
"grad_norm": 0.6505969762802124,
|
| 169 |
+
"learning_rate": 0.00019943026878531983,
|
| 170 |
+
"loss": 0.6129,
|
| 171 |
+
"step": 22
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.18969072164948453,
|
| 175 |
+
"grad_norm": 0.6324624419212341,
|
| 176 |
+
"learning_rate": 0.0001993314674622646,
|
| 177 |
+
"loss": 0.6289,
|
| 178 |
+
"step": 23
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1979381443298969,
|
| 182 |
+
"grad_norm": 0.6155864000320435,
|
| 183 |
+
"learning_rate": 0.00019922479868326578,
|
| 184 |
+
"loss": 0.6358,
|
| 185 |
+
"step": 24
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.20618556701030927,
|
| 189 |
+
"grad_norm": 0.6395933628082275,
|
| 190 |
+
"learning_rate": 0.0001991102708969241,
|
| 191 |
+
"loss": 0.6225,
|
| 192 |
+
"step": 25
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.21443298969072164,
|
| 196 |
+
"grad_norm": 0.5889492034912109,
|
| 197 |
+
"learning_rate": 0.00019898789317430575,
|
| 198 |
+
"loss": 0.6674,
|
| 199 |
+
"step": 26
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.22268041237113403,
|
| 203 |
+
"grad_norm": 0.5262942910194397,
|
| 204 |
+
"learning_rate": 0.00019885767520822376,
|
| 205 |
+
"loss": 0.6077,
|
| 206 |
+
"step": 27
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2309278350515464,
|
| 210 |
+
"grad_norm": 0.5878570675849915,
|
| 211 |
+
"learning_rate": 0.0001987196273124703,
|
| 212 |
+
"loss": 0.6145,
|
| 213 |
+
"step": 28
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.23917525773195877,
|
| 217 |
+
"grad_norm": 0.5845457315444946,
|
| 218 |
+
"learning_rate": 0.00019857376042099983,
|
| 219 |
+
"loss": 0.6435,
|
| 220 |
+
"step": 29
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.24742268041237114,
|
| 224 |
+
"grad_norm": 0.6508314609527588,
|
| 225 |
+
"learning_rate": 0.00019842008608706295,
|
| 226 |
+
"loss": 0.6799,
|
| 227 |
+
"step": 30
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.2556701030927835,
|
| 231 |
+
"grad_norm": 0.5770230293273926,
|
| 232 |
+
"learning_rate": 0.00019825861648229152,
|
| 233 |
+
"loss": 0.6092,
|
| 234 |
+
"step": 31
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2639175257731959,
|
| 238 |
+
"grad_norm": 0.5438909530639648,
|
| 239 |
+
"learning_rate": 0.00019808936439573454,
|
| 240 |
+
"loss": 0.5952,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2721649484536082,
|
| 245 |
+
"grad_norm": 0.5276155471801758,
|
| 246 |
+
"learning_rate": 0.00019791234323284513,
|
| 247 |
+
"loss": 0.5899,
|
| 248 |
+
"step": 33
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2804123711340206,
|
| 252 |
+
"grad_norm": 0.6430350542068481,
|
| 253 |
+
"learning_rate": 0.00019772756701441887,
|
| 254 |
+
"loss": 0.6581,
|
| 255 |
+
"step": 34
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.28865979381443296,
|
| 259 |
+
"grad_norm": 0.6087874174118042,
|
| 260 |
+
"learning_rate": 0.0001975350503754833,
|
| 261 |
+
"loss": 0.654,
|
| 262 |
+
"step": 35
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.29690721649484536,
|
| 266 |
+
"grad_norm": 0.610534131526947,
|
| 267 |
+
"learning_rate": 0.00019733480856413868,
|
| 268 |
+
"loss": 0.6655,
|
| 269 |
+
"step": 36
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.30515463917525776,
|
| 273 |
+
"grad_norm": 0.5277837514877319,
|
| 274 |
+
"learning_rate": 0.0001971268574403503,
|
| 275 |
+
"loss": 0.6228,
|
| 276 |
+
"step": 37
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3134020618556701,
|
| 280 |
+
"grad_norm": 0.6729940176010132,
|
| 281 |
+
"learning_rate": 0.00019691121347469235,
|
| 282 |
+
"loss": 0.8324,
|
| 283 |
+
"step": 38
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3216494845360825,
|
| 287 |
+
"grad_norm": 0.541552722454071,
|
| 288 |
+
"learning_rate": 0.00019668789374704338,
|
| 289 |
+
"loss": 0.54,
|
| 290 |
+
"step": 39
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.32989690721649484,
|
| 294 |
+
"grad_norm": 0.5642793774604797,
|
| 295 |
+
"learning_rate": 0.0001964569159452335,
|
| 296 |
+
"loss": 0.641,
|
| 297 |
+
"step": 40
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.33814432989690724,
|
| 301 |
+
"grad_norm": 0.5639921426773071,
|
| 302 |
+
"learning_rate": 0.00019621829836364337,
|
| 303 |
+
"loss": 0.6042,
|
| 304 |
+
"step": 41
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3463917525773196,
|
| 308 |
+
"grad_norm": 0.566059410572052,
|
| 309 |
+
"learning_rate": 0.00019597205990175525,
|
| 310 |
+
"loss": 0.6364,
|
| 311 |
+
"step": 42
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.354639175257732,
|
| 315 |
+
"grad_norm": 0.5911106467247009,
|
| 316 |
+
"learning_rate": 0.00019571822006265622,
|
| 317 |
+
"loss": 0.6777,
|
| 318 |
+
"step": 43
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3628865979381443,
|
| 322 |
+
"grad_norm": 0.5940718054771423,
|
| 323 |
+
"learning_rate": 0.00019545679895149315,
|
| 324 |
+
"loss": 0.713,
|
| 325 |
+
"step": 44
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.3711340206185567,
|
| 329 |
+
"grad_norm": 0.46311718225479126,
|
| 330 |
+
"learning_rate": 0.0001951878172738806,
|
| 331 |
+
"loss": 0.5298,
|
| 332 |
+
"step": 45
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.37938144329896906,
|
| 336 |
+
"grad_norm": 0.5446880459785461,
|
| 337 |
+
"learning_rate": 0.00019491129633426068,
|
| 338 |
+
"loss": 0.546,
|
| 339 |
+
"step": 46
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.38762886597938145,
|
| 343 |
+
"grad_norm": 0.6126728653907776,
|
| 344 |
+
"learning_rate": 0.00019462725803421566,
|
| 345 |
+
"loss": 0.5725,
|
| 346 |
+
"step": 47
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3958762886597938,
|
| 350 |
+
"grad_norm": 0.49817898869514465,
|
| 351 |
+
"learning_rate": 0.0001943357248707334,
|
| 352 |
+
"loss": 0.6224,
|
| 353 |
+
"step": 48
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4041237113402062,
|
| 357 |
+
"grad_norm": 0.4865269362926483,
|
| 358 |
+
"learning_rate": 0.0001940367199344253,
|
| 359 |
+
"loss": 0.544,
|
| 360 |
+
"step": 49
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.41237113402061853,
|
| 364 |
+
"grad_norm": 0.48718348145484924,
|
| 365 |
+
"learning_rate": 0.00019373026690769763,
|
| 366 |
+
"loss": 0.6132,
|
| 367 |
+
"step": 50
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.42061855670103093,
|
| 371 |
+
"grad_norm": 0.5080978274345398,
|
| 372 |
+
"learning_rate": 0.0001934163900628756,
|
| 373 |
+
"loss": 0.6278,
|
| 374 |
+
"step": 51
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4288659793814433,
|
| 378 |
+
"grad_norm": 0.4930504262447357,
|
| 379 |
+
"learning_rate": 0.00019309511426028104,
|
| 380 |
+
"loss": 0.602,
|
| 381 |
+
"step": 52
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.43711340206185567,
|
| 385 |
+
"grad_norm": 0.4977351725101471,
|
| 386 |
+
"learning_rate": 0.00019276646494626332,
|
| 387 |
+
"loss": 0.5516,
|
| 388 |
+
"step": 53
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.44536082474226807,
|
| 392 |
+
"grad_norm": 0.4758591055870056,
|
| 393 |
+
"learning_rate": 0.00019243046815118386,
|
| 394 |
+
"loss": 0.5136,
|
| 395 |
+
"step": 54
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4536082474226804,
|
| 399 |
+
"grad_norm": 0.4887770712375641,
|
| 400 |
+
"learning_rate": 0.00019208715048735445,
|
| 401 |
+
"loss": 0.6265,
|
| 402 |
+
"step": 55
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4618556701030928,
|
| 406 |
+
"grad_norm": 0.5064010620117188,
|
| 407 |
+
"learning_rate": 0.00019173653914692946,
|
| 408 |
+
"loss": 0.6524,
|
| 409 |
+
"step": 56
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.47010309278350515,
|
| 413 |
+
"grad_norm": 0.5001596808433533,
|
| 414 |
+
"learning_rate": 0.00019137866189975202,
|
| 415 |
+
"loss": 0.622,
|
| 416 |
+
"step": 57
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.47835051546391755,
|
| 420 |
+
"grad_norm": 0.4940868616104126,
|
| 421 |
+
"learning_rate": 0.00019101354709115468,
|
| 422 |
+
"loss": 0.6362,
|
| 423 |
+
"step": 58
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.4865979381443299,
|
| 427 |
+
"grad_norm": 0.4839000701904297,
|
| 428 |
+
"learning_rate": 0.00019064122363971427,
|
| 429 |
+
"loss": 0.6223,
|
| 430 |
+
"step": 59
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.4948453608247423,
|
| 434 |
+
"grad_norm": 0.4475175440311432,
|
| 435 |
+
"learning_rate": 0.00019026172103496137,
|
| 436 |
+
"loss": 0.5625,
|
| 437 |
+
"step": 60
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5030927835051546,
|
| 441 |
+
"grad_norm": 0.4716227352619171,
|
| 442 |
+
"learning_rate": 0.0001898750693350447,
|
| 443 |
+
"loss": 0.5161,
|
| 444 |
+
"step": 61
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5030927835051546,
|
| 448 |
+
"eval_loss": 0.5744044780731201,
|
| 449 |
+
"eval_runtime": 296.9417,
|
| 450 |
+
"eval_samples_per_second": 2.021,
|
| 451 |
+
"eval_steps_per_second": 1.01,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.511340206185567,
|
| 456 |
+
"grad_norm": 0.47013187408447266,
|
| 457 |
+
"learning_rate": 0.00018948129916435046,
|
| 458 |
+
"loss": 0.592,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.5195876288659794,
|
| 463 |
+
"grad_norm": 0.44856756925582886,
|
| 464 |
+
"learning_rate": 0.00018908044171107657,
|
| 465 |
+
"loss": 0.5981,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.5278350515463918,
|
| 470 |
+
"grad_norm": 0.4443698525428772,
|
| 471 |
+
"learning_rate": 0.00018867252872476257,
|
| 472 |
+
"loss": 0.6068,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.5360824742268041,
