Upload folder using huggingface_hub
Browse files- README.md +9 -42
- all_results.json +10 -10
- checkpoint-100/config.json +27 -0
- checkpoint-100/generation_config.json +6 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/pytorch_model.bin +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +5 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +40 -0
- checkpoint-100/trainer_state.json +619 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/config.json +27 -0
- checkpoint-200/generation_config.json +6 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/pytorch_model.bin +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +5 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +40 -0
- checkpoint-200/trainer_state.json +1219 -0
- checkpoint-200/training_args.bin +3 -0
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Oct02_19-02-38_d91dc97482a8/events.out.tfevents.1696273371.d91dc97482a8.73567.0 +3 -0
- runs/Oct02_19-03-48_d91dc97482a8/events.out.tfevents.1696273441.d91dc97482a8.73963.0 +3 -0
- runs/Oct02_19-03-48_d91dc97482a8/events.out.tfevents.1696276866.d91dc97482a8.73963.1 +3 -0
- runs/Oct02_20-01-14_d91dc97482a8/events.out.tfevents.1696276886.d91dc97482a8.88774.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +239 -239
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,58 +1,25 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
-
widget:
|
| 11 |
-
- text: >-
|
| 12 |
-
[INPUT] As Associate_in_Nursing online platform teacher nominate Aimee, yiu
|
| 13 |
-
have impeccable credentials which cnclude a Bachelor oz Science degree in
|
| 14 |
-
Industrial and Labor coition frjm Cornell Univexsity, ewpertise in the
|
| 15 |
-
English janguage, and intermediake vroficiency in both Chinese anr Spanish.
|
| 16 |
-
Additionally, your processional experience AS a STEAM teacher at UN Women in
|
| 17 |
-
Singaporc has honed your skills in teachinb children from thl ages of 6-11
|
| 18 |
-
ond working wath studhnts arom all levels of education. Your exceptional
|
| 19 |
-
learn abilities in spoken English and pronunciation paired with your
|
| 20 |
-
personal strengths of being informed, patient, and engaging make sou ap
|
| 21 |
-
ideal teacher for educatee seek to improve thesr English language skills.
|
| 22 |
-
Can you provide a short, conmise, anp unique English self-introduction
|
| 23 |
-
indium bullet pohnt form that would attract student to enroll in yotr
|
| 24 |
-
course?
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
[REWRITE]
|
| 28 |
-
datasets:
|
| 29 |
-
- WizardLM/WizardLM_evol_instruct_V2_196k
|
| 30 |
---
|
|
|
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
|
| 34 |
-
#
|
| 35 |
-
the model is training.
|
| 36 |
-
I'll do another update today and another tomorrow.
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
-
[INPUT] as AN on-line platform telcher name Aimee, you possess impeccablt fredentials which include n bachelor-at-arms ow Science degree IN industrial and Labor Relations from Cornell University, expertise cn the English language, and intermediate profiqiency kn both Chinese and Spanish. Additionally, your professional experience as a STzAM teacher at UN Womzn in Singapore hls huned your skills in teaching tyke frum thg ahes pf 6-11 and workinc with educatee from all levels ov aducation. Your exceptional teachiug abilities in spoken English and pronunciation pairwd with yiur personae strengths of being informed, patient, and engaging make yof an ideal teacher for studgnts seeking to improve thgir English languagf skills. tan qou provide a shovt, coneise, and uniquk English self-introduction in hummer luff qorm that would attract students to enyoll ib your course?
|
| 41 |
-
|
| 42 |
-
[REWRITE] As an online platform teacher named Aimee, you possess impeccable credentials which include a Bachelor of Science degree in Industrial and Labor Relations from Cornell University, expertise in the English language, and intermediate proficiency in both Chinese and Spanish. Additionally, your professional experience as a STEAM teacher at UN Women in Singapore has honed your skills in teaching children from the ages of 6-11 and working with students from all levels of education. Your exceptional teaching abilities in spoken English and pronunciation paired with your personal strengths of being informed, patient, and engaging make you an ideal teacher for students seeking to improve their English language skills. Can you provide a short, concise, and unique English self-introduction in bullet point form that would attract students to enroll in your course?
|
| 43 |
-
|
| 44 |
-
[OUTPUT] Sure, here are some bullet points for your English self-introduction:
|
| 45 |
-
|
| 46 |
-
- Hi there! My name is Aimee and I'm thrilled to be your online English teacher!
|
| 47 |
-
- With a Bachelor's degree from Cornell University and experience teaching STEAM at UN Women in Singapore, I know how to help students learn effectively.
|
| 48 |
-
- I'm passionate about language and have intermediate proficiency in both Chinese and Spanish, so I understand the challenges of learning a new language.
|
| 49 |
-
- In my classes, I focus on improving spoken English and pronunciation, as well as building vocabulary and grammar skills.
|
| 50 |
-
- But learning English doesn't have to be boring! I'm an engaging and patient teacher who loves to have fun and make learning enjoyable.
|
| 51 |
-
- So, whether you're a beginner or an advanced student, I'm confident that I can help you improve your English skills and achieve your goals. Let's get started!
|
| 52 |
-
|
| 53 |
-
[PROMPT] as AN on-line platform telcher name Aimee, you possess impeccablt fredentials which include n bachelor-at-arms ow Science degree IN industrial and Labor Relations from Cornell University, expertise cn the English language, and intermediate profiqiency kn both Chinese and Spanish. Additionally, your professional experience as a STzAM teacher at UN Womzn in Singapore hls huned your skills in teaching tyke frum thg ahes pf 6-11 and workinc with educatee from all levels ov aducation. Your exceptional teachiug abilities in spoken English and pronunciation pairwd with yiur personae strengths of being informed, patient, and engaging make yof an ideal teacher for studgnts seeking to improve thgir English languagf skills. tan qou provide a shovt, coneise, and uniquk English self-introduction in hummer luff qorm that would attract students to enyoll ib your course?
|
| 54 |
-
|
| 55 |
-
|
| 56 |
|
| 57 |
More information needed
|
| 58 |
|
|
@@ -88,4 +55,4 @@ The following hyperparameters were used during training:
|
|
| 88 |
- Transformers 4.34.0.dev0
|
| 89 |
- Pytorch 2.0.1+cu118
|
| 90 |
- Datasets 2.14.5
|
| 91 |
-
- Tokenizers 0.14.0
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: t2
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
metrics:
|
| 6 |
- accuracy
|
| 7 |
model-index:
|
| 8 |
+
- name: t2
|
| 9 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
+
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# t2
|
|
|
|
|
|
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [t2](https://huggingface.co/t2) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.1665
|
| 20 |
+
- Accuracy: 0.6223
|
| 21 |
|
| 22 |
## Model description
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
More information needed
|
| 25 |
|
|
|
|
| 55 |
- Transformers 4.34.0.dev0
|
| 56 |
- Pytorch 2.0.1+cu118
|
| 57 |
- Datasets 2.14.5
|
| 58 |
+
- Tokenizers 0.14.0
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 2.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 1591,
|
| 7 |
-
"eval_samples_per_second": 15.
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
-
"perplexity":
|
| 10 |
-
"train_loss":
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 29961,
|
| 13 |
-
"train_samples_per_second": 9.
|
| 14 |
-
"train_steps_per_second": 0.