|
| 477 |
+
"grad_norm": 0.423221617937088,
|
| 478 |
+
"learning_rate": 0.00018825759251377483,
|
| 479 |
+
"loss": 0.537,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.5443298969072164,
|
| 484 |
+
"grad_norm": 0.4647126793861389,
|
| 485 |
+
"learning_rate": 0.00018783566594274783,
|
| 486 |
+
"loss": 0.5896,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.5525773195876289,
|
| 491 |
+
"grad_norm": 0.4287152588367462,
|
| 492 |
+
"learning_rate": 0.00018740678242998077,
|
| 493 |
+
"loss": 0.5424,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5608247422680412,
|
| 498 |
+
"grad_norm": 0.4562716484069824,
|
| 499 |
+
"learning_rate": 0.00018697097594479103,
|
| 500 |
+
"loss": 0.5571,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.5690721649484536,
|
| 505 |
+
"grad_norm": 0.37922483682632446,
|
| 506 |
+
"learning_rate": 0.0001865282810048235,
|
| 507 |
+
"loss": 0.5337,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.5773195876288659,
|
| 512 |
+
"grad_norm": 0.4227437973022461,
|
| 513 |
+
"learning_rate": 0.0001860787326733168,
|
| 514 |
+
"loss": 0.5989,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.5855670103092784,
|
| 519 |
+
"grad_norm": 0.39743122458457947,
|
| 520 |
+
"learning_rate": 0.0001856223665563258,
|
| 521 |
+
"loss": 0.537,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5938144329896907,
|
| 526 |
+
"grad_norm": 0.41971203684806824,
|
| 527 |
+
"learning_rate": 0.00018515921879990187,
|
| 528 |
+
"loss": 0.5353,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.6020618556701031,
|
| 533 |
+
"grad_norm": 0.4010031819343567,
|
| 534 |
+
"learning_rate": 0.00018468932608722973,
|
| 535 |
+
"loss": 0.5954,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.6103092783505155,
|
| 540 |
+
"grad_norm": 0.469838947057724,
|
| 541 |
+
"learning_rate": 0.000184212725635722,
|
| 542 |
+
"loss": 0.6942,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.6185567010309279,
|
| 547 |
+
"grad_norm": 0.381673663854599,
|
| 548 |
+
"learning_rate": 0.00018372945519407158,
|
| 549 |
+
"loss": 0.557,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6268041237113402,
|
| 554 |
+
"grad_norm": 0.3736635446548462,
|
| 555 |
+
"learning_rate": 0.00018323955303926163,
|
| 556 |
+
"loss": 0.5174,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.6350515463917525,
|
| 561 |
+
"grad_norm": 0.4390040338039398,
|
| 562 |
+
"learning_rate": 0.00018274305797353395,
|
| 563 |
+
"loss": 0.6249,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.643298969072165,
|
| 568 |
+
"grad_norm": 0.4298490285873413,
|
| 569 |
+
"learning_rate": 0.00018224000932131568,
|
| 570 |
+
"loss": 0.5682,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.6515463917525773,
|
| 575 |
+
"grad_norm": 0.3995118737220764,
|
| 576 |
+
"learning_rate": 0.00018173044692610467,
|
| 577 |
+
"loss": 0.5261,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.6597938144329897,
|
| 582 |
+
"grad_norm": 0.41546231508255005,
|
| 583 |
+
"learning_rate": 0.00018121441114731367,
|
| 584 |
+
"loss": 0.5296,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.668041237113402,
|
| 589 |
+
"grad_norm": 0.4129379093647003,
|
| 590 |
+
"learning_rate": 0.0001806919428570737,
|
| 591 |
+
"loss": 0.5576,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.6762886597938145,
|
| 596 |
+
"grad_norm": 0.4260002672672272,
|
| 597 |
+
"learning_rate": 0.00018016308343699687,
|
| 598 |
+
"loss": 0.6042,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.6845360824742268,
|
| 603 |
+
"grad_norm": 0.3927561640739441,
|
| 604 |
+
"learning_rate": 0.00017962787477489878,
|
| 605 |
+
"loss": 0.5349,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.6927835051546392,
|
| 610 |
+
"grad_norm": 0.39806240797042847,
|
| 611 |
+
"learning_rate": 0.00017908635926148069,
|
| 612 |
+
"loss": 0.5386,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.7010309278350515,
|
| 617 |
+
"grad_norm": 0.3762768805027008,
|
| 618 |
+
"learning_rate": 0.00017853857978697223,
|
| 619 |
+
"loss": 0.545,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.709278350515464,
|
| 624 |
+
"grad_norm": 0.4306787848472595,
|
| 625 |
+
"learning_rate": 0.00017798457973773417,
|
| 626 |
+
"loss": 0.6305,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.7175257731958763,
|
| 631 |
+
"grad_norm": 0.3811737596988678,
|
| 632 |
+
"learning_rate": 0.00017742440299282203,
|
| 633 |
+
"loss": 0.539,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.7257731958762886,
|
| 638 |
+
"grad_norm": 0.39163580536842346,
|
| 639 |
+
"learning_rate": 0.00017685809392051083,
|
| 640 |
+
"loss": 0.5286,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.734020618556701,
|
| 645 |
+
"grad_norm": 0.4237455725669861,
|
| 646 |
+
"learning_rate": 0.00017628569737478076,
|
| 647 |
+
"loss": 0.5801,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.7422680412371134,
|
| 652 |
+
"grad_norm": 0.41603776812553406,
|
| 653 |
+
"learning_rate": 0.00017570725869176467,
|
| 654 |
+
"loss": 0.6001,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7505154639175258,
|
| 659 |
+
"grad_norm": 0.3811546862125397,
|
| 660 |
+
"learning_rate": 0.00017512282368615728,
|
| 661 |
+
"loss": 0.5942,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.7587628865979381,
|
| 666 |
+
"grad_norm": 0.3982357680797577,
|
| 667 |
+
"learning_rate": 0.00017453243864758638,
|
| 668 |
+
"loss": 0.5655,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.7670103092783506,
|
| 673 |
+
"grad_norm": 0.43069708347320557,
|
| 674 |
+
"learning_rate": 0.00017393615033694656,
|
| 675 |
+
"loss": 0.5251,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.7752577319587629,
|
| 680 |
+
"grad_norm": 0.3952259421348572,
|
| 681 |
+
"learning_rate": 0.0001733340059826956,
|
| 682 |
+
"loss": 0.5462,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.7835051546391752,
|
| 687 |
+
"grad_norm": 0.40667715668678284,
|
| 688 |
+
"learning_rate": 0.00017272605327711365,
|
| 689 |
+
"loss": 0.5303,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.7917525773195876,
|
| 694 |
+
"grad_norm": 0.3917592465877533,
|
| 695 |
+
"learning_rate": 0.000172112340372526,
|
| 696 |
+
"loss": 0.612,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8,
|
| 701 |
+
"grad_norm": 0.37455278635025024,
|
| 702 |
+
"learning_rate": 0.00017149291587748898,
|
| 703 |
+
"loss": 0.4831,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.8082474226804124,
|
| 708 |
+
"grad_norm": 0.3805007040500641,
|
| 709 |
+
"learning_rate": 0.00017086782885294025,
|
| 710 |
+
"loss": 0.5237,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8164948453608247,
|
| 715 |
+
"grad_norm": 0.4057518541812897,
|
| 716 |
+
"learning_rate": 0.0001702371288083127,
|
| 717 |
+
"loss": 0.611,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.8247422680412371,
|
| 722 |
+
"grad_norm": 0.424902081489563,
|
| 723 |
+
"learning_rate": 0.00016960086569761332,
|
| 724 |
+
"loss": 0.5071,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.8329896907216495,
|
| 729 |
+
"grad_norm": 0.41015303134918213,
|
| 730 |
+
"learning_rate": 0.0001689590899154664,
|
| 731 |
+
"loss": 0.6073,
|
| 732 |
+
"step": 101
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.8412371134020619,
|
| 736 |
+
"grad_norm": 0.3922909200191498,
|
| 737 |
+
"learning_rate": 0.00016831185229312237,
|
| 738 |
+
"loss": 0.5923,
|
| 739 |
+
"step": 102
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.8494845360824742,
|
| 743 |
+
"grad_norm": 0.43730470538139343,
|
| 744 |
+
"learning_rate": 0.0001676592040944315,
|
| 745 |
+
"loss": 0.5937,
|
| 746 |
+
"step": 103
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.8577319587628865,
|
| 750 |
+
"grad_norm": 0.3726069927215576,
|
| 751 |
+
"learning_rate": 0.0001670011970117838,
|
| 752 |
+
"loss": 0.4912,
|
| 753 |
+
"step": 104
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.865979381443299,
|
| 757 |
+
"grad_norm": 0.404433012008667,
|
| 758 |
+
"learning_rate": 0.00016633788316201454,
|
| 759 |
+
"loss": 0.474,
|
| 760 |
+
"step": 105
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.8742268041237113,
|
| 764 |
+
"grad_norm": 0.41312918066978455,
|
| 765 |
+
"learning_rate": 0.0001656693150822766,
|
| 766 |
+
"loss": 0.5545,
|
| 767 |
+
"step": 106
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.8824742268041237,
|
| 771 |
+
"grad_norm": 0.42073437571525574,
|
| 772 |
+
"learning_rate": 0.0001649955457258792,
|
| 773 |
+
"loss": 0.5488,
|
| 774 |
+
"step": 107
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.8907216494845361,
|
| 778 |
+
"grad_norm": 0.39594408869743347,
|
| 779 |
+
"learning_rate": 0.00016431662845809388,
|
| 780 |
+
"loss": 0.5798,
|
| 781 |
+
"step": 108
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.8989690721649485,
|
| 785 |
+
"grad_norm": 0.41331595182418823,
|
| 786 |
+
"learning_rate": 0.00016363261705192757,
|
| 787 |
+
"loss": 0.5188,
|
| 788 |
+
"step": 109
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.9072164948453608,
|
| 792 |
+
"grad_norm": 0.3879910111427307,
|
| 793 |
+
"learning_rate": 0.00016294356568386369,
|
| 794 |
+
"loss": 0.5676,
|
| 795 |
+
"step": 110
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.9154639175257732,
|
| 799 |
+
"grad_norm": 0.41248220205307007,
|
| 800 |
+
"learning_rate": 0.00016224952892957123,
|
| 801 |
+
"loss": 0.541,
|
| 802 |
+
"step": 111
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.9237113402061856,
|
| 806 |
+
"grad_norm": 0.3406890034675598,
|
| 807 |
+
"learning_rate": 0.0001615505617595819,
|
| 808 |
+
"loss": 0.4902,
|
| 809 |
+
"step": 112
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.931958762886598,
|
| 813 |
+
"grad_norm": 0.3741547167301178,
|
| 814 |
+
"learning_rate": 0.00016084671953493643,
|
| 815 |
+
"loss": 0.5247,
|
| 816 |
+
"step": 113
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.9402061855670103,
|
| 820 |
+
"grad_norm": 0.37796300649642944,
|
| 821 |
+
"learning_rate": 0.00016013805800279976,
|
| 822 |
+
"loss": 0.5091,
|
| 823 |
+
"step": 114
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.9484536082474226,
|
| 827 |
+
"grad_norm": 0.3957986533641815,
|
| 828 |
+
"learning_rate": 0.00015942463329204546,
|
| 829 |
+
"loss": 0.5809,
|
| 830 |
+
"step": 115
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.9567010309278351,
|
| 834 |
+
"grad_norm": 0.38373249769210815,
|
| 835 |
+
"learning_rate": 0.00015870650190881022,
|
| 836 |
+
"loss": 0.4693,
|
| 837 |
+
"step": 116
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.9649484536082474,
|
| 841 |
+
"grad_norm": 0.4250248074531555,
|
| 842 |
+
"learning_rate": 0.00015798372073201836,
|
| 843 |
+
"loss": 0.5668,
|
| 844 |
+
"step": 117
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.9731958762886598,
|
| 848 |
+
"grad_norm": 0.37807247042655945,
|
| 849 |
+
"learning_rate": 0.00015725634700887678,
|
| 850 |
+
"loss": 0.5159,
|
| 851 |
+
"step": 118
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.9814432989690721,
|
| 855 |
+
"grad_norm": 0.3726092278957367,
|
| 856 |
+
"learning_rate": 0.00015652443835034068,
|
| 857 |
+
"loss": 0.5605,
|
| 858 |
+
"step": 119
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.9896907216494846,
|
| 862 |
+
"grad_norm": 0.38076040148735046,
|
| 863 |
+
"learning_rate": 0.0001557880527265505,
|
| 864 |
+
"loss": 0.537,
|
| 865 |
+
"step": 120
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.9979381443298969,
|
| 869 |
+
"grad_norm": 0.37176623940467834,
|
| 870 |
+
"learning_rate": 0.00015504724846224064,
|
| 871 |
+
"loss": 0.5603,
|
| 872 |
+
"step": 121
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.0061855670103093,
|
| 876 |
+
"grad_norm": 0.36700350046157837,
|
| 877 |
+
"learning_rate": 0.00015430208423211975,
|
| 878 |
+
"loss": 0.5398,
|
| 879 |
+
"step": 122
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.0061855670103093,
|
| 883 |
+
"eval_loss": 0.5378922820091248,
|
| 884 |
+
"eval_runtime": 296.9545,
|
| 885 |
+
"eval_samples_per_second": 2.021,
|
| 886 |
+
"eval_steps_per_second": 1.01,
|
| 887 |
+
"step": 122
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 1.0041237113402062,
|
| 891 |
+
"grad_norm": 0.35800787806510925,
|
| 892 |
+
"learning_rate": 0.00015355261905622343,
|
| 893 |
+
"loss": 0.5065,
|
| 894 |
+
"step": 123
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.0123711340206185,
|
| 898 |
+
"grad_norm": 0.32381781935691833,
|
| 899 |
+
"learning_rate": 0.0001527989122952398,
|
| 900 |
+
"loss": 0.4246,
|
| 901 |
+
"step": 124
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.0206185567010309,
|
| 905 |
+
"grad_norm": 0.34609419107437134,
|
| 906 |
+
"learning_rate": 0.00015204102364580765,
|
| 907 |
+
"loss": 0.4654,
|
| 908 |
+
"step": 125
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 1.0288659793814432,
|
| 912 |
+
"grad_norm": 0.3360902965068817,
|
| 913 |
+
"learning_rate": 0.00015127901313578831,
|
| 914 |
+
"loss": 0.424,
|
| 915 |
+
"step": 126
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.0371134020618558,
|
| 919 |
+
"grad_norm": 0.3538791835308075,
|
| 920 |
+
"learning_rate": 0.00015051294111951134,
|
| 921 |
+
"loss": 0.4261,
|
| 922 |
+
"step": 127
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.045360824742268,
|
| 926 |
+
"grad_norm": 0.36259981989860535,
|
| 927 |
+
"learning_rate": 0.000149742868272994,
|
| 928 |
+
"loss": 0.4162,
|
| 929 |
+
"step": 128
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.0536082474226804,
|
| 933 |
+
"grad_norm": 0.3865598440170288,
|
| 934 |
+
"learning_rate": 0.00014896885558913562,
|
| 935 |
+
"loss": 0.4767,
|
| 936 |
+
"step": 129
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.0618556701030928,
|
| 940 |
+
"grad_norm": 0.34752511978149414,
|
| 941 |
+
"learning_rate": 0.00014819096437288664,
|
| 942 |
+
"loss": 0.4461,
|
| 943 |
+
"step": 130
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 1.0701030927835051,
|
| 947 |
+
"grad_norm": 0.3833150565624237,
|
| 948 |
+
"learning_rate": 0.000147409256236393,
|
| 949 |
+
"loss": 0.469,
|
| 950 |
+
"step": 131
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.0783505154639175,
|
| 954 |
+
"grad_norm": 0.3767507076263428,
|
| 955 |
+
"learning_rate": 0.0001466237930941163,
|
| 956 |
+
"loss": 0.4165,
|
| 957 |
+
"step": 132
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.0865979381443298,
|
| 961 |
+
"grad_norm": 0.47273167967796326,
|
| 962 |
+
"learning_rate": 0.00014583463715792984,
|
| 963 |
+
"loss": 0.6179,
|
| 964 |
+
"step": 133
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.0948453608247424,
|
| 968 |
+
"grad_norm": 0.3700537383556366,
|
| 969 |
+
"learning_rate": 0.00014504185093219116,
|
| 970 |
+
"loss": 0.4509,
|
| 971 |
+
"step": 134
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.1030927835051547,
|
| 975 |
+
"grad_norm": 0.4104892611503601,
|
| 976 |
+
"learning_rate": 0.0001442454972087915,
|
| 977 |
+
"loss": 0.4542,
|
| 978 |
+
"step": 135
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.111340206185567,
|
| 982 |
+
"grad_norm": 0.39110255241394043,
|
| 983 |
+
"learning_rate": 0.00014344563906218256,
|
| 984 |
+
"loss": 0.4679,
|
| 985 |
+
"step": 136
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 1.1195876288659794,
|
| 989 |
+
"grad_norm": 0.42041921615600586,
|
| 990 |
+
"learning_rate": 0.0001426423398443803,
|
| 991 |
+
"loss": 0.4453,
|
| 992 |
+
"step": 137
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 1.1278350515463917,
|
| 996 |
+
"grad_norm": 0.4177539050579071,
|
| 997 |
+
"learning_rate": 0.0001418356631799478,
|
| 998 |
+
"loss": 0.4112,
|
| 999 |
+
"step": 138
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.136082474226804,
|
| 1003 |
+
"grad_norm": 0.4446333944797516,
|
| 1004 |
+
"learning_rate": 0.00014102567296095551,
|
| 1005 |
+
"loss": 0.4735,
|
| 1006 |
+
"step": 139
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.1443298969072164,
|
| 1010 |
+
"grad_norm": 0.39587873220443726,
|
| 1011 |
+
"learning_rate": 0.00014021243334192082,
|
| 1012 |
+
"loss": 0.4636,
|
| 1013 |
+
"step": 140
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.1525773195876288,
|
| 1017 |
+
"grad_norm": 0.415682852268219,
|
| 1018 |
+
"learning_rate": 0.00013939600873472694,
|
| 1019 |
+
"loss": 0.4534,
|
| 1020 |
+
"step": 141
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.1608247422680413,
|
| 1024 |
+
"grad_norm": 0.3811276853084564,
|
| 1025 |
+
"learning_rate": 0.00013857646380352102,
|
| 1026 |
+
"loss": 0.4555,
|
| 1027 |
+
"step": 142
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.1690721649484537,
|
| 1031 |
+
"grad_norm": 0.3821997046470642,
|
| 1032 |
+
"learning_rate": 0.00013775386345959246,
|
| 1033 |
+
"loss": 0.4381,
|
| 1034 |
+
"step": 143
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.177319587628866,
|
| 1038 |
+
"grad_norm": 0.3770444989204407,
|
| 1039 |
+
"learning_rate": 0.00013692827285623197,
|
| 1040 |
+
"loss": 0.4064,
|
| 1041 |
+
"step": 144
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.1855670103092784,
|
| 1045 |
+
"grad_norm": 0.43066269159317017,
|
| 1046 |
+
"learning_rate": 0.0001360997573835708,
|
| 1047 |
+
"loss": 0.4532,
|
| 1048 |
+
"step": 145
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.1938144329896907,
|
| 1052 |
+
"grad_norm": 0.36327502131462097,
|
| 1053 |
+
"learning_rate": 0.00013526838266340177,
|
| 1054 |
+
"loss": 0.3665,
|
| 1055 |
+
"step": 146
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.202061855670103,
|
| 1059 |
+
"grad_norm": 0.40168052911758423,
|
| 1060 |
+
"learning_rate": 0.00013443421454398174,
|
| 1061 |
+
"loss": 0.4727,
|
| 1062 |
+
"step": 147
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.2103092783505154,
|
| 1066 |
+
"grad_norm": 0.39729252457618713,
|
| 1067 |
+
"learning_rate": 0.00013359731909481616,
|
| 1068 |
+
"loss": 0.4236,
|
| 1069 |
+
"step": 148
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.218556701030928,
|
| 1073 |
+
"grad_norm": 0.39847901463508606,
|
| 1074 |
+
"learning_rate": 0.00013275776260142608,
|
| 1075 |
+
"loss": 0.4036,
|
| 1076 |
+
"step": 149
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.2268041237113403,
|
| 1080 |
+
"grad_norm": 0.3883432447910309,
|
| 1081 |
+
"learning_rate": 0.00013191561156009803,
|
| 1082 |
+
"loss": 0.4061,
|
| 1083 |
+
"step": 150
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.2350515463917526,
|
| 1087 |
+
"grad_norm": 0.3763248026371002,
|
| 1088 |
+
"learning_rate": 0.0001310709326726173,
|
| 1089 |
+
"loss": 0.3907,
|
| 1090 |
+
"step": 151
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.243298969072165,
|
| 1094 |
+
"grad_norm": 0.4451892673969269,
|
| 1095 |
+
"learning_rate": 0.00013022379284098487,
|
| 1096 |
+
"loss": 0.483,
|
| 1097 |
+
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.2515463917525773,
|
| 1101 |
+
"grad_norm": 0.4433348774909973,
|
| 1102 |
+
"learning_rate": 0.00012937425916211852,
|
| 1103 |
+
"loss": 0.4228,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.2597938144329897,
|
| 1108 |
+
"grad_norm": 0.42469412088394165,
|
| 1109 |
+
"learning_rate": 0.00012852239892253842,
|
| 1110 |
+