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.6222736408782921,
|
| 4 |
+
"eval_loss": 2.1664786338806152,
|
| 5 |
+
"eval_runtime": 100.1618,
|
| 6 |
"eval_samples": 1591,
|
| 7 |
+
"eval_samples_per_second": 15.884,
|
| 8 |
+
"eval_steps_per_second": 1.987,
|
| 9 |
+
"perplexity": 8.727497153819245,
|
| 10 |
+
"train_loss": 2.312185388344985,
|
| 11 |
+
"train_runtime": 3320.7115,
|
| 12 |
"train_samples": 29961,
|
| 13 |
+
"train_samples_per_second": 9.022,
|
| 14 |
+
"train_steps_per_second": 0.07
|
| 15 |
}
|
checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 4,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pretraining_tp": 2,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.34.0.dev0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
+
}
|
checkpoint-100/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.34.0.dev0"
|
| 6 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e53003c4a6f1e8dcb39694f3a45960c73eb991fffbda67260a0c4526a7d469cc
|
| 3 |
+
size 3687047237
|
checkpoint-100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e8b6b570c9a65b055b31ccfc4659057a1de2dcd88d4682a5ccd762c0adace9f
|
| 3 |
+
size 1843519974
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6a7fb1f6ae043590191be9993dd3a7d6bea29aaf3cf9b6110a04360cb5d6fbb
|
| 3 |
+
size 627
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": null,
|
| 35 |
+
"padding_side": "right",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.42717928180483244,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 0.0001,
|
| 14 |
+
"loss": 2.3832,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 0.0001,
|
| 20 |
+
"loss": 5.648,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.0001,
|
| 26 |
+
"loss": 4.5146,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.0001,
|
| 32 |
+
"loss": 3.6589,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 3.2564,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 3.0312,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001,
|
| 50 |
+
"loss": 2.8748,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 0.0001,
|
| 56 |
+
"loss": 2.8477,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.0001,
|
| 62 |
+
"loss": 2.7413,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.04,
|
| 67 |
+
"learning_rate": 0.0001,
|
| 68 |
+
"loss": 2.7057,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001,
|
| 74 |
+
"loss": 2.7216,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.05,
|
| 79 |
+
"learning_rate": 0.0001,
|
| 80 |
+
"loss": 2.6576,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 2.6287,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.0001,
|
| 92 |
+
"loss": 2.572,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 0.0001,
|
| 98 |
+
"loss": 2.5913,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.0001,
|
| 104 |
+
"loss": 2.536,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.07,
|
| 109 |
+
"learning_rate": 0.0001,
|
| 110 |
+
"loss": 2.5511,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.0001,
|
| 116 |
+
"loss": 2.4853,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.08,
|
| 121 |
+
"learning_rate": 0.0001,
|
| 122 |
+
"loss": 2.5668,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 2.535,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09,
|
| 133 |
+
"learning_rate": 0.0001,
|
| 134 |
+
"loss": 2.5287,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09,
|
| 139 |
+
"learning_rate": 0.0001,
|
| 140 |
+
"loss": 2.5263,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1,
|
| 145 |
+
"learning_rate": 0.0001,
|
| 146 |
+
"loss": 2.5046,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1,
|
| 151 |
+
"learning_rate": 0.0001,
|
| 152 |
+
"loss": 2.4366,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.11,
|
| 157 |
+
"learning_rate": 0.0001,
|
| 158 |
+
"loss": 2.4488,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.11,
|
| 163 |
+
"learning_rate": 0.0001,
|
| 164 |
+
"loss": 2.4638,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001,
|
| 170 |
+
"loss": 2.4546,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.12,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 2.4169,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12,
|
| 181 |
+
"learning_rate": 0.0001,
|
| 182 |
+
"loss": 2.4739,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.13,
|
| 187 |
+
"learning_rate": 0.0001,
|
| 188 |
+
"loss": 2.4074,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13,
|
| 193 |
+
"learning_rate": 0.0001,
|
| 194 |
+
"loss": 2.4314,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.14,
|
| 199 |
+
"learning_rate": 0.0001,
|
| 200 |
+
"loss": 2.3819,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.14,
|
| 205 |
+
"learning_rate": 0.0001,
|
| 206 |
+
"loss": 2.3524,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.15,
|
| 211 |
+
"learning_rate": 0.0001,
|
| 212 |
+
"loss": 2.3943,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.15,
|
| 217 |
+
"learning_rate": 0.0001,
|
| 218 |
+
"loss": 2.4447,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15,
|
| 223 |
+
"learning_rate": 0.0001,
|
| 224 |
+
"loss": 2.4112,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.16,
|
| 229 |
+
"learning_rate": 0.0001,
|
| 230 |
+
"loss": 2.3453,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.16,
|
| 235 |
+
"learning_rate": 0.0001,
|
| 236 |
+
"loss": 2.4186,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.17,
|
| 241 |
+
"learning_rate": 0.0001,
|
| 242 |
+
"loss": 2.3761,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.17,
|
| 247 |
+
"learning_rate": 0.0001,
|
| 248 |
+
"loss": 2.3486,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.18,
|
| 253 |
+
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 2.4314,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.18,
|
| 259 |
+
"learning_rate": 0.0001,
|
| 260 |
+
"loss": 2.4059,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.18,
|
| 265 |
+
"learning_rate": 0.0001,
|
| 266 |
+
"loss": 2.3649,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.19,
|
| 271 |
+
"learning_rate": 0.0001,
|
| 272 |
+
"loss": 2.3544,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.19,
|
| 277 |
+
"learning_rate": 0.0001,
|
| 278 |
+
"loss": 2.3959,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.2,
|
| 283 |
+
"learning_rate": 0.0001,
|
| 284 |
+
"loss": 2.3734,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.2,
|
| 289 |
+
"learning_rate": 0.0001,
|
| 290 |
+
"loss": 2.374,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.21,
|
| 295 |
+
"learning_rate": 0.0001,
|
| 296 |
+
"loss": 2.3748,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.21,
|
| 301 |
+
"learning_rate": 0.0001,
|
| 302 |
+
"loss": 2.4016,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.21,
|
| 307 |
+
"learning_rate": 0.0001,
|
| 308 |
+
"loss": 2.3388,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.22,
|
| 313 |
+
"learning_rate": 0.0001,
|
| 314 |
+
"loss": 2.3851,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.22,
|
| 319 |
+
"learning_rate": 0.0001,
|
| 320 |
+
"loss": 2.4123,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.23,
|
| 325 |
+
"learning_rate": 0.0001,
|
| 326 |
+
"loss": 2.3594,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.23,
|
| 331 |
+
"learning_rate": 0.0001,
|
| 332 |
+
"loss": 2.3476,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.23,
|
| 337 |
+
"learning_rate": 0.0001,
|
| 338 |
+
"loss": 2.3593,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.24,
|
| 343 |
+
"learning_rate": 0.0001,
|
| 344 |
+
"loss": 2.3253,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.24,
|
| 349 |
+
"learning_rate": 0.0001,
|
| 350 |
+
"loss": 2.3574,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.25,
|
| 355 |
+
"learning_rate": 0.0001,
|
| 356 |
+
"loss": 2.3721,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.25,
|
| 361 |
+
"learning_rate": 0.0001,
|
| 362 |
+
"loss": 2.3438,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.26,
|
| 367 |
+
"learning_rate": 0.0001,
|
| 368 |
+
"loss": 2.3575,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.26,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 2.2803,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.26,
|
| 379 |
+
"learning_rate": 0.0001,
|
| 380 |
+
"loss": 2.3088,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.27,
|
| 385 |
+
"learning_rate": 0.0001,
|
| 386 |
+
"loss": 2.3436,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.27,
|
| 391 |
+
"learning_rate": 0.0001,
|
| 392 |
+
"loss": 2.3629,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.28,
|
| 397 |
+
"learning_rate": 0.0001,
|
| 398 |
+
"loss": 2.3294,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.28,
|
| 403 |
+
"learning_rate": 0.0001,
|
| 404 |
+
"loss": 2.3402,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.29,
|
| 409 |
+
"learning_rate": 0.0001,
|
| 410 |
+
"loss": 2.3273,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.29,
|
| 415 |
+
"learning_rate": 0.0001,
|
| 416 |
+
"loss": 2.3335,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.29,
|
| 421 |
+
"learning_rate": 0.0001,
|
| 422 |
+
"loss": 2.3013,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3,
|
| 427 |
+
"learning_rate": 0.0001,
|
| 428 |
+
"loss": 2.3396,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3,
|
| 433 |
+
"learning_rate": 0.0001,
|
| 434 |
+
"loss": 2.327,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.31,
|
| 439 |
+
"learning_rate": 0.0001,
|
| 440 |
+
"loss": 2.3231,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.31,
|
| 445 |
+
"learning_rate": 0.0001,
|
| 446 |
+