"loss": 0.4543,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 1.268041237113402,
|
| 1115 |
+
"grad_norm": 0.41997918486595154,
|
| 1116 |
+
"learning_rate": 0.00012766827959303787,
|
| 1117 |
+
"loss": 0.3975,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.2762886597938143,
|
| 1122 |
+
"grad_norm": 0.4060366749763489,
|
| 1123 |
+
"learning_rate": 0.00012681196882333916,
|
| 1124 |
+
"loss": 0.4245,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.2845360824742267,
|
| 1129 |
+
"grad_norm": 0.4799356162548065,
|
| 1130 |
+
"learning_rate": 0.0001259535344367357,
|
| 1131 |
+
"loss": 0.3823,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 1.2927835051546392,
|
| 1136 |
+
"grad_norm": 0.387761652469635,
|
| 1137 |
+
"learning_rate": 0.00012509304442471985,
|
| 1138 |
+
"loss": 0.4591,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.3010309278350516,
|
| 1143 |
+
"grad_norm": 0.4064452350139618,
|
| 1144 |
+
"learning_rate": 0.0001242305669415979,
|
| 1145 |
+
"loss": 0.439,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.309278350515464,
|
| 1150 |
+
"grad_norm": 0.39760932326316833,
|
| 1151 |
+
"learning_rate": 0.00012336617029909205,
|
| 1152 |
+
"loss": 0.4017,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 1.3175257731958763,
|
| 1157 |
+
"grad_norm": 0.43200570344924927,
|
| 1158 |
+
"learning_rate": 0.00012249992296092956,
|
| 1159 |
+
"loss": 0.4423,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.3257731958762886,
|
| 1164 |
+
"grad_norm": 0.43232297897338867,
|
| 1165 |
+
"learning_rate": 0.00012163189353742035,
|
| 1166 |
+
"loss": 0.4342,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 1.334020618556701,
|
| 1171 |
+
"grad_norm": 0.43833640217781067,
|
| 1172 |
+
"learning_rate": 0.00012076215078002278,
|
| 1173 |
+
"loss": 0.5219,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 1.3422680412371135,
|
| 1178 |
+
"grad_norm": 0.40365973114967346,
|
| 1179 |
+
"learning_rate": 0.0001198907635758982,
|
| 1180 |
+
"loss": 0.4123,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 1.3505154639175259,
|
| 1185 |
+
"grad_norm": 0.43913137912750244,
|
| 1186 |
+
"learning_rate": 0.00011901780094245483,
|
| 1187 |
+
"loss": 0.4149,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 1.3587628865979382,
|
| 1192 |
+
"grad_norm": 0.4219210147857666,
|
| 1193 |
+
"learning_rate": 0.00011814333202188126,
|
| 1194 |
+
"loss": 0.4127,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 1.3670103092783505,
|
| 1199 |
+
"grad_norm": 0.42331403493881226,
|
| 1200 |
+
"learning_rate": 0.0001172674260756702,
|
| 1201 |
+
"loss": 0.3926,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.3752577319587629,
|
| 1206 |
+
"grad_norm": 0.3824922442436218,
|
| 1207 |
+
"learning_rate": 0.00011639015247913261,
|
| 1208 |
+
"loss": 0.3781,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.3835051546391752,
|
| 1213 |
+
"grad_norm": 0.4475767910480499,
|
| 1214 |
+
"learning_rate": 0.0001155115807159029,
|
| 1215 |
+
"loss": 0.5629,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 1.3917525773195876,
|
| 1220 |
+
"grad_norm": 0.36695027351379395,
|
| 1221 |
+
"learning_rate": 0.00011463178037243554,
|
| 1222 |
+
"loss": 0.3622,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 1.4,
|
| 1227 |
+
"grad_norm": 0.41651466488838196,
|
| 1228 |
+
"learning_rate": 0.0001137508211324936,
|
| 1229 |
+
"loss": 0.4043,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.4082474226804123,
|
| 1234 |
+
"grad_norm": 0.4297608733177185,
|
| 1235 |
+
"learning_rate": 0.00011286877277162943,
|
| 1236 |
+
"loss": 0.4575,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 1.4164948453608248,
|
| 1241 |
+
"grad_norm": 0.441707968711853,
|
| 1242 |
+
"learning_rate": 0.00011198570515165822,
|
| 1243 |
+
"loss": 0.4435,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.4247422680412372,
|
| 1248 |
+
"grad_norm": 0.4173315465450287,
|
| 1249 |
+
"learning_rate": 0.00011110168821512452,
|
| 1250 |
+
"loss": 0.4367,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 1.4329896907216495,
|
| 1255 |
+
"grad_norm": 0.42195403575897217,
|
| 1256 |
+
"learning_rate": 0.00011021679197976274,
|
| 1257 |
+
"loss": 0.4258,
|
| 1258 |
+
"step": 175
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.4412371134020618,
|
| 1262 |
+
"grad_norm": 0.394330769777298,
|
| 1263 |
+
"learning_rate": 0.00010933108653295128,
|
| 1264 |
+
"loss": 0.4329,
|
| 1265 |
+
"step": 176
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 1.4494845360824742,
|
| 1269 |
+
"grad_norm": 0.4263797998428345,
|
| 1270 |
+
"learning_rate": 0.00010844464202616127,
|
| 1271 |
+
"loss": 0.475,
|
| 1272 |
+
"step": 177
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 1.4577319587628865,
|
| 1276 |
+
"grad_norm": 0.36980873346328735,
|
| 1277 |
+
"learning_rate": 0.00010755752866940062,
|
| 1278 |
+
"loss": 0.3833,
|
| 1279 |
+
"step": 178
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 1.465979381443299,
|
| 1283 |
+
"grad_norm": 0.42231741547584534,
|
| 1284 |
+
"learning_rate": 0.0001066698167256527,
|
| 1285 |
+
"loss": 0.4716,
|
| 1286 |
+
"step": 179
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 1.4742268041237114,
|
| 1290 |
+
"grad_norm": 0.40805140137672424,
|
| 1291 |
+
"learning_rate": 0.00010578157650531146,
|
| 1292 |
+
"loss": 0.4483,
|
| 1293 |
+
"step": 180
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.4824742268041238,
|
| 1297 |
+
"grad_norm": 0.4024035334587097,
|
| 1298 |
+
"learning_rate": 0.00010489287836061246,
|
| 1299 |
+
"loss": 0.4319,
|
| 1300 |
+
"step": 181
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.4907216494845361,
|
| 1304 |
+
"grad_norm": 0.38521435856819153,
|
| 1305 |
+
"learning_rate": 0.00010400379268006082,
|
| 1306 |
+
"loss": 0.4082,
|
| 1307 |
+
"step": 182
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 1.4989690721649485,
|
| 1311 |
+
"grad_norm": 0.4192781448364258,
|
| 1312 |
+
"learning_rate": 0.00010311438988285598,
|
| 1313 |
+
"loss": 0.4614,
|
| 1314 |
+
"step": 183
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.4989690721649485,
|
| 1318 |
+
"eval_loss": 0.5294703245162964,
|
| 1319 |
+
"eval_runtime": 297.0142,
|
| 1320 |
+
"eval_samples_per_second": 2.02,
|
| 1321 |
+
"eval_steps_per_second": 1.01,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.5072164948453608,
|
| 1326 |
+
"grad_norm": 0.4073619246482849,
|
| 1327 |
+
"learning_rate": 0.00010222474041331436,
|
| 1328 |
+
"loss": 0.4335,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.5154639175257731,
|
| 1333 |
+
"grad_norm": 0.3790091574192047,
|
| 1334 |
+
"learning_rate": 0.0001013349147352898,
|
| 1335 |
+
"loss": 0.3892,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.5237113402061855,
|
| 1340 |
+
"grad_norm": 0.39920473098754883,
|
| 1341 |
+
"learning_rate": 0.00010044498332659264,
|
| 1342 |
+
"loss": 0.416,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.5319587628865978,
|
| 1347 |
+
"grad_norm": 0.37349697947502136,
|
| 1348 |
+
"learning_rate": 9.955501667340741e-05,
|
| 1349 |
+
"loss": 0.3943,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.5402061855670102,
|
| 1354 |
+
"grad_norm": 0.3844608962535858,
|
| 1355 |
+
"learning_rate": 9.866508526471023e-05,
|
| 1356 |
+
"loss": 0.4057,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.5484536082474227,
|
| 1361 |
+
"grad_norm": 0.40029478073120117,
|
| 1362 |
+
"learning_rate": 9.77752595866857e-05,
|
| 1363 |
+
"loss": 0.429,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.556701030927835,
|
| 1368 |
+
"grad_norm": 0.42949914932250977,
|
| 1369 |
+
"learning_rate": 9.688561011714404e-05,
|
| 1370 |
+
"loss": 0.4247,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.5649484536082474,
|
| 1375 |
+
"grad_norm": 0.3950637876987457,
|
| 1376 |
+
"learning_rate": 9.599620731993922e-05,
|
| 1377 |
+
"loss": 0.4358,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.5731958762886598,
|
| 1382 |
+
"grad_norm": 0.4211474359035492,
|
| 1383 |
+
"learning_rate": 9.510712163938755e-05,
|
| 1384 |
+
"loss": 0.4485,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.5814432989690723,
|
| 1389 |
+
"grad_norm": 0.41278165578842163,
|
| 1390 |
+
"learning_rate": 9.421842349468855e-05,
|
| 1391 |
+
"loss": 0.458,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.5896907216494847,
|
| 1396 |
+
"grad_norm": 0.4086206555366516,
|
| 1397 |
+
"learning_rate": 9.333018327434731e-05,
|
| 1398 |
+
"loss": 0.4295,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.597938144329897,
|
| 1403 |
+
"grad_norm": 0.38980671763420105,
|
| 1404 |
+
"learning_rate": 9.244247133059938e-05,
|
| 1405 |
+
"loss": 0.3858,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.6061855670103093,
|
| 1410 |
+
"grad_norm": 0.4090917706489563,
|
| 1411 |
+
"learning_rate": 9.155535797383874e-05,
|
| 1412 |
+
"loss": 0.3678,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.6144329896907217,
|
| 1417 |
+
"grad_norm": 0.4124603271484375,
|
| 1418 |
+
"learning_rate": 9.066891346704875e-05,
|
| 1419 |
+
"loss": 0.4203,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.622680412371134,
|
| 1424 |
+
"grad_norm": 0.4070824384689331,
|
| 1425 |
+
"learning_rate": 8.978320802023731e-05,
|
| 1426 |
+
"loss": 0.4558,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.6309278350515464,
|
| 1431 |
+
"grad_norm": 0.376213401556015,
|
| 1432 |
+
"learning_rate": 8.88983117848755e-05,
|
| 1433 |
+
"loss": 0.3928,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.6391752577319587,
|
| 1438 |
+
"grad_norm": 0.4122854769229889,
|
| 1439 |
+
"learning_rate": 8.801429484834183e-05,
|
| 1440 |
+
"loss": 0.4521,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.647422680412371,
|
| 1445 |
+
"grad_norm": 0.38308247923851013,
|
| 1446 |
+
"learning_rate": 8.713122722837058e-05,
|
| 1447 |
+
"loss": 0.3727,
|
| 1448 |
+
"step": 201
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.6556701030927834,
|
| 1452 |
+
"grad_norm": 0.4036957919597626,
|
| 1453 |
+
"learning_rate": 8.624917886750638e-05,
|
| 1454 |
+
"loss": 0.4497,
|
| 1455 |
+
"step": 202
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.6639175257731957,
|
| 1459 |
+
"grad_norm": 0.44214046001434326,
|
| 1460 |
+
"learning_rate": 8.536821962756447e-05,
|
| 1461 |
+
"loss": 0.5122,
|
| 1462 |
+
"step": 203
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 1.6721649484536083,
|
| 1466 |
+
"grad_norm": 0.40875983238220215,
|
| 1467 |
+
"learning_rate": 8.448841928409711e-05,
|
| 1468 |
+
"loss": 0.4393,
|
| 1469 |
+
"step": 204
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 1.6804123711340206,
|
| 1473 |
+
"grad_norm": 0.42527636885643005,
|
| 1474 |
+
"learning_rate": 8.360984752086743e-05,
|
| 1475 |
+
"loss": 0.4545,
|
| 1476 |
+
"step": 205
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 1.688659793814433,
|
| 1480 |
+
"grad_norm": 0.433173269033432,
|
| 1481 |
+
"learning_rate": 8.273257392432981e-05,
|
| 1482 |
+
"loss": 0.4867,
|
| 1483 |
+
"step": 206
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 1.6969072164948453,
|
| 1487 |
+
"grad_norm": 0.386598140001297,
|
| 1488 |
+
"learning_rate": 8.185666797811878e-05,
|
| 1489 |
+
"loss": 0.4253,
|
| 1490 |
+
"step": 207
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.705154639175258,
|
| 1494 |
+
"grad_norm": 0.40319326519966125,
|
| 1495 |
+
"learning_rate": 8.09821990575452e-05,
|
| 1496 |
+
"loss": 0.3935,
|
| 1497 |
+
"step": 208
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 1.7134020618556702,
|
| 1501 |
+
"grad_norm": 0.4310265779495239,
|
| 1502 |
+
"learning_rate": 8.010923642410184e-05,
|
| 1503 |
+
"loss": 0.4184,
|
| 1504 |
+
"step": 209
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 1.7216494845360826,
|
| 1508 |
+
"grad_norm": 0.3964579999446869,
|
| 1509 |
+
"learning_rate": 7.923784921997726e-05,
|
| 1510 |
+
"loss": 0.4449,
|
| 1511 |
+
"step": 210
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.729896907216495,
|
| 1515 |
+
"grad_norm": 0.39828160405158997,
|
| 1516 |
+
"learning_rate": 7.836810646257971e-05,
|
| 1517 |
+
"loss": 0.4227,
|
| 1518 |
+
"step": 211
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 1.7381443298969073,
|
| 1522 |
+
"grad_norm": 0.3750438392162323,
|
| 1523 |
+
"learning_rate": 7.750007703907046e-05,
|
| 1524 |
+
"loss": 0.3746,
|
| 1525 |
+
"step": 212
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 1.7463917525773196,
|
| 1529 |
+
"grad_norm": 0.40668681263923645,
|
| 1530 |
+
"learning_rate": 7.663382970090795e-05,
|
| 1531 |
+
"loss": 0.4351,
|
| 1532 |
+
"step": 213
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 1.754639175257732,
|
| 1536 |
+
"grad_norm": 0.4102826714515686,
|
| 1537 |
+
"learning_rate": 7.57694330584021e-05,
|
| 1538 |
+
"loss": 0.3999,
|
| 1539 |
+
"step": 214
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 1.7628865979381443,
|
| 1543 |
+
"grad_norm": 0.4256535470485687,
|
| 1544 |
+
"learning_rate": 7.490695557528016e-05,
|
| 1545 |
+
"loss": 0.4321,
|
| 1546 |
+
"step": 215
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.7711340206185566,
|
| 1550 |
+
"grad_norm": 0.3946252167224884,
|
| 1551 |
+
"learning_rate": 7.404646556326433e-05,
|
| 1552 |
+
"loss": 0.4323,
|
| 1553 |
+
"step": 216
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 1.779381443298969,
|
| 1557 |
+
"grad_norm": 0.3808107078075409,
|
| 1558 |
+
"learning_rate": 7.318803117666084e-05,
|
| 1559 |
+
"loss": 0.3942,
|
| 1560 |
+
"step": 217
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 1.7876288659793813,
|
| 1564 |
+
"grad_norm": 0.420895516872406,
|
| 1565 |
+
"learning_rate": 7.233172040696216e-05,
|
| 1566 |
+
"loss": 0.4466,
|
| 1567 |
+
"step": 218
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 1.7958762886597937,
|
| 1571 |
+
"grad_norm": 0.3973442614078522,
|
| 1572 |
+
"learning_rate": 7.14776010774616e-05,
|
| 1573 |
+
"loss": 0.4455,
|
| 1574 |
+
"step": 219
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.8041237113402062,
|
| 1578 |
+
"grad_norm": 0.40194034576416016,
|
| 1579 |
+
"learning_rate": 7.062574083788152e-05,
|
| 1580 |
+
"loss": 0.4622,
|
| 1581 |
+
"step": 220
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 1.8123711340206186,
|
| 1585 |
+
"grad_norm": 0.37952494621276855,
|
| 1586 |
+
"learning_rate": 6.977620715901514e-05,
|
| 1587 |
+
"loss": 0.3899,
|
| 1588 |
+
"step": 221
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 1.820618556701031,
|
| 1592 |
+
"grad_norm": 0.43268251419067383,
|
| 1593 |
+
"learning_rate": 6.892906732738271e-05,
|
| 1594 |
+
"loss": 0.4555,
|
| 1595 |
+
"step": 222
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 1.8288659793814435,
|
| 1599 |
+
"grad_norm": 0.39225122332572937,
|
| 1600 |
+
"learning_rate": 6.8084388439902e-05,
|
| 1601 |
+
"loss": 0.3727,
|
| 1602 |
+
"step": 223
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.8371134020618558,
|
| 1606 |
+
"grad_norm": 0.39572715759277344,
|
| 1607 |
+
"learning_rate": 6.724223739857392e-05,
|
| 1608 |
+
"loss": 0.4696,
|
| 1609 |
+
"step": 224
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 1.8453608247422681,
|
| 1613 |
+
"grad_norm": 0.4312278628349304,
|
| 1614 |
+
"learning_rate": 6.640268090518385e-05,
|
| 1615 |
+
"loss": 0.492,
|
| 1616 |
+
"step": 225
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 1.8536082474226805,
|
| 1620 |
+
"grad_norm": 0.40482354164123535,
|
| 1621 |
+
"learning_rate": 6.556578545601829e-05,
|
| 1622 |
+
"loss": 0.4342,
|
| 1623 |
+
"step": 226
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 1.8618556701030928,
|
| 1627 |
+
"grad_norm": 0.3752698302268982,
|
| 1628 |
+
"learning_rate": 6.473161733659828e-05,
|
| 1629 |
+
"loss": 0.4197,
|
| 1630 |
+
"step": 227
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 1.8701030927835052,
|
| 1634 |
+
"grad_norm": 0.41621121764183044,
|
| 1635 |
+
"learning_rate": 6.390024261642922e-05,
|
| 1636 |
+
"loss": 0.4895,
|
| 1637 |
+
"step": 228
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 1.8783505154639175,
|
| 1641 |
+
"grad_norm": 0.3930753767490387,
|
| 1642 |
+
"learning_rate": 6.307172714376808e-05,
|
| 1643 |
+
"loss": 0.4508,
|
| 1644 |
+
"step": 229
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 1.8865979381443299,
|
| 1648 |
+
"grad_norm": 0.4012429714202881,
|
| 1649 |
+
"learning_rate": 6.224613654040753e-05,
|
| 1650 |
+
"loss": 0.4536,
|
| 1651 |
+
"step": 230
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 1.8948453608247422,
|
| 1655 |
+
"grad_norm": 0.3710065186023712,
|
| 1656 |
+
"learning_rate": 6.142353619647903e-05,
|
| 1657 |
+
"loss": 0.4206,
|
| 1658 |
+
"step": 231
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.9030927835051545,
|
| 1662 |
+
"grad_norm": 0.3984532058238983,
|
| 1663 |
+
"learning_rate": 6.0603991265273074e-05,
|
| 1664 |
+
"loss": 0.394,
|
| 1665 |
+
"step": 232
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 1.9113402061855669,
|
| 1669 |
+
"grad_norm": 0.3717309832572937,
|
| 1670 |
+
"learning_rate": 5.978756665807917e-05,
|
| 1671 |
+
"loss": 0.4004,
|
| 1672 |
+
"step": 233
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 1.9195876288659792,
|
| 1676 |
+
"grad_norm": 0.3788721561431885,
|
| 1677 |
+
"learning_rate": 5.897432703904453e-05,
|
| 1678 |
+
"loss": 0.4225,
|
| 1679 |
+
"step": 234
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 1.9278350515463918,
|
| 1683 |
+
"grad_norm": 0.4055582284927368,
|
| 1684 |
+
"learning_rate": 5.8164336820052203e-05,
|
| 1685 |
+
"loss": 0.4771,
|
| 1686 |
+
"step": 235
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.9360824742268041,
|
| 1690 |
+
"grad_norm": 0.39383062720298767,
|
| 1691 |
+
"learning_rate": 5.735766015561971e-05,
|
| 1692 |
+
"loss": 0.4054,
|
| 1693 |
+
"step": 236
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.9443298969072165,
|
| 1697 |
+
"grad_norm": 0.39192789793014526,
|
| 1698 |
+
"learning_rate": 5.65543609378175e-05,
|
| 1699 |
+
"loss": 0.4554,
|
| 1700 |
+
"step": 237
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.9525773195876288,
|
| 1704 |
+
"grad_norm": 0.43132880330085754,
|
| 1705 |
+
"learning_rate": 5.5754502791208504e-05,
|
| 1706 |
+
"loss": 0.4845,
|
| 1707 |
+
"step": 238
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.9608247422680414,
|
| 1711 |
+
"grad_norm": 0.3810337483882904,
|
| 1712 |
+
"learning_rate": 5.495814906780886e-05,
|
| 1713 |
+
"loss": 0.4253,
|
| 1714 |
+
"step": 239
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.9690721649484537,
|
| 1718 |
+
"grad_norm": 0.38002529740333557,
|
| 1719 |
+
"learning_rate": 5.4165362842070185e-05,
|
| 1720 |
+
"loss": 0.4291,
|
| 1721 |
+
"step": 240
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 1.977319587628866,
|
| 1725 |
+
"grad_norm": 0.3775567412376404,
|
| 1726 |
+
"learning_rate": 5.3376206905883694e-05,
|
| 1727 |
+
"loss": 0.397,
|
| 1728 |
+
"step": 241
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 1.9855670103092784,
|
| 1732 |
+
"grad_norm": 0.36817148327827454,
|
| 1733 |
+
"learning_rate": 5.259074376360701e-05,
|
| 1734 |
+
"loss": 0.3816,
|
| 1735 |
+
"step": 242