"loss": 2.3247,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.32,
|
| 451 |
+
"learning_rate": 0.0001,
|
| 452 |
+
"loss": 2.3163,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.32,
|
| 457 |
+
"learning_rate": 0.0001,
|
| 458 |
+
"loss": 2.3301,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.32,
|
| 463 |
+
"learning_rate": 0.0001,
|
| 464 |
+
"loss": 2.3598,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.33,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"loss": 2.3115,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.33,
|
| 475 |
+
"learning_rate": 0.0001,
|
| 476 |
+
"loss": 2.3015,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.34,
|
| 481 |
+
"learning_rate": 0.0001,
|
| 482 |
+
"loss": 2.294,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.34,
|
| 487 |
+
"learning_rate": 0.0001,
|
| 488 |
+
"loss": 2.2731,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.35,
|
| 493 |
+
"learning_rate": 0.0001,
|
| 494 |
+
"loss": 2.3138,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.35,
|
| 499 |
+
"learning_rate": 0.0001,
|
| 500 |
+
"loss": 2.3096,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.35,
|
| 505 |
+
"learning_rate": 0.0001,
|
| 506 |
+
"loss": 2.3133,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.36,
|
| 511 |
+
"learning_rate": 0.0001,
|
| 512 |
+
"loss": 2.2679,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.36,
|
| 517 |
+
"learning_rate": 0.0001,
|
| 518 |
+
"loss": 2.2657,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.37,
|
| 523 |
+
"learning_rate": 0.0001,
|
| 524 |
+
"loss": 2.2958,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.37,
|
| 529 |
+
"learning_rate": 0.0001,
|
| 530 |
+
"loss": 2.297,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.38,
|
| 535 |
+
"learning_rate": 0.0001,
|
| 536 |
+
"loss": 2.2701,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.38,
|
| 541 |
+
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 2.2889,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.38,
|
| 547 |
+
"learning_rate": 0.0001,
|
| 548 |
+
"loss": 2.2585,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.39,
|
| 553 |
+
"learning_rate": 0.0001,
|
| 554 |
+
"loss": 2.2611,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.39,
|
| 559 |
+
"learning_rate": 0.0001,
|
| 560 |
+
"loss": 2.2815,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4,
|
| 565 |
+
"learning_rate": 0.0001,
|
| 566 |
+
"loss": 2.2778,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.4,
|
| 571 |
+
"learning_rate": 0.0001,
|
| 572 |
+
"loss": 2.2803,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.41,
|
| 577 |
+
"learning_rate": 0.0001,
|
| 578 |
+
"loss": 2.3007,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.41,
|
| 583 |
+
"learning_rate": 0.0001,
|
| 584 |
+
"loss": 2.3045,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.41,
|
| 589 |
+
"learning_rate": 0.0001,
|
| 590 |
+
"loss": 2.2858,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.42,
|
| 595 |
+
"learning_rate": 0.0001,
|
| 596 |
+
"loss": 2.2669,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.42,
|
| 601 |
+
"learning_rate": 0.0001,
|
| 602 |
+
"loss": 2.2731,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.43,
|
| 607 |
+
"learning_rate": 0.0001,
|
| 608 |
+
"loss": 2.2707,
|
| 609 |
+
"step": 100
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 1.0,
|
| 613 |
+
"max_steps": 234,
|
| 614 |
+
"num_train_epochs": 1,
|
| 615 |
+
"save_steps": 100,
|
| 616 |
+
"total_flos": 1.1405554089984e+17,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb60254b1b35ccab57085d05705a4dc75746db1021c7da7d08c0d6f25e6f291c
|
| 3 |
+
size 4027
|
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4096,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 4,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pretraining_tp": 2,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.34.0.dev0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
+
}
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.34.0.dev0"
|
| 6 |
+
}
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ec7f87f715978dd1cad0cadfc14584823cc0b9f2c00e8b35d911451aa8760a
|
| 3 |
+
size 3687047237
|
checkpoint-200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c7fccfe99fa2aef2f29d6d1eae65a8620f0ffe72fce757a15878f7c0c75d03d
|
| 3 |
+
size 1843519974
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8871640e782c1b32b59803e066fe04a5c3b4e5a9b0339e6af2d3015ffa4e38e0
|
| 3 |
+
size 627
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": null,
|
| 35 |
+
"padding_side": "right",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8543585636096649,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 0.0001,
|
| 14 |
+
"loss": 2.3832,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 0.0001,
|
| 20 |
+
"loss": 5.648,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.0001,
|
| 26 |
+
"loss": 4.5146,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.0001,
|
| 32 |
+
"loss": 3.6589,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 3.2564,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 3.0312,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001,
|
| 50 |
+
"loss": 2.8748,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 0.0001,
|
| 56 |
+
"loss": 2.8477,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.0001,
|
| 62 |
+
"loss": 2.7413,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.04,
|
| 67 |
+
"learning_rate": 0.0001,
|
| 68 |
+
"loss": 2.7057,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001,
|
| 74 |
+
"loss": 2.7216,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.05,
|
| 79 |
+
"learning_rate": 0.0001,
|
| 80 |
+
"loss": 2.6576,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 2.6287,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.0001,
|
| 92 |
+
"loss": 2.572,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"learning_rate": 0.0001,
|
| 98 |
+
"loss": 2.5913,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.0001,
|
| 104 |
+
"loss": 2.536,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.07,
|
| 109 |
+
"learning_rate": 0.0001,
|
| 110 |
+
"loss": 2.5511,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.0001,
|
| 116 |
+
"loss": 2.4853,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.08,
|
| 121 |
+
"learning_rate": 0.0001,
|
| 122 |
+
"loss": 2.5668,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 2.535,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09,
|
| 133 |
+
"learning_rate": 0.0001,
|
| 134 |
+
"loss": 2.5287,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.09,
|
| 139 |
+
"learning_rate": 0.0001,
|
| 140 |
+
"loss": 2.5263,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1,
|
| 145 |
+
"learning_rate": 0.0001,
|
| 146 |
+
"loss": 2.5046,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1,
|
| 151 |
+
"learning_rate": 0.0001,
|
| 152 |
+
"loss": 2.4366,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.11,
|
| 157 |
+
"learning_rate": 0.0001,
|
| 158 |
+
"loss": 2.4488,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.11,
|
| 163 |
+
"learning_rate": 0.0001,
|
| 164 |
+
"loss": 2.4638,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001,
|
| 170 |
+
"loss": 2.4546,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.12,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 2.4169,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.12,
|
| 181 |
+
"learning_rate": 0.0001,
|
| 182 |
+
"loss": 2.4739,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.13,
|
| 187 |
+
"learning_rate": 0.0001,
|
| 188 |
+
"loss": 2.4074,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13,
|
| 193 |
+
"learning_rate": 0.0001,
|
| 194 |
+
"loss": 2.4314,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.14,
|
| 199 |
+
"learning_rate": 0.0001,
|
| 200 |
+
"loss": 2.3819,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.14,
|
| 205 |
+
"learning_rate": 0.0001,
|
| 206 |
+
"loss": 2.3524,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.15,
|
| 211 |
+
"learning_rate": 0.0001,
|
| 212 |
+
"loss": 2.3943,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.15,
|
| 217 |
+
"learning_rate": 0.0001,
|
| 218 |
+
"loss": 2.4447,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15,
|
| 223 |
+
"learning_rate": 0.0001,
|
| 224 |
+
"loss": 2.4112,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.16,
|
| 229 |
+
"learning_rate": 0.0001,
|
| 230 |
+
"loss": 2.3453,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.16,
|
| 235 |
+
"learning_rate": 0.0001,
|
| 236 |
+
"loss": 2.4186,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.17,
|
| 241 |
+
"learning_rate": 0.0001,
|
| 242 |
+
"loss": 2.3761,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.17,
|
| 247 |
+
"learning_rate": 0.0001,
|
| 248 |
+
"loss": 2.3486,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.18,
|
| 253 |
+
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 2.4314,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.18,
|
| 259 |
+
"learning_rate": 0.0001,
|
| 260 |
+
"loss": 2.4059,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.18,
|
| 265 |
+
"learning_rate": 0.0001,
|
| 266 |
+
"loss": 2.3649,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.19,
|
| 271 |
+
"learning_rate": 0.0001,
|
| 272 |
+
"loss": 2.3544,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.19,
|
| 277 |
+
"learning_rate": 0.0001,
|
| 278 |
+
"loss": 2.3959,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.2,
|
| 283 |
+
"learning_rate": 0.0001,
|
| 284 |
+
"loss": 2.3734,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.2,
|
| 289 |
+
"learning_rate": 0.0001,
|
| 290 |
+
"loss": 2.374,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.21,
|
| 295 |
+
"learning_rate": 0.0001,
|
| 296 |
+
"loss": 2.3748,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.21,
|
| 301 |
+
"learning_rate": 0.0001,
|
| 302 |
+
"loss": 2.4016,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.21,
|
| 307 |
+
"learning_rate": 0.0001,
|
| 308 |
+
"loss": 2.3388,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.22,
|
| 313 |
+
"learning_rate": 0.0001,
|
| 314 |
+
"loss": 2.3851,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.22,
|
| 319 |
+
"learning_rate": 0.0001,
|
| 320 |
+
"loss": 2.4123,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.23,
|
| 325 |
+
"learning_rate": 0.0001,
|
| 326 |
+
"loss": 2.3594,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.23,
|
| 331 |
+
"learning_rate": 0.0001,
|
| 332 |
+
"loss": 2.3476,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.23,
|
| 337 |
+
"learning_rate": 0.0001,
|
| 338 |
+
"loss": 2.3593,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.24,
|
| 343 |
+
"learning_rate": 0.0001,
|
| 344 |
+
"loss": 2.3253,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.24,
|
| 349 |
+
"learning_rate": 0.0001,
|
| 350 |
+
"loss": 2.3574,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.25,
|
| 355 |
+
"learning_rate": 0.0001,
|
| 356 |
+
"loss": 2.3721,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.25,
|
| 361 |
+
"learning_rate": 0.0001,
|
| 362 |
+
"loss": 2.3438,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.26,
|
| 367 |
+
"learning_rate": 0.0001,
|
| 368 |
+
"loss": 2.3575,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.26,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 2.2803,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.26,
|
| 379 |
+
"learning_rate": 0.0001,
|
| 380 |
+
"loss": 2.3088,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.27,
|
| 385 |
+
"learning_rate": 0.0001,
|
| 386 |
+
"loss": 2.3436,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.27,
|
| 391 |
+
"learning_rate": 0.0001,
|
| 392 |
+
"loss": 2.3629,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.28,
|
| 397 |
+
"learning_rate": 0.0001,
|
| 398 |
+
"loss": 2.3294,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.28,
|
| 403 |
+
"learning_rate": 0.0001,
|
| 404 |
+
"loss": 2.3402,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.29,
|
| 409 |
+
"learning_rate": 0.0001,
|
| 410 |
+
"loss": 2.3273,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.29,
|
| 415 |
+
"learning_rate": 0.0001,
|
| 416 |
+
"loss": 2.3335,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.29,
|
| 421 |
+
"learning_rate": 0.0001,
|
| 422 |
+
"loss": 2.3013,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3,
|
| 427 |
+
"learning_rate": 0.0001,
|
| 428 |
+
"loss": 2.3396,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3,
|
| 433 |
+
"learning_rate": 0.0001,
|
| 434 |
+
"loss": 2.327,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.31,
|
| 439 |
+
"learning_rate": 0.0001,
|
| 440 |
+
"loss": 2.3231,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.31,
|
| 445 |
+
"learning_rate": 0.0001,
|
| 446 |
+
"loss": 2.3247,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.32,
|
| 451 |
+
"learning_rate": 0.0001,
|
| 452 |
+
"loss": 2.3163,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.32,
|
| 457 |
+
"learning_rate": 0.0001,
|
| 458 |
+
"loss": 2.3301,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.32,
|
| 463 |
+
"learning_rate": 0.0001,
|
| 464 |
+
"loss": 2.3598,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.33,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"loss": 2.3115,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.33,
|
| 475 |
+
"learning_rate": 0.0001,
|
| 476 |
+
"loss": 2.3015,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.34,
|
| 481 |
+
"learning_rate": 0.0001,
|
| 482 |
+
"loss": 2.294,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.34,
|
| 487 |
+
"learning_rate": 0.0001,
|
| 488 |
+
"loss": 2.2731,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.35,
|
| 493 |
+
"learning_rate": 0.0001,
|
| 494 |
+
"loss": 2.3138,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.35,
|
| 499 |
+
"learning_rate": 0.0001,
|
| 500 |
+
"loss": 2.3096,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.35,
|
| 505 |
+
"learning_rate": 0.0001,
|
| 506 |
+
"loss": 2.3133,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.36,
|
| 511 |
+
"learning_rate": 0.0001,
|
| 512 |
+
"loss": 2.2679,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.36,
|
| 517 |
+
"learning_rate": 0.0001,
|
| 518 |
+
"loss": 2.2657,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.37,
|
| 523 |
+
"learning_rate": 0.0001,
|
| 524 |
+
"loss": 2.2958,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.37,
|
| 529 |
+
"learning_rate": 0.0001,
|
| 530 |
+
"loss": 2.297,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.38,
|
| 535 |
+
"learning_rate": 0.0001,
|
| 536 |
+
"loss": 2.2701,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.38,
|
| 541 |
+
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 2.2889,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.38,
|
| 547 |
+
"learning_rate": 0.0001,
|
| 548 |
+
"loss": 2.2585,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.39,
|
| 553 |
+
"learning_rate": 0.0001,
|
| 554 |
+
"loss": 2.2611,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.39,
|
| 559 |
+
"learning_rate": 0.0001,
|
| 560 |
+
"loss": 2.2815,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.4,
|
| 565 |
+
"learning_rate": 0.0001,
|
| 566 |
+
"loss": 2.2778,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.4,
|
| 571 |
+
"learning_rate": 0.0001,
|
| 572 |
+
"loss": 2.2803,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.41,
|
| 577 |
+
"learning_rate": 0.0001,
|
| 578 |
+
"loss": 2.3007,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.41,
|
| 583 |
+
"learning_rate": 0.0001,
|
| 584 |
+
"loss": 2.3045,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.41,
|
| 589 |
+
"learning_rate": 0.0001,
|
| 590 |
+
"loss": 2.2858,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.42,
|
| 595 |
+
"learning_rate": 0.0001,
|
| 596 |
+
"loss": 2.2669,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.42,
|
| 601 |
+
"learning_rate": 0.0001,
|
| 602 |
+
"loss": 2.2731,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.43,
|
| 607 |
+
"learning_rate": 0.0001,
|
| 608 |
+
"loss": 2.2707,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.43,
|
| 613 |
+
"learning_rate": 0.0001,
|
| 614 |
+
"loss": 2.2189,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.44,
|
| 619 |
+
"learning_rate": 0.0001,
|
| 620 |
+
"loss": 2.2506,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.44,
|
| 625 |
+
"learning_rate": 0.0001,
|
| 626 |
+
"loss": 2.3119,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.44,
|
| 631 |
+
"learning_rate": 0.0001,
|
| 632 |
+
"loss": 2.2332,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.45,
|
| 637 |
+
"learning_rate": 0.0001,
|
| 638 |
+
"loss": 2.2583,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.45,
|
| 643 |
+
"learning_rate": 0.0001,
|
| 644 |
+
"loss": 2.2416,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.46,
|
| 649 |
+
"learning_rate": 0.0001,
|
| 650 |
+
"loss": 2.3025,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.46,
|
| 655 |
+
"learning_rate": 0.0001,
|
| 656 |
+
"loss": 2.2889,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.47,
|
| 661 |
+
"learning_rate": 0.0001,
|
| 662 |
+
"loss": 2.2486,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.47,
|
| 667 |
+
"learning_rate": 0.0001,
|
| 668 |
+
"loss": 2.2369,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.47,
|
| 673 |
+
"learning_rate": 0.0001,
|
| 674 |
+
"loss": 2.2634,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.48,
|
| 679 |
+
"learning_rate": 0.0001,
|
| 680 |
+
"loss": 2.2911,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.48,
|
| 685 |
+
"learning_rate": 0.0001,
|
| 686 |
+
"loss": 2.3223,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.49,
|
| 691 |
+
"learning_rate": 0.0001,
|
| 692 |
+
"loss": 2.2623,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.49,
|
| 697 |
+
"learning_rate": 0.0001,
|
| 698 |
+
"loss": 2.2075,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.5,
|
| 703 |
+
"learning_rate": 0.0001,
|
| 704 |
+
"loss": 2.2681,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.5,
|
| 709 |
+
"learning_rate": 0.0001,
|
| 710 |
+
"loss": 2.2436,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.5,
|
| 715 |
+
"learning_rate": 0.0001,
|
| 716 |
+
"loss": 2.2396,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.51,
|
| 721 |
+
"learning_rate": 0.0001,
|
| 722 |
+
"loss": 2.2725,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.51,
|
| 727 |
+
"learning_rate": 0.0001,
|
| 728 |
+
"loss": 2.2974,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.52,
|
| 733 |
+
"learning_rate": 0.0001,
|
| 734 |
+
"loss": 2.266,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.52,
|
| 739 |
+
"learning_rate": 0.0001,
|
| 740 |
+
"loss": 2.258,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.53,
|
| 745 |
+
"learning_rate": 0.0001,
|
| 746 |
+
"loss": 2.2597,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.53,
|
| 751 |
+
"learning_rate": 0.0001,
|
| 752 |
+
"loss": 2.234,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.53,
|
| 757 |
+
"learning_rate": 0.0001,
|
| 758 |
+
"loss": 2.2263,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.54,
|
| 763 |
+
"learning_rate": 0.0001,
|
| 764 |
+