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 1.9938144329896907,
|
| 1739 |
+
"grad_norm": 0.4288536608219147,
|
| 1740 |
+
"learning_rate": 5.18090356271134e-05,
|
| 1741 |
+
"loss": 0.4502,
|
| 1742 |
+
"step": 243
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 2.002061855670103,
|
| 1746 |
+
"grad_norm": 0.39343351125717163,
|
| 1747 |
+
"learning_rate": 5.1031144410864384e-05,
|
| 1748 |
+
"loss": 0.4323,
|
| 1749 |
+
"step": 244
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 2.002061855670103,
|
| 1753 |
+
"eval_loss": 0.5178368091583252,
|
| 1754 |
+
"eval_runtime": 297.015,
|
| 1755 |
+
"eval_samples_per_second": 2.02,
|
| 1756 |
+
"eval_steps_per_second": 1.01,
|
| 1757 |
+
"step": 244
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 2.0103092783505154,
|
| 1761 |
+
"grad_norm": 0.5457305312156677,
|
| 1762 |
+
"learning_rate": 5.0257131727006016e-05,
|
| 1763 |
+
"loss": 0.3386,
|
| 1764 |
+
"step": 245
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 2.0082474226804123,
|
| 1768 |
+
"grad_norm": 0.3745405972003937,
|
| 1769 |
+
"learning_rate": 4.9487058880488656e-05,
|
| 1770 |
+
"loss": 0.3649,
|
| 1771 |
+
"step": 246
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 2.0164948453608247,
|
| 1775 |
+
"grad_norm": 0.3878428637981415,
|
| 1776 |
+
"learning_rate": 4.87209868642117e-05,
|
| 1777 |
+
"loss": 0.3819,
|
| 1778 |
+
"step": 247
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 2.024742268041237,
|
| 1782 |
+
"grad_norm": 0.3813370168209076,
|
| 1783 |
+
"learning_rate": 4.795897635419235e-05,
|
| 1784 |
+
"loss": 0.3593,
|
| 1785 |
+
"step": 248
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 2.0329896907216494,
|
| 1789 |
+
"grad_norm": 0.3491398096084595,
|
| 1790 |
+
"learning_rate": 4.720108770476024e-05,
|
| 1791 |
+
"loss": 0.3451,
|
| 1792 |
+
"step": 249
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 2.0412371134020617,
|
| 1796 |
+
"grad_norm": 0.3811284303665161,
|
| 1797 |
+
"learning_rate": 4.6447380943776575e-05,
|
| 1798 |
+
"loss": 0.3804,
|
| 1799 |
+
"step": 250
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 2.049484536082474,
|
| 1803 |
+
"grad_norm": 0.3748043477535248,
|
| 1804 |
+
"learning_rate": 4.56979157678803e-05,
|
| 1805 |
+
"loss": 0.3629,
|
| 1806 |
+
"step": 251
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 2.0577319587628864,
|
| 1810 |
+
"grad_norm": 0.325930655002594,
|
| 1811 |
+
"learning_rate": 4.495275153775937e-05,
|
| 1812 |
+
"loss": 0.2997,
|
| 1813 |
+
"step": 252
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 2.065979381443299,
|
| 1817 |
+
"grad_norm": 0.3703972399234772,
|
| 1818 |
+
"learning_rate": 4.4211947273449494e-05,
|
| 1819 |
+
"loss": 0.3476,
|
| 1820 |
+
"step": 253
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 2.0742268041237115,
|
| 1824 |
+
"grad_norm": 0.3672904670238495,
|
| 1825 |
+
"learning_rate": 4.347556164965934e-05,
|
| 1826 |
+
"loss": 0.3728,
|
| 1827 |
+
"step": 254
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 2.082474226804124,
|
| 1831 |
+
"grad_norm": 0.37608975172042847,
|
| 1832 |
+
"learning_rate": 4.274365299112323e-05,
|
| 1833 |
+
"loss": 0.3471,
|
| 1834 |
+
"step": 255
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 2.090721649484536,
|
| 1838 |
+
"grad_norm": 0.3415372669696808,
|
| 1839 |
+
"learning_rate": 4.2016279267981664e-05,
|
| 1840 |
+
"loss": 0.3589,
|
| 1841 |
+
"step": 256
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 2.0989690721649485,
|
| 1845 |
+
"grad_norm": 0.3874717354774475,
|
| 1846 |
+
"learning_rate": 4.129349809118981e-05,
|
| 1847 |
+
"loss": 0.3728,
|
| 1848 |
+
"step": 257
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 2.107216494845361,
|
| 1852 |
+
"grad_norm": 0.3430662155151367,
|
| 1853 |
+
"learning_rate": 4.057536670795459e-05,
|
| 1854 |
+
"loss": 0.3566,
|
| 1855 |
+
"step": 258
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 2.1154639175257732,
|
| 1859 |
+
"grad_norm": 0.39854690432548523,
|
| 1860 |
+
"learning_rate": 3.9861941997200245e-05,
|
| 1861 |
+
"loss": 0.4037,
|
| 1862 |
+
"step": 259
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 2.1237113402061856,
|
| 1866 |
+
"grad_norm": 0.34778809547424316,
|
| 1867 |
+
"learning_rate": 3.915328046506357e-05,
|
| 1868 |
+
"loss": 0.3291,
|
| 1869 |
+
"step": 260
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 2.131958762886598,
|
| 1873 |
+
"grad_norm": 0.383894145488739,
|
| 1874 |
+
"learning_rate": 3.8449438240418134e-05,
|
| 1875 |
+
"loss": 0.3737,
|
| 1876 |
+
"step": 261
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 2.1402061855670103,
|
| 1880 |
+
"grad_norm": 0.37021082639694214,
|
| 1881 |
+
"learning_rate": 3.775047107042883e-05,
|
| 1882 |
+
"loss": 0.3602,
|
| 1883 |
+
"step": 262
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 2.1484536082474226,
|
| 1887 |
+
"grad_norm": 0.40833646059036255,
|
| 1888 |
+
"learning_rate": 3.705643431613634e-05,
|
| 1889 |
+
"loss": 0.4031,
|
| 1890 |
+
"step": 263
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 2.156701030927835,
|
| 1894 |
+
"grad_norm": 0.3483593761920929,
|
| 1895 |
+
"learning_rate": 3.636738294807245e-05,
|
| 1896 |
+
"loss": 0.3332,
|
| 1897 |
+
"step": 264
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 2.1649484536082473,
|
| 1901 |
+
"grad_norm": 0.4144445061683655,
|
| 1902 |
+
"learning_rate": 3.568337154190614e-05,
|
| 1903 |
+
"loss": 0.4228,
|
| 1904 |
+
"step": 265
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 2.1731958762886596,
|
| 1908 |
+
"grad_norm": 0.37662217020988464,
|
| 1909 |
+
"learning_rate": 3.500445427412077e-05,
|
| 1910 |
+
"loss": 0.3613,
|
| 1911 |
+
"step": 266
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 2.181443298969072,
|
| 1915 |
+
"grad_norm": 0.36589595675468445,
|
| 1916 |
+
"learning_rate": 3.433068491772341e-05,
|
| 1917 |
+
"loss": 0.3088,
|
| 1918 |
+
"step": 267
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 2.1896907216494848,
|
| 1922 |
+
"grad_norm": 0.37732839584350586,
|
| 1923 |
+
"learning_rate": 3.366211683798549e-05,
|
| 1924 |
+
"loss": 0.3393,
|
| 1925 |
+
"step": 268
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 2.197938144329897,
|
| 1929 |
+
"grad_norm": 0.34662479162216187,
|
| 1930 |
+
"learning_rate": 3.299880298821625e-05,
|
| 1931 |
+
"loss": 0.3447,
|
| 1932 |
+
"step": 269
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 2.2061855670103094,
|
| 1936 |
+
"grad_norm": 0.3836705982685089,
|
| 1937 |
+
"learning_rate": 3.23407959055685e-05,
|
| 1938 |
+
"loss": 0.3733,
|
| 1939 |
+
"step": 270
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 2.2144329896907218,
|
| 1943 |
+
"grad_norm": 0.3639705777168274,
|
| 1944 |
+
"learning_rate": 3.1688147706877666e-05,
|
| 1945 |
+
"loss": 0.3425,
|
| 1946 |
+
"step": 271
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 2.222680412371134,
|
| 1950 |
+
"grad_norm": 0.3514609634876251,
|
| 1951 |
+
"learning_rate": 3.1040910084533614e-05,
|
| 1952 |
+
"loss": 0.3195,
|
| 1953 |
+
"step": 272
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 2.2309278350515465,
|
| 1957 |
+
"grad_norm": 0.3559933006763458,
|
| 1958 |
+
"learning_rate": 3.039913430238672e-05,
|
| 1959 |
+
"loss": 0.3442,
|
| 1960 |
+
"step": 273
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 2.239175257731959,
|
| 1964 |
+
"grad_norm": 0.38752618432044983,
|
| 1965 |
+
"learning_rate": 2.9762871191687313e-05,
|
| 1966 |
+
"loss": 0.3778,
|
| 1967 |
+
"step": 274
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 2.247422680412371,
|
| 1971 |
+
"grad_norm": 0.3630293309688568,
|
| 1972 |
+
"learning_rate": 2.913217114705975e-05,
|
| 1973 |
+
"loss": 0.3355,
|
| 1974 |
+
"step": 275
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 2.2556701030927835,
|
| 1978 |
+
"grad_norm": 0.3738977015018463,
|
| 1979 |
+
"learning_rate": 2.850708412251103e-05,
|
| 1980 |
+
"loss": 0.3583,
|
| 1981 |
+
"step": 276
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 2.263917525773196,
|
| 1985 |
+
"grad_norm": 0.38425007462501526,
|
| 1986 |
+
"learning_rate": 2.7887659627474017e-05,
|
| 1987 |
+
"loss": 0.356,
|
| 1988 |
+
"step": 277
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 2.272164948453608,
|
| 1992 |
+
"grad_norm": 0.3420022428035736,
|
| 1993 |
+
"learning_rate": 2.7273946722886366e-05,
|
| 1994 |
+
"loss": 0.3227,
|
| 1995 |
+
"step": 278
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 2.2804123711340205,
|
| 1999 |
+
"grad_norm": 0.3774506449699402,
|
| 2000 |
+
"learning_rate": 2.6665994017304407e-05,
|
| 2001 |
+
"loss": 0.3707,
|
| 2002 |
+
"step": 279
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 2.288659793814433,
|
| 2006 |
+
"grad_norm": 0.347858190536499,
|
| 2007 |
+
"learning_rate": 2.6063849663053475e-05,
|
| 2008 |
+
"loss": 0.3151,
|
| 2009 |
+
"step": 280
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 2.296907216494845,
|
| 2013 |
+
"grad_norm": 0.39050960540771484,
|
| 2014 |
+
"learning_rate": 2.5467561352413648e-05,
|
| 2015 |
+
"loss": 0.3882,
|
| 2016 |
+
"step": 281
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 2.3051546391752575,
|
| 2020 |
+
"grad_norm": 0.35410475730895996,
|
| 2021 |
+
"learning_rate": 2.4877176313842753e-05,
|
| 2022 |
+
"loss": 0.3098,
|
| 2023 |
+
"step": 282
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 2.31340206185567,
|
| 2027 |
+
"grad_norm": 0.3665927052497864,
|
| 2028 |
+
"learning_rate": 2.4292741308235345e-05,
|
| 2029 |
+
"loss": 0.3504,
|
| 2030 |
+
"step": 283
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.3216494845360827,