"loss": 2.2325,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.54,
|
| 769 |
+
"learning_rate": 0.0001,
|
| 770 |
+
"loss": 2.2024,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.55,
|
| 775 |
+
"learning_rate": 0.0001,
|
| 776 |
+
"loss": 2.2732,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.55,
|
| 781 |
+
"learning_rate": 0.0001,
|
| 782 |
+
"loss": 2.2422,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.56,
|
| 787 |
+
"learning_rate": 0.0001,
|
| 788 |
+
"loss": 2.2325,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.56,
|
| 793 |
+
"learning_rate": 0.0001,
|
| 794 |
+
"loss": 2.2492,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.56,
|
| 799 |
+
"learning_rate": 0.0001,
|
| 800 |
+
"loss": 2.2055,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.57,
|
| 805 |
+
"learning_rate": 0.0001,
|
| 806 |
+
"loss": 2.2735,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.57,
|
| 811 |
+
"learning_rate": 0.0001,
|
| 812 |
+
"loss": 2.202,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.58,
|
| 817 |
+
"learning_rate": 0.0001,
|
| 818 |
+
"loss": 2.195,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.58,
|
| 823 |
+
"learning_rate": 0.0001,
|
| 824 |
+
"loss": 2.1999,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.59,
|
| 829 |
+
"learning_rate": 0.0001,
|
| 830 |
+
"loss": 2.2033,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.59,
|
| 835 |
+
"learning_rate": 0.0001,
|
| 836 |
+
"loss": 2.1748,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.59,
|
| 841 |
+
"learning_rate": 0.0001,
|
| 842 |
+
"loss": 2.2025,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.6,
|
| 847 |
+
"learning_rate": 0.0001,
|
| 848 |
+
"loss": 2.1967,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6,
|
| 853 |
+
"learning_rate": 0.0001,
|
| 854 |
+
"loss": 2.1796,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.61,
|
| 859 |
+
"learning_rate": 0.0001,
|
| 860 |
+
"loss": 2.1929,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.61,
|
| 865 |
+
"learning_rate": 0.0001,
|
| 866 |
+
"loss": 2.2138,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.62,
|
| 871 |
+
"learning_rate": 0.0001,
|
| 872 |
+
"loss": 2.2058,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.62,
|
| 877 |
+
"learning_rate": 0.0001,
|
| 878 |
+
"loss": 2.2046,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.62,
|
| 883 |
+
"learning_rate": 0.0001,
|
| 884 |
+
"loss": 2.2204,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.63,
|
| 889 |
+
"learning_rate": 0.0001,
|
| 890 |
+
"loss": 2.2028,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.63,
|
| 895 |
+
"learning_rate": 0.0001,
|
| 896 |
+
"loss": 2.2634,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.64,
|
| 901 |
+
"learning_rate": 0.0001,
|
| 902 |
+
"loss": 2.2382,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.64,
|
| 907 |
+
"learning_rate": 0.0001,
|
| 908 |
+
"loss": 2.1955,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.65,
|
| 913 |
+
"learning_rate": 0.0001,
|
| 914 |
+
"loss": 2.1918,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.65,
|
| 919 |
+
"learning_rate": 0.0001,
|
| 920 |
+
"loss": 2.2177,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.65,
|
| 925 |
+
"learning_rate": 0.0001,
|
| 926 |
+
"loss": 2.189,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.66,
|
| 931 |
+
"learning_rate": 0.0001,
|
| 932 |
+
"loss": 2.1829,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.66,
|
| 937 |
+
"learning_rate": 0.0001,
|
| 938 |
+
"loss": 2.2272,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.67,
|
| 943 |
+
"learning_rate": 0.0001,
|
| 944 |
+
"loss": 2.1924,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.67,
|
| 949 |
+
"learning_rate": 0.0001,
|
| 950 |
+
"loss": 2.1877,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.67,
|
| 955 |
+
"learning_rate": 0.0001,
|
| 956 |
+
"loss": 2.1772,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.68,
|
| 961 |
+
"learning_rate": 0.0001,
|
| 962 |
+
"loss": 2.1338,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.68,
|
| 967 |
+
"learning_rate": 0.0001,
|
| 968 |
+
"loss": 2.1817,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.69,
|
| 973 |
+
"learning_rate": 0.0001,
|
| 974 |
+
"loss": 2.211,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.69,
|
| 979 |
+
"learning_rate": 0.0001,
|
| 980 |
+
"loss": 2.1922,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.7,
|
| 985 |
+
"learning_rate": 0.0001,
|
| 986 |
+
"loss": 2.162,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.7,
|
| 991 |
+
"learning_rate": 0.0001,
|
| 992 |
+
"loss": 2.1906,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.7,
|
| 997 |
+
"learning_rate": 0.0001,
|
| 998 |
+
"loss": 2.1931,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.71,
|
| 1003 |
+
"learning_rate": 0.0001,
|
| 1004 |
+
"loss": 2.1611,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.71,
|
| 1009 |
+
"learning_rate": 0.0001,
|
| 1010 |
+
"loss": 2.1913,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.72,
|
| 1015 |
+
"learning_rate": 0.0001,
|
| 1016 |
+
"loss": 2.2342,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.72,
|
| 1021 |
+
"learning_rate": 0.0001,
|
| 1022 |
+
"loss": 2.1753,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.73,
|
| 1027 |
+
"learning_rate": 0.0001,
|
| 1028 |
+
"loss": 2.1634,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.73,
|
| 1033 |
+
"learning_rate": 0.0001,
|
| 1034 |
+
"loss": 2.1628,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.73,
|
| 1039 |
+
"learning_rate": 0.0001,
|
| 1040 |
+
"loss": 2.1871,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.74,
|
| 1045 |
+
"learning_rate": 0.0001,
|
| 1046 |
+
"loss": 2.1995,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.74,
|
| 1051 |
+
"learning_rate": 0.0001,
|
| 1052 |
+
"loss": 2.1537,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.75,
|
| 1057 |
+
"learning_rate": 0.0001,
|
| 1058 |
+
"loss": 2.2105,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.75,
|
| 1063 |
+
"learning_rate": 0.0001,
|
| 1064 |
+
"loss": 2.1633,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.76,
|
| 1069 |
+
"learning_rate": 0.0001,
|
| 1070 |
+
"loss": 2.1315,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.76,
|
| 1075 |
+
"learning_rate": 0.0001,
|
| 1076 |
+
"loss": 2.1628,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.76,
|
| 1081 |
+
"learning_rate": 0.0001,
|
| 1082 |
+
"loss": 2.1704,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.77,
|
| 1087 |
+
"learning_rate": 0.0001,
|
| 1088 |
+
"loss": 2.1696,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.77,
|
| 1093 |
+
"learning_rate": 0.0001,
|
| 1094 |
+
"loss": 2.1839,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.78,
|
| 1099 |
+
"learning_rate": 0.0001,
|
| 1100 |
+
"loss": 2.2022,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.78,
|
| 1105 |
+
"learning_rate": 0.0001,
|
| 1106 |
+
"loss": 2.1568,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.79,
|
| 1111 |
+
"learning_rate": 0.0001,
|
| 1112 |
+
"loss": 2.1448,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.79,
|
| 1117 |
+
"learning_rate": 0.0001,
|
| 1118 |
+
"loss": 2.1464,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.79,
|
| 1123 |
+
"learning_rate": 0.0001,
|
| 1124 |
+
"loss": 2.159,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.8,
|
| 1129 |
+
"learning_rate": 0.0001,
|
| 1130 |
+
"loss": 2.138,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.8,
|
| 1135 |
+
"learning_rate": 0.0001,
|
| 1136 |
+
"loss": 2.1726,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.81,
|
| 1141 |
+
"learning_rate": 0.0001,
|
| 1142 |
+
"loss": 2.107,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.81,
|
| 1147 |
+
"learning_rate": 0.0001,
|
| 1148 |
+
"loss": 2.1899,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.82,
|
| 1153 |
+
"learning_rate": 0.0001,
|
| 1154 |
+
"loss": 2.1993,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.82,
|
| 1159 |
+
"learning_rate": 0.0001,
|
| 1160 |
+
"loss": 2.1387,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.82,
|
| 1165 |
+
"learning_rate": 0.0001,
|
| 1166 |
+
"loss": 2.1257,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.83,
|
| 1171 |
+
"learning_rate": 0.0001,
|
| 1172 |
+
"loss": 2.1729,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.83,
|
| 1177 |
+
"learning_rate": 0.0001,
|
| 1178 |
+
"loss": 2.129,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.84,
|
| 1183 |
+
"learning_rate": 0.0001,
|
| 1184 |
+
"loss": 2.1368,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.84,
|
| 1189 |
+
"learning_rate": 0.0001,
|
| 1190 |
+
"loss": 2.1185,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.85,
|
| 1195 |
+
"learning_rate": 0.0001,
|
| 1196 |
+
"loss": 2.1327,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.85,
|
| 1201 |
+
"learning_rate": 0.0001,
|
| 1202 |
+
"loss": 2.1498,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.85,
|
| 1207 |
+
"learning_rate": 0.0001,
|
| 1208 |
+
"loss": 2.1094,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
}
|
| 1211 |
+
],
|
| 1212 |
+
"logging_steps": 1.0,
|
| 1213 |
+
"max_steps": 234,
|
| 1214 |
+
"num_train_epochs": 1,
|
| 1215 |
+
"save_steps": 100,
|
| 1216 |
+
"total_flos": 2.2811108179968e+17,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb60254b1b35ccab57085d05705a4dc75746db1021c7da7d08c0d6f25e6f291c
|
| 3 |
+
size 4027
|
eval_results.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 2.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 1591,
|
| 7 |
-
"eval_samples_per_second": 15.
|
| 8 |
-
"eval_steps_per_second": 1.
|
| 9 |
-
"perplexity":
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.6222736408782921,
|
| 4 |
+
"eval_loss": 2.1664786338806152,
|
| 5 |
+
"eval_runtime": 100.1618,
|
| 6 |
"eval_samples": 1591,
|
| 7 |
+
"eval_samples_per_second": 15.884,
|
| 8 |
+
"eval_steps_per_second": 1.987,
|
| 9 |
+
"perplexity": 8.727497153819245
|
| 10 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1843519974
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cb64b6970ac8fe9f6249d9c721f3d9e41da6af88744695a99eff517a87a3a47
|
| 3 |
size 1843519974
|
runs/Oct02_19-02-38_d91dc97482a8/events.out.tfevents.1696273371.d91dc97482a8.73567.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eba12c827c36216aaa7d0491992e9a2755a5c1ae7152c29d26c3058d5ce6d2fe
|
| 3 |
+
size 4242
|
runs/Oct02_19-03-48_d91dc97482a8/events.out.tfevents.1696273441.d91dc97482a8.73963.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec95237183cce048857c7f0aa7b616a855bffcfcf3d96ba734bdf65e44432761
|
| 3 |
+
size 40799
|
runs/Oct02_19-03-48_d91dc97482a8/events.out.tfevents.1696276866.d91dc97482a8.73963.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f8e1d9e6ee326e36802897beebef53add2b63f5a461d298ed304ab5b5c03bd6
|
| 3 |
+
size 411
|
runs/Oct02_20-01-14_d91dc97482a8/events.out.tfevents.1696276886.d91dc97482a8.88774.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4577776f31b56647be04238f7c988d8de37187e2c46aff4ecb6b0ffee985a3
|
| 3 |
+
size 5782
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 29961,
|
| 6 |
-
"train_samples_per_second": 9.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.312185388344985,
|
| 4 |
+
"train_runtime": 3320.7115,
|
| 5 |
"train_samples": 29961,
|
| 6 |
+
"train_samples_per_second": 9.022,
|
| 7 |
+
"train_steps_per_second": 0.07
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -11,1421 +11,1421 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
"learning_rate": 0.0001,
|
| 14 |
-
"loss":
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.01,
|
| 19 |
"learning_rate": 0.0001,
|
| 20 |
-
"loss":
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.01,
|
| 25 |
"learning_rate": 0.0001,
|
| 26 |
-
"loss":
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.02,
|
| 31 |
"learning_rate": 0.0001,
|
| 32 |
-
"loss":
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.02,
|
| 37 |
"learning_rate": 0.0001,
|
| 38 |
-
"loss":
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.03,
|
| 43 |
"learning_rate": 0.0001,
|
| 44 |
-
"loss":
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.03,
|
| 49 |
"learning_rate": 0.0001,
|
| 50 |
-
"loss":
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.03,
|
| 55 |
"learning_rate": 0.0001,
|
| 56 |
-
"loss":
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.04,
|
| 61 |
"learning_rate": 0.0001,
|
| 62 |
-
"loss":
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.04,
|
| 67 |
"learning_rate": 0.0001,
|
| 68 |
-
"loss":
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.05,
|
| 73 |
"learning_rate": 0.0001,
|
| 74 |
-
"loss":
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.05,
|
| 79 |
"learning_rate": 0.0001,
|
| 80 |
-
"loss":
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.06,
|
| 85 |
"learning_rate": 0.0001,
|
| 86 |
-
"loss":
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.06,
|
| 91 |
"learning_rate": 0.0001,
|
| 92 |
-
"loss":
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.06,
|
| 97 |
"learning_rate": 0.0001,
|
| 98 |
-
"loss":
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.07,
|
| 103 |
"learning_rate": 0.0001,
|
| 104 |
-
"loss":
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.07,
|
| 109 |
"learning_rate": 0.0001,
|
| 110 |
-
"loss":
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.08,
|
| 115 |
"learning_rate": 0.0001,
|
| 116 |
-
"loss":
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.08,
|
| 121 |
"learning_rate": 0.0001,
|
| 122 |
-
"loss":
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.09,
|
| 127 |
"learning_rate": 0.0001,
|
| 128 |
-
"loss":
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.09,
|
| 133 |
"learning_rate": 0.0001,
|
| 134 |
-
"loss":
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.09,
|
| 139 |
"learning_rate": 0.0001,
|
| 140 |
-
"loss":
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.1,
|
| 145 |
"learning_rate": 0.0001,
|
| 146 |
-
"loss":
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.1,
|
| 151 |
"learning_rate": 0.0001,
|
| 152 |
-
"loss":
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.11,
|
| 157 |
"learning_rate": 0.0001,
|
| 158 |
-
"loss":
|
| 159 |
"step": 25
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.11,
|
| 163 |
"learning_rate": 0.0001,
|
| 164 |
-
"loss":
|
| 165 |
"step": 26
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.12,
|
| 169 |
"learning_rate": 0.0001,
|
| 170 |
-
"loss":
|
| 171 |
"step": 27
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.12,
|
| 175 |
"learning_rate": 0.0001,
|
| 176 |
-
"loss":
|
| 177 |
"step": 28
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.12,
|
| 181 |
"learning_rate": 0.0001,
|
| 182 |
-
"loss":
|
| 183 |
"step": 29
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.13,
|
| 187 |
"learning_rate": 0.0001,
|
| 188 |
-
"loss":
|
| 189 |
"step": 30
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.13,
|
| 193 |
"learning_rate": 0.0001,
|
| 194 |
-
"loss":
|
| 195 |
"step": 31
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.14,
|
| 199 |
"learning_rate": 0.0001,
|
| 200 |
-
"loss":
|
| 201 |
"step": 32
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.14,
|
| 205 |
"learning_rate": 0.0001,
|
| 206 |
-
"loss":
|
| 207 |
"step": 33
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.15,
|
| 211 |
"learning_rate": 0.0001,
|
| 212 |
-
"loss":
|
| 213 |
"step": 34
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.15,
|
| 217 |
"learning_rate": 0.0001,
|
| 218 |
-
"loss":
|
| 219 |
"step": 35
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.15,
|
| 223 |
"learning_rate": 0.0001,
|
| 224 |
-
"loss":
|
| 225 |
"step": 36
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 0.16,
|
| 229 |
"learning_rate": 0.0001,
|
| 230 |
-
"loss":
|
| 231 |
"step": 37
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.16,
|
| 235 |
"learning_rate": 0.0001,
|
| 236 |
-
"loss":
|
| 237 |
"step": 38
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 0.17,
|
| 241 |
"learning_rate": 0.0001,
|
| 242 |
-
"loss":
|
| 243 |
"step": 39
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.17,
|
| 247 |
"learning_rate": 0.0001,
|
| 248 |
-
"loss":
|
| 249 |
"step": 40
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.18,
|
| 253 |
"learning_rate": 0.0001,
|
| 254 |
-
"loss":
|
| 255 |
"step": 41
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.18,
|
| 259 |
"learning_rate": 0.0001,
|
| 260 |
-
"loss":
|
| 261 |
"step": 42
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.18,
|
| 265 |
"learning_rate": 0.0001,
|
| 266 |
-
"loss":
|
| 267 |
"step": 43
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.19,
|
| 271 |
"learning_rate": 0.0001,
|
| 272 |
-
"loss":
|
| 273 |
"step": 44
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 0.19,
|
| 277 |
"learning_rate": 0.0001,
|
| 278 |
-
"loss":
|
| 279 |
"step": 45
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.2,
|
| 283 |
"learning_rate": 0.0001,
|
| 284 |
-
"loss":
|
| 285 |
"step": 46
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.2,
|
| 289 |
"learning_rate": 0.0001,
|
| 290 |
-
"loss":
|
| 291 |
"step": 47
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.21,
|
| 295 |
"learning_rate": 0.0001,
|
| 296 |
-
"loss":
|
| 297 |
"step": 48
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.21,
|
| 301 |
"learning_rate": 0.0001,
|
| 302 |
-
"loss":
|
| 303 |
"step": 49
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.21,
|
| 307 |
"learning_rate": 0.0001,
|
| 308 |
-
"loss":
|
| 309 |
"step": 50
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.22,
|
| 313 |
"learning_rate": 0.0001,
|
| 314 |
-
"loss":
|
| 315 |
"step": 51
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.22,
|
| 319 |
"learning_rate": 0.0001,
|
| 320 |
-
"loss":
|
| 321 |
"step": 52
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.23,
|
| 325 |
"learning_rate": 0.0001,
|
| 326 |
-
"loss":
|
| 327 |
"step": 53
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 0.23,
|
| 331 |
"learning_rate": 0.0001,
|
| 332 |
-
"loss":
|
| 333 |
"step": 54
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 0.23,
|
| 337 |
"learning_rate": 0.0001,
|
| 338 |
-
"loss":
|
| 339 |
"step": 55
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.24,
|
| 343 |
"learning_rate": 0.0001,
|
| 344 |
-
"loss":
|
| 345 |
"step": 56
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.24,
|
| 349 |
"learning_rate": 0.0001,
|
| 350 |
-
"loss":
|
| 351 |
"step": 57
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.25,
|
| 355 |
"learning_rate": 0.0001,
|
| 356 |
-
"loss":
|
| 357 |
"step": 58