|
| 2034 |
+
"grad_norm": 0.33465299010276794,
|
| 2035 |
+
"learning_rate": 2.3714302625219243e-05,
|
| 2036 |
+
"loss": 0.2926,
|
| 2037 |
+
"step": 284
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 2.329896907216495,
|
| 2041 |
+
"grad_norm": 0.4150053560733795,
|
| 2042 |
+
"learning_rate": 2.3141906079489183e-05,
|
| 2043 |
+
"loss": 0.3964,
|
| 2044 |
+
"step": 285
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 2.3381443298969073,
|
| 2048 |
+
"grad_norm": 0.33678460121154785,
|
| 2049 |
+
"learning_rate": 2.2575597007177984e-05,
|
| 2050 |
+
"loss": 0.326,
|
| 2051 |
+
"step": 286
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 2.3463917525773197,
|
| 2055 |
+
"grad_norm": 0.3581312894821167,
|
| 2056 |
+
"learning_rate": 2.2015420262265863e-05,
|
| 2057 |
+
"loss": 0.3698,
|
| 2058 |
+
"step": 287
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 2.354639175257732,
|
| 2062 |
+
"grad_norm": 0.37406647205352783,
|
| 2063 |
+
"learning_rate": 2.1461420213027772e-05,
|
| 2064 |
+
"loss": 0.3661,
|
| 2065 |
+
"step": 288
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 2.3628865979381444,
|
| 2069 |
+
"grad_norm": 0.35271313786506653,
|
| 2070 |
+
"learning_rate": 2.0913640738519335e-05,
|
| 2071 |
+
"loss": 0.3609,
|
| 2072 |
+
"step": 289
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 2.3711340206185567,
|
| 2076 |
+
"grad_norm": 0.3584725558757782,
|
| 2077 |
+
"learning_rate": 2.0372125225101234e-05,
|
| 2078 |
+
"loss": 0.3293,
|
| 2079 |
+
"step": 290
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 2.379381443298969,
|
| 2083 |
+
"grad_norm": 0.4022175073623657,
|
| 2084 |
+
"learning_rate": 1.983691656300314e-05,
|
| 2085 |
+
"loss": 0.3965,
|
| 2086 |
+
"step": 291
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 2.3876288659793814,
|
| 2090 |
+
"grad_norm": 0.3425813317298889,
|
| 2091 |
+
"learning_rate": 1.930805714292634e-05,
|
| 2092 |
+
"loss": 0.3163,
|
| 2093 |
+
"step": 292
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 2.3958762886597937,
|
| 2097 |
+
"grad_norm": 0.35875558853149414,
|
| 2098 |
+
"learning_rate": 1.8785588852686376e-05,
|
| 2099 |
+
"loss": 0.3114,
|
| 2100 |
+
"step": 293
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 2.404123711340206,
|
| 2104 |
+
"grad_norm": 0.35764867067337036,
|
| 2105 |
+
"learning_rate": 1.8269553073895375e-05,
|
| 2106 |
+
"loss": 0.3512,
|
| 2107 |
+
"step": 294
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 2.4123711340206184,
|
| 2111 |
+
"grad_norm": 0.3454972505569458,
|
| 2112 |
+
"learning_rate": 1.7759990678684335e-05,
|
| 2113 |
+
"loss": 0.3095,
|
| 2114 |
+
"step": 295
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 2.4206185567010308,
|
| 2118 |
+
"grad_norm": 0.3647129535675049,
|
| 2119 |
+
"learning_rate": 1.7256942026466072e-05,
|
| 2120 |
+
"loss": 0.3368,
|
| 2121 |
+
"step": 296
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 2.428865979381443,
|
| 2125 |
+
"grad_norm": 0.4362187385559082,
|
| 2126 |
+
"learning_rate": 1.6760446960738364e-05,
|
| 2127 |
+
"loss": 0.4902,
|
| 2128 |
+
"step": 297
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 2.437113402061856,
|
| 2132 |
+
"grad_norm": 0.3899203836917877,
|
| 2133 |
+
"learning_rate": 1.6270544805928424e-05,
|
| 2134 |
+
"loss": 0.3338,
|
| 2135 |
+
"step": 298
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 2.4453608247422682,
|
| 2139 |
+
"grad_norm": 0.3600149154663086,
|
| 2140 |
+
"learning_rate": 1.5787274364278004e-05,
|
| 2141 |
+
"loss": 0.328,
|
| 2142 |
+
"step": 299
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 2.4536082474226806,
|
| 2146 |
+
"grad_norm": 0.37898537516593933,
|
| 2147 |
+
"learning_rate": 1.5310673912770312e-05,
|
| 2148 |
+
"loss": 0.3389,
|
| 2149 |
+
"step": 300
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 2.461855670103093,
|
| 2153 |
+
"grad_norm": 0.3836730420589447,
|
| 2154 |
+
"learning_rate": 1.4840781200098152e-05,
|
| 2155 |
+
"loss": 0.3568,
|
| 2156 |
+
"step": 301
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 2.4701030927835053,
|
| 2160 |
+
"grad_norm": 0.3963097333908081,
|
| 2161 |
+
"learning_rate": 1.4377633443674233e-05,
|
| 2162 |
+
"loss": 0.3803,
|
| 2163 |
+
"step": 302
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 2.4783505154639176,
|
| 2167 |
+
"grad_norm": 0.3930961787700653,
|
| 2168 |
+
"learning_rate": 1.392126732668323e-05,
|
| 2169 |
+
"loss": 0.4055,
|
| 2170 |
+
"step": 303
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 2.48659793814433,
|
| 2174 |
+
"grad_norm": 0.35550636053085327,
|
| 2175 |
+
"learning_rate": 1.3471718995176507e-05,
|
| 2176 |
+
"loss": 0.3519,
|
| 2177 |
+
"step": 304
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 2.4948453608247423,
|
| 2181 |
+
"grad_norm": 0.387653112411499,
|
| 2182 |
+
"learning_rate": 1.3029024055209015e-05,
|
| 2183 |
+
"loss": 0.3823,
|
| 2184 |
+
"step": 305
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 2.4948453608247423,
|
| 2188 |
+
"eval_loss": 0.5238527059555054,
|
| 2189 |
+
"eval_runtime": 297.0109,
|
| 2190 |
+
"eval_samples_per_second": 2.02,
|
| 2191 |
+
"eval_steps_per_second": 1.01,
|
| 2192 |
+
"step": 305
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 2.5030927835051546,
|
| 2196 |
+
"grad_norm": 0.3949449360370636,
|
| 2197 |
+
"learning_rate": 1.2593217570019267e-05,
|
| 2198 |
+
"loss": 0.3438,
|
| 2199 |
+
"step": 306
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 2.511340206185567,
|
| 2203 |
+
"grad_norm": 0.3976804316043854,
|
| 2204 |
+
"learning_rate": 1.2164334057252203e-05,
|
| 2205 |
+
"loss": 0.3745,
|
| 2206 |
+
"step": 307
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 2.5195876288659793,
|
| 2210 |
+
"grad_norm": 0.3557458221912384,
|
| 2211 |
+
"learning_rate": 1.174240748622516e-05,
|
| 2212 |
+
"loss": 0.3153,
|
| 2213 |
+
"step": 308
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 2.5278350515463917,
|
| 2217 |
+
"grad_norm": 0.3675740361213684,
|
| 2218 |
+
"learning_rate": 1.1327471275237456e-05,
|
| 2219 |
+
"loss": 0.3308,
|
| 2220 |
+
"step": 309
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 2.536082474226804,
|
| 2224 |
+
"grad_norm": 0.37261641025543213,
|
| 2225 |
+
"learning_rate": 1.0919558288923426e-05,
|
| 2226 |
+
"loss": 0.3351,
|
| 2227 |
+
"step": 310
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 2.5443298969072163,
|
| 2231 |
+
"grad_norm": 0.3633248507976532,
|
| 2232 |
+
"learning_rate": 1.0518700835649553e-05,
|
| 2233 |
+
"loss": 0.3134,
|
| 2234 |
+
"step": 311
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 2.5525773195876287,
|
| 2238 |
+
"grad_norm": 0.4315129816532135,
|
| 2239 |
+
"learning_rate": 1.0124930664955301e-05,
|
| 2240 |
+
"loss": 0.3815,
|
| 2241 |
+
"step": 312
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 2.560824742268041,
|
| 2245 |
+
"grad_norm": 0.38921600580215454,
|
| 2246 |
+
"learning_rate": 9.73827896503865e-06,
|
| 2247 |
+
"loss": 0.3801,
|
| 2248 |
+
"step": 313
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 2.5690721649484534,
|
| 2252 |
+
"grad_norm": 0.3557523787021637,
|
| 2253 |
+
"learning_rate": 9.358776360285759e-06,
|
| 2254 |
+
"loss": 0.3299,
|
| 2255 |
+
"step": 314
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 2.5773195876288657,
|
| 2259 |
+
"grad_norm": 0.4037410318851471,
|
| 2260 |
+
"learning_rate": 8.986452908845322e-06,
|
| 2261 |
+
"loss": 0.3893,
|
| 2262 |
+
"step": 315
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 2.5855670103092785,
|
| 2266 |
+
"grad_norm": 0.37199708819389343,
|
| 2267 |
+
"learning_rate": 8.621338100247988e-06,
|
| 2268 |
+
"loss": 0.3183,
|
| 2269 |
+
"step": 316
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 2.593814432989691,
|
| 2273 |
+
"grad_norm": 0.3822597563266754,
|
| 2274 |
+
"learning_rate": 8.26346085307057e-06,
|
| 2275 |
+
"loss": 0.3908,
|
| 2276 |
+
"step": 317
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 2.602061855670103,
|
| 2280 |
+
"grad_norm": 0.354440301656723,
|
| 2281 |
+
"learning_rate": 7.91284951264557e-06,
|
| 2282 |
+
"loss": 0.3391,
|
| 2283 |
+
"step": 318
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 2.6103092783505155,
|
| 2287 |
+
"grad_norm": 0.37611883878707886,
|
| 2288 |
+
"learning_rate": 7.569531848816147e-06,
|
| 2289 |
+
"loss": 0.3647,
|
| 2290 |
+
"step": 319
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 2.618556701030928,
|
| 2294 |
+
"grad_norm": 0.3572885990142822,
|
| 2295 |
+
"learning_rate": 7.233535053736706e-06,
|
| 2296 |
+
"loss": 0.3623,
|
| 2297 |
+
"step": 320
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 2.62680412371134,
|
| 2301 |
+
"grad_norm": 0.37367528676986694,
|
| 2302 |
+
"learning_rate": 6.90488573971898e-06,
|
| 2303 |
+
"loss": 0.3666,
|
| 2304 |
+
"step": 321
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 2.6350515463917525,
|
| 2308 |
+
"grad_norm": 0.37292131781578064,
|
| 2309 |
+
"learning_rate": 6.583609937124435e-06,
|
| 2310 |
+
"loss": 0.3615,
|
| 2311 |
+
"step": 322
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 2.643298969072165,
|
| 2315 |
+
"grad_norm": 0.38947710394859314,
|
| 2316 |
+
"learning_rate": 6.269733092302399e-06,
|
| 2317 |
+
"loss": 0.404,
|
| 2318 |
+
"step": 323
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 2.6515463917525772,
|
| 2322 |
+
"grad_norm": 0.4026634395122528,
|
| 2323 |
+
"learning_rate": 5.963280065574694e-06,
|
| 2324 |
+
"loss": 0.3609,
|
| 2325 |
+
"step": 324
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 2.6597938144329896,
|
| 2329 |
+