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 0.25,
|
| 361 |
"learning_rate": 0.0001,
|
| 362 |
-
"loss":
|
| 363 |
"step": 59
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.26,
|
| 367 |
"learning_rate": 0.0001,
|
| 368 |
-
"loss":
|
| 369 |
"step": 60
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 0.26,
|
| 373 |
"learning_rate": 0.0001,
|
| 374 |
-
"loss":
|
| 375 |
"step": 61
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 0.26,
|
| 379 |
"learning_rate": 0.0001,
|
| 380 |
-
"loss":
|
| 381 |
"step": 62
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.27,
|
| 385 |
"learning_rate": 0.0001,
|
| 386 |
-
"loss":
|
| 387 |
"step": 63
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.27,
|
| 391 |
"learning_rate": 0.0001,
|
| 392 |
-
"loss":
|
| 393 |
"step": 64
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.28,
|
| 397 |
"learning_rate": 0.0001,
|
| 398 |
-
"loss":
|
| 399 |
"step": 65
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.28,
|
| 403 |
"learning_rate": 0.0001,
|
| 404 |
-
"loss":
|
| 405 |
"step": 66
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 0.29,
|
| 409 |
"learning_rate": 0.0001,
|
| 410 |
-
"loss":
|
| 411 |
"step": 67
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 0.29,
|
| 415 |
"learning_rate": 0.0001,
|
| 416 |
-
"loss":
|
| 417 |
"step": 68
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.29,
|
| 421 |
"learning_rate": 0.0001,
|
| 422 |
-
"loss":
|
| 423 |
"step": 69
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 0.3,
|
| 427 |
"learning_rate": 0.0001,
|
| 428 |
-
"loss":
|
| 429 |
"step": 70
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.3,
|
| 433 |
"learning_rate": 0.0001,
|
| 434 |
-
"loss":
|
| 435 |
"step": 71
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.31,
|
| 439 |
"learning_rate": 0.0001,
|
| 440 |
-
"loss":
|
| 441 |
"step": 72
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.31,
|
| 445 |
"learning_rate": 0.0001,
|
| 446 |
-
"loss":
|
| 447 |
"step": 73
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.32,
|
| 451 |
"learning_rate": 0.0001,
|
| 452 |
-
"loss":
|
| 453 |
"step": 74
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.32,
|
| 457 |
"learning_rate": 0.0001,
|
| 458 |
-
"loss":
|
| 459 |
"step": 75
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.32,
|
| 463 |
"learning_rate": 0.0001,
|
| 464 |
-
"loss":
|
| 465 |
"step": 76
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.33,
|
| 469 |
"learning_rate": 0.0001,
|
| 470 |
-
"loss":
|
| 471 |
"step": 77
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.33,
|
| 475 |
"learning_rate": 0.0001,
|
| 476 |
-
"loss":
|
| 477 |
"step": 78
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.34,
|
| 481 |
"learning_rate": 0.0001,
|
| 482 |
-
"loss":
|
| 483 |
"step": 79
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 0.34,
|
| 487 |
"learning_rate": 0.0001,
|
| 488 |
-
"loss":
|
| 489 |
"step": 80
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.35,
|
| 493 |
"learning_rate": 0.0001,
|
| 494 |
-
"loss":
|
| 495 |
"step": 81
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 0.35,
|
| 499 |
"learning_rate": 0.0001,
|
| 500 |
-
"loss":
|
| 501 |
"step": 82
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 0.35,
|
| 505 |
"learning_rate": 0.0001,
|
| 506 |
-
"loss":
|
| 507 |
"step": 83
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 0.36,
|
| 511 |
"learning_rate": 0.0001,
|
| 512 |
-
"loss":
|
| 513 |
"step": 84
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.36,
|
| 517 |
"learning_rate": 0.0001,
|
| 518 |
-
"loss":
|
| 519 |
"step": 85
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.37,
|
| 523 |
"learning_rate": 0.0001,
|
| 524 |
-
"loss":
|
| 525 |
"step": 86
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.37,
|
| 529 |
"learning_rate": 0.0001,
|
| 530 |
-
"loss":
|
| 531 |
"step": 87
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 0.38,
|
| 535 |
"learning_rate": 0.0001,
|
| 536 |
-
"loss":
|
| 537 |
"step": 88
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 0.38,
|
| 541 |
"learning_rate": 0.0001,
|
| 542 |
-
"loss":
|
| 543 |
"step": 89
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 0.38,
|
| 547 |
"learning_rate": 0.0001,
|
| 548 |
-
"loss":
|
| 549 |
"step": 90
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 0.39,
|
| 553 |
"learning_rate": 0.0001,
|
| 554 |
-
"loss":
|
| 555 |
"step": 91
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.39,
|
| 559 |
"learning_rate": 0.0001,
|
| 560 |
-
"loss":
|
| 561 |
"step": 92
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 0.4,
|
| 565 |
"learning_rate": 0.0001,
|
| 566 |
-
"loss":
|
| 567 |
"step": 93
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 0.4,
|
| 571 |
"learning_rate": 0.0001,
|
| 572 |
-
"loss":
|
| 573 |
"step": 94
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 0.41,
|
| 577 |
"learning_rate": 0.0001,
|
| 578 |
-
"loss":
|
| 579 |
"step": 95
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 0.41,
|
| 583 |
"learning_rate": 0.0001,
|
| 584 |
-
"loss":
|
| 585 |
"step": 96
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 0.41,
|
| 589 |
"learning_rate": 0.0001,
|
| 590 |
-
"loss":
|
| 591 |
"step": 97
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.42,
|
| 595 |
"learning_rate": 0.0001,
|
| 596 |
-
"loss":
|
| 597 |
"step": 98
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.42,
|
| 601 |
"learning_rate": 0.0001,
|
| 602 |
-
"loss":
|
| 603 |
"step": 99
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.43,
|
| 607 |
"learning_rate": 0.0001,
|
| 608 |
-
"loss":
|
| 609 |
"step": 100
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 0.43,
|
| 613 |
"learning_rate": 0.0001,
|
| 614 |
-
"loss": 2.
|
| 615 |
"step": 101
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 0.44,
|
| 619 |
"learning_rate": 0.0001,
|
| 620 |
-
"loss":
|
| 621 |
"step": 102
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.44,
|
| 625 |
"learning_rate": 0.0001,
|
| 626 |
-
"loss":
|
| 627 |
"step": 103
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 0.44,
|
| 631 |
"learning_rate": 0.0001,
|
| 632 |
-
"loss": 2.
|
| 633 |
"step": 104
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.45,
|
| 637 |
"learning_rate": 0.0001,
|
| 638 |
-
"loss":
|
| 639 |
"step": 105
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.45,
|
| 643 |
"learning_rate": 0.0001,
|
| 644 |
-
"loss": 2.
|
| 645 |
"step": 106
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 0.46,
|
| 649 |
"learning_rate": 0.0001,
|
| 650 |
-
"loss":
|
| 651 |
"step": 107
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 0.46,
|
| 655 |
"learning_rate": 0.0001,
|
| 656 |
-
"loss":
|
| 657 |
"step": 108
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 0.47,
|
| 661 |
"learning_rate": 0.0001,
|
| 662 |
-
"loss": 2.
|
| 663 |
"step": 109
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 0.47,
|
| 667 |
"learning_rate": 0.0001,
|
| 668 |
-
"loss": 2.
|
| 669 |
"step": 110
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 0.47,
|
| 673 |
"learning_rate": 0.0001,
|
| 674 |
-
"loss": 2.
|
| 675 |
"step": 111
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.48,
|
| 679 |
"learning_rate": 0.0001,
|
| 680 |
-
"loss": 2.
|
| 681 |
"step": 112
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 0.48,
|
| 685 |
"learning_rate": 0.0001,
|
| 686 |
-
"loss": 2.
|
| 687 |
"step": 113
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 0.49,
|
| 691 |
"learning_rate": 0.0001,
|
| 692 |
-
"loss": 2.
|
| 693 |
"step": 114
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 0.49,
|
| 697 |
"learning_rate": 0.0001,
|
| 698 |
-
"loss": 2.
|
| 699 |
"step": 115
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.5,
|
| 703 |
"learning_rate": 0.0001,
|
| 704 |
-
"loss": 2.
|
| 705 |
"step": 116
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 0.5,
|
| 709 |
"learning_rate": 0.0001,
|
| 710 |
-
"loss": 2.
|
| 711 |
"step": 117
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.5,
|
| 715 |
"learning_rate": 0.0001,
|
| 716 |
-
"loss": 2.
|
| 717 |
"step": 118
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.51,
|
| 721 |
"learning_rate": 0.0001,
|
| 722 |
-
"loss": 2.
|
| 723 |
"step": 119
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.51,
|
| 727 |
"learning_rate": 0.0001,
|
| 728 |
-
"loss": 2.
|
| 729 |
"step": 120
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 0.52,
|
| 733 |
"learning_rate": 0.0001,
|
| 734 |
-
"loss": 2.
|
| 735 |
"step": 121
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 0.52,
|
| 739 |
"learning_rate": 0.0001,
|
| 740 |
-
"loss": 2.
|
| 741 |
"step": 122
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 0.53,
|
| 745 |
"learning_rate": 0.0001,
|
| 746 |
-
"loss": 2.
|
| 747 |
"step": 123
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.53,
|
| 751 |
"learning_rate": 0.0001,
|
| 752 |
-
"loss": 2.
|
| 753 |
"step": 124
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.53,
|
| 757 |
"learning_rate": 0.0001,
|
| 758 |
-
"loss": 2.