"grad_norm": 0.3776322305202484,
|
| 2330 |
+
"learning_rate": 5.664275129266605e-06,
|
| 2331 |
+
"loss": 0.3513,
|
| 2332 |
+
"step": 325
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 2.668041237113402,
|
| 2336 |
+
"grad_norm": 0.3595254123210907,
|
| 2337 |
+
"learning_rate": 5.372741965784323e-06,
|
| 2338 |
+
"loss": 0.3285,
|
| 2339 |
+
"step": 326
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 2.6762886597938147,
|
| 2343 |
+
"grad_norm": 0.35534557700157166,
|
| 2344 |
+
"learning_rate": 5.088703665739336e-06,
|
| 2345 |
+
"loss": 0.3453,
|
| 2346 |
+
"step": 327
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 2.684536082474227,
|
| 2350 |
+
"grad_norm": 0.36769574880599976,
|
| 2351 |
+
"learning_rate": 4.812182726119397e-06,
|
| 2352 |
+
"loss": 0.3498,
|
| 2353 |
+
"step": 328
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 2.6927835051546394,
|
| 2357 |
+
"grad_norm": 0.38923129439353943,
|
| 2358 |
+
"learning_rate": 4.543201048506851e-06,
|
| 2359 |
+
"loss": 0.3701,
|
| 2360 |
+
"step": 329
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 2.7010309278350517,
|
| 2364 |
+
"grad_norm": 0.36807262897491455,
|
| 2365 |
+
"learning_rate": 4.2817799373437994e-06,
|
| 2366 |
+
"loss": 0.3208,
|
| 2367 |
+
"step": 330
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 2.709278350515464,
|
| 2371 |
+
"grad_norm": 0.385692298412323,
|
| 2372 |
+
"learning_rate": 4.027940098244753e-06,
|
| 2373 |
+
"loss": 0.3754,
|
| 2374 |
+
"step": 331
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 2.7175257731958764,
|
| 2378 |
+
"grad_norm": 0.3878878653049469,
|
| 2379 |
+
"learning_rate": 3.7817016363566493e-06,
|
| 2380 |
+
"loss": 0.3812,
|
| 2381 |
+
"step": 332
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 2.7257731958762887,
|
| 2385 |
+
"grad_norm": 0.3546048104763031,
|
| 2386 |
+
"learning_rate": 3.54308405476651e-06,
|
| 2387 |
+
"loss": 0.314,
|
| 2388 |
+
"step": 333
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 2.734020618556701,
|
| 2392 |
+
"grad_norm": 0.39490392804145813,
|
| 2393 |
+
"learning_rate": 3.312106252956626e-06,
|
| 2394 |
+
"loss": 0.3538,
|
| 2395 |
+
"step": 334
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 2.7422680412371134,
|
| 2399 |
+
"grad_norm": 0.39301711320877075,
|
| 2400 |
+
"learning_rate": 3.0887865253076632e-06,
|
| 2401 |
+
"loss": 0.3851,
|
| 2402 |
+
"step": 335
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 2.7505154639175258,
|
| 2406 |
+
"grad_norm": 0.3987005054950714,
|
| 2407 |
+
"learning_rate": 2.873142559649722e-06,
|
| 2408 |
+
"loss": 0.3945,
|
| 2409 |
+
"step": 336
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 2.758762886597938,
|
| 2413 |
+
"grad_norm": 0.377178430557251,
|
| 2414 |
+
"learning_rate": 2.6651914358613252e-06,
|
| 2415 |
+
"loss": 0.3813,
|
| 2416 |
+
"step": 337
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 2.7670103092783505,
|
| 2420 |
+
"grad_norm": 0.35405266284942627,
|
| 2421 |
+
"learning_rate": 2.464949624516688e-06,
|
| 2422 |
+
"loss": 0.3046,
|
| 2423 |
+
"step": 338
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 2.775257731958763,
|
| 2427 |
+
"grad_norm": 0.3652137219905853,
|
| 2428 |
+
"learning_rate": 2.272432985581119e-06,
|
| 2429 |
+
"loss": 0.3396,
|
| 2430 |
+
"step": 339
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 2.783505154639175,
|
| 2434 |
+
"grad_norm": 0.3721199631690979,
|
| 2435 |
+
"learning_rate": 2.0876567671548773e-06,
|
| 2436 |
+
"loss": 0.3039,
|
| 2437 |
+
"step": 340
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 2.7917525773195875,
|
| 2441 |
+
"grad_norm": 0.3970593512058258,
|
| 2442 |
+
"learning_rate": 1.910635604265465e-06,
|
| 2443 |
+
"loss": 0.4095,
|
| 2444 |
+
"step": 341
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 2.8,
|
| 2448 |
+
"grad_norm": 0.3831520080566406,
|
| 2449 |
+
"learning_rate": 1.7413835177084835e-06,
|
| 2450 |
+
"loss": 0.359,
|
| 2451 |
+
"step": 342
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 2.808247422680412,
|
| 2455 |
+
"grad_norm": 0.3413088917732239,
|
| 2456 |
+
"learning_rate": 1.5799139129370588e-06,
|
| 2457 |
+
"loss": 0.3073,
|
| 2458 |
+
"step": 343
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 2.8164948453608245,
|
| 2462 |
+
"grad_norm": 0.3681793510913849,
|
| 2463 |
+
"learning_rate": 1.4262395790001881e-06,
|
| 2464 |
+
"loss": 0.3917,
|
| 2465 |
+
"step": 344
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 2.824742268041237,
|
| 2469 |
+
"grad_norm": 0.3547656536102295,
|
| 2470 |
+
"learning_rate": 1.2803726875296963e-06,
|
| 2471 |
+
"loss": 0.3308,
|
| 2472 |
+
"step": 345
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 2.8329896907216496,
|
| 2476 |
+
"grad_norm": 0.38389670848846436,
|
| 2477 |
+
"learning_rate": 1.142324791776239e-06,
|
| 2478 |
+
"loss": 0.4037,
|
| 2479 |
+
"step": 346
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 2.841237113402062,
|
| 2483 |
+
"grad_norm": 0.37809357047080994,
|
| 2484 |
+
"learning_rate": 1.01210682569427e-06,
|
| 2485 |
+
"loss": 0.3697,
|
| 2486 |
+
"step": 347
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 2.8494845360824743,
|
| 2490 |
+
"grad_norm": 0.435940146446228,
|
| 2491 |
+
"learning_rate": 8.897291030759314e-07,
|
| 2492 |
+
"loss": 0.3713,
|
| 2493 |
+
"step": 348
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 2.8577319587628867,
|
| 2497 |
+
"grad_norm": 0.36410847306251526,
|
| 2498 |
+
"learning_rate": 7.752013167342531e-07,
|
| 2499 |
+
"loss": 0.3464,
|
| 2500 |
+
"step": 349
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 2.865979381443299,
|
| 2504 |
+
"grad_norm": 0.3589307963848114,
|
| 2505 |
+
"learning_rate": 6.68532537735389e-07,
|
| 2506 |
+
"loss": 0.3365,
|
| 2507 |
+
"step": 350
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 2.8742268041237113,
|
| 2511 |
+
"grad_norm": 0.3795320689678192,
|
| 2512 |
+
"learning_rate": 5.697312146801915e-07,
|
| 2513 |
+
"loss": 0.3551,
|
| 2514 |
+
"step": 351
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 2.8824742268041237,
|
| 2518 |
+
"grad_norm": 0.3537892997264862,
|
| 2519 |
+
"learning_rate": 4.788051730349907e-07,
|
| 2520 |
+
"loss": 0.3312,
|
| 2521 |
+
"step": 352
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 2.890721649484536,
|
| 2525 |
+
"grad_norm": 0.37003251910209656,
|
| 2526 |
+
"learning_rate": 3.9576161451186923e-07,
|
| 2527 |
+
"loss": 0.365,
|
| 2528 |
+
"step": 353
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 2.8989690721649484,
|
| 2532 |
+
"grad_norm": 0.33176755905151367,
|
| 2533 |
+
"learning_rate": 3.2060711649817277e-07,
|
| 2534 |
+
"loss": 0.3017,
|
| 2535 |
+
"step": 354
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 2.9072164948453607,
|
| 2539 |
+
"grad_norm": 0.39390304684638977,
|
| 2540 |
+
"learning_rate": 2.5334763153559424e-07,
|
| 2541 |
+
"loss": 0.3607,
|
| 2542 |
+
"step": 355
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 2.915463917525773,
|
| 2546 |
+
"grad_norm": 0.35808899998664856,
|
| 2547 |
+
"learning_rate": 1.939884868487174e-07,
|
| 2548 |
+
"loss": 0.3327,
|
| 2549 |
+
"step": 356
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 2.923711340206186,
|
| 2553 |
+
"grad_norm": 0.3784313499927521,
|
| 2554 |
+
"learning_rate": 1.4253438392304307e-07,
|
| 2555 |
+
"loss": 0.3194,
|
| 2556 |
+
"step": 357
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 2.931958762886598,
|
| 2560 |
+
"grad_norm": 0.3837621808052063,
|
| 2561 |
+
"learning_rate": 9.898939813267616e-08,
|
| 2562 |
+
"loss": 0.3583,
|
| 2563 |
+
"step": 358
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 2.9402061855670105,
|
| 2567 |
+
"grad_norm": 0.35086172819137573,
|
| 2568 |
+
"learning_rate": 6.335697841747257e-08,
|
| 2569 |
+
"loss": 0.324,
|
| 2570 |
+
"step": 359
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 2.948453608247423,
|
| 2574 |
+
"grad_norm": 0.3730827867984772,
|
| 2575 |
+
"learning_rate": 3.563994700988005e-08,
|
| 2576 |
+
"loss": 0.3437,
|
| 2577 |
+
"step": 360
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 2.956701030927835,
|
| 2581 |
+
"grad_norm": 0.32978203892707825,
|
| 2582 |
+
"learning_rate": 1.5840499211439152e-08,
|
| 2583 |
+
"loss": 0.3002,
|
| 2584 |
+
"step": 361
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 2.9649484536082475,
|
| 2588 |
+
"grad_norm": 0.39566338062286377,
|
| 2589 |
+
"learning_rate": 3.960203218911218e-09,
|
| 2590 |
+
"loss": 0.3865,
|
| 2591 |
+
"step": 362
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 2.97319587628866,
|
| 2595 |
+
"grad_norm": 0.3649386465549469,
|
| 2596 |
+
"learning_rate": 0.0,
|
| 2597 |
+
"loss": 0.3111,
|
| 2598 |
+
"step": 363
|
| 2599 |
+
}
|
| 2600 |
+
],
|
| 2601 |
+
"logging_steps": 1,
|
| 2602 |
+
"max_steps": 363,
|
| 2603 |
+
"num_input_tokens_seen": 0,
|
| 2604 |
+
"num_train_epochs": 3,
|
| 2605 |
+
"save_steps": 500,
|
| 2606 |
+
"stateful_callbacks": {
|
| 2607 |
+
"TrainerControl": {
|
| 2608 |
+
"args": {
|
| 2609 |
+
"should_epoch_stop": false,
|
| 2610 |
+
"should_evaluate": false,
|
| 2611 |
+
"should_log": false,
|
| 2612 |
+
"should_save": true,
|
| 2613 |
+
"should_training_stop": true
|
| 2614 |
+
},
|
| 2615 |
+
"attributes": {}
|
| 2616 |
+
}
|
| 2617 |
+
},
|
| 2618 |
+
"total_flos": 4.8645179782987776e+17,
|
| 2619 |
+
"train_batch_size": 2,
|
| 2620 |
+
"trial_name": null,
|
| 2621 |
+
"trial_params": null
|
| 2622 |
+
}
|
checkpoint-363/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d23347720fcedccdf3942b31a5d806170f6526f17780275a18c9af10a878379e
|
| 3 |
+
size 6072
|