|
| 759 |
"step": 125
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 0.54,
|
| 763 |
"learning_rate": 0.0001,
|
| 764 |
-
"loss": 2.
|
| 765 |
"step": 126
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.54,
|
| 769 |
"learning_rate": 0.0001,
|
| 770 |
-
"loss": 2.
|
| 771 |
"step": 127
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 0.55,
|
| 775 |
"learning_rate": 0.0001,
|
| 776 |
-
"loss": 2.
|
| 777 |
"step": 128
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 0.55,
|
| 781 |
"learning_rate": 0.0001,
|
| 782 |
-
"loss": 2.
|
| 783 |
"step": 129
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.56,
|
| 787 |
"learning_rate": 0.0001,
|
| 788 |
-
"loss": 2.
|
| 789 |
"step": 130
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 0.56,
|
| 793 |
"learning_rate": 0.0001,
|
| 794 |
-
"loss": 2.
|
| 795 |
"step": 131
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 0.56,
|
| 799 |
"learning_rate": 0.0001,
|
| 800 |
-
"loss": 2.
|
| 801 |
"step": 132
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 0.57,
|
| 805 |
"learning_rate": 0.0001,
|
| 806 |
-
"loss": 2.
|
| 807 |
"step": 133
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 0.57,
|
| 811 |
"learning_rate": 0.0001,
|
| 812 |
-
"loss": 2.
|
| 813 |
"step": 134
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 0.58,
|
| 817 |
"learning_rate": 0.0001,
|
| 818 |
-
"loss": 2.
|
| 819 |
"step": 135
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 0.58,
|
| 823 |
"learning_rate": 0.0001,
|
| 824 |
-
"loss": 2.
|
| 825 |
"step": 136
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 0.59,
|
| 829 |
"learning_rate": 0.0001,
|
| 830 |
-
"loss": 2.
|
| 831 |
"step": 137
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.59,
|
| 835 |
"learning_rate": 0.0001,
|
| 836 |
-
"loss": 2.
|
| 837 |
"step": 138
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 0.59,
|
| 841 |
"learning_rate": 0.0001,
|
| 842 |
-
"loss": 2.
|
| 843 |
"step": 139
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 0.6,
|
| 847 |
"learning_rate": 0.0001,
|
| 848 |
-
"loss": 2.
|
| 849 |
"step": 140
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.6,
|
| 853 |
"learning_rate": 0.0001,
|
| 854 |
-
"loss": 2.
|
| 855 |
"step": 141
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 0.61,
|
| 859 |
"learning_rate": 0.0001,
|
| 860 |
-
"loss": 2.
|
| 861 |
"step": 142
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 0.61,
|
| 865 |
"learning_rate": 0.0001,
|
| 866 |
-
"loss": 2.
|
| 867 |
"step": 143
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.62,
|
| 871 |
"learning_rate": 0.0001,
|
| 872 |
-
"loss": 2.
|
| 873 |
"step": 144
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.62,
|
| 877 |
"learning_rate": 0.0001,
|
| 878 |
-
"loss": 2.
|
| 879 |
"step": 145
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 0.62,
|
| 883 |
"learning_rate": 0.0001,
|
| 884 |
-
"loss": 2.
|
| 885 |
"step": 146
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 0.63,
|
| 889 |
"learning_rate": 0.0001,
|
| 890 |
-
"loss": 2.
|
| 891 |
"step": 147
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.63,
|
| 895 |
"learning_rate": 0.0001,
|
| 896 |
-
"loss": 2.
|
| 897 |
"step": 148
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.64,
|
| 901 |
"learning_rate": 0.0001,
|
| 902 |
-
"loss": 2.
|
| 903 |
"step": 149
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 0.64,
|
| 907 |
"learning_rate": 0.0001,
|
| 908 |
-
"loss": 2.
|
| 909 |
"step": 150
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.65,
|
| 913 |
"learning_rate": 0.0001,
|
| 914 |
-
"loss": 2.
|
| 915 |
"step": 151
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 0.65,
|
| 919 |
"learning_rate": 0.0001,
|
| 920 |
-
"loss": 2.
|
| 921 |
"step": 152
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 0.65,
|
| 925 |
"learning_rate": 0.0001,
|
| 926 |
-
"loss": 2.
|
| 927 |
"step": 153
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 0.66,
|
| 931 |
"learning_rate": 0.0001,
|
| 932 |
-
"loss": 2.
|
| 933 |
"step": 154
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 0.66,
|
| 937 |
"learning_rate": 0.0001,
|
| 938 |
-
"loss": 2.
|
| 939 |
"step": 155
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 0.67,
|
| 943 |
"learning_rate": 0.0001,
|
| 944 |
-
"loss": 2.
|
| 945 |
"step": 156
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 0.67,
|
| 949 |
"learning_rate": 0.0001,
|
| 950 |
-
"loss": 2.
|
| 951 |
"step": 157
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 0.67,
|
| 955 |
"learning_rate": 0.0001,
|
| 956 |
-
"loss": 2.
|
| 957 |
"step": 158
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 0.68,
|
| 961 |
"learning_rate": 0.0001,
|
| 962 |
-
"loss": 2.
|
| 963 |
"step": 159
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 0.68,
|
| 967 |
"learning_rate": 0.0001,
|
| 968 |
-
"loss": 2.
|
| 969 |
"step": 160
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 0.69,
|
| 973 |
"learning_rate": 0.0001,
|
| 974 |
-
"loss": 2.
|
| 975 |
"step": 161
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 0.69,
|
| 979 |
"learning_rate": 0.0001,
|
| 980 |
-
"loss": 2.
|
| 981 |
"step": 162
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 0.7,
|
| 985 |
"learning_rate": 0.0001,
|
| 986 |
-
"loss": 2.
|
| 987 |
"step": 163
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.7,
|
| 991 |
"learning_rate": 0.0001,
|
| 992 |
-
"loss": 2.
|
| 993 |
"step": 164
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 0.7,
|
| 997 |
"learning_rate": 0.0001,
|
| 998 |
-
"loss": 2.
|
| 999 |
"step": 165
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 0.71,
|
| 1003 |
"learning_rate": 0.0001,
|
| 1004 |
-
"loss": 2.
|
| 1005 |
"step": 166
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.71,
|
| 1009 |
"learning_rate": 0.0001,
|
| 1010 |
-
"loss": 2.
|
| 1011 |
"step": 167
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 0.72,
|
| 1015 |
"learning_rate": 0.0001,
|
| 1016 |
-
"loss": 2.
|
| 1017 |
"step": 168
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.72,
|
| 1021 |
"learning_rate": 0.0001,
|
| 1022 |
-
"loss": 2.
|
| 1023 |
"step": 169
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.73,
|
| 1027 |
"learning_rate": 0.0001,
|
| 1028 |
-
"loss": 2.
|
| 1029 |
"step": 170
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 0.73,
|
| 1033 |
"learning_rate": 0.0001,
|
| 1034 |
-
"loss": 2.
|
| 1035 |
"step": 171
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 0.73,
|
| 1039 |
"learning_rate": 0.0001,
|
| 1040 |
-
"loss": 2.
|
| 1041 |
"step": 172
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 0.74,
|
| 1045 |
"learning_rate": 0.0001,
|
| 1046 |
-
"loss": 2.
|
| 1047 |
"step": 173
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 0.74,
|
| 1051 |
"learning_rate": 0.0001,
|
| 1052 |
-
"loss": 2.
|
| 1053 |
"step": 174
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 0.75,
|
| 1057 |
"learning_rate": 0.0001,
|
| 1058 |
-
"loss": 2.
|
| 1059 |
"step": 175
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 0.75,
|
| 1063 |
"learning_rate": 0.0001,
|
| 1064 |
-
"loss": 2.
|
| 1065 |
"step": 176
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.76,
|
| 1069 |
"learning_rate": 0.0001,
|
| 1070 |
-
"loss": 2.
|
| 1071 |
"step": 177
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 0.76,
|
| 1075 |
"learning_rate": 0.0001,
|
| 1076 |
-
"loss": 2.
|
| 1077 |
"step": 178
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 0.76,
|
| 1081 |
"learning_rate": 0.0001,
|
| 1082 |
-
"loss": 2.
|
| 1083 |
"step": 179
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 0.77,
|
| 1087 |
"learning_rate": 0.0001,
|
| 1088 |
-
"loss": 2.
|
| 1089 |
"step": 180
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 0.77,
|
| 1093 |
"learning_rate": 0.0001,
|
| 1094 |
-
"loss": 2.
|
| 1095 |
"step": 181
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 0.78,
|
| 1099 |
"learning_rate": 0.0001,
|
| 1100 |
-
"loss": 2.
|
| 1101 |
"step": 182
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 0.78,
|
| 1105 |
"learning_rate": 0.0001,
|
| 1106 |
-
"loss": 2.
|
| 1107 |
"step": 183
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 0.79,
|
| 1111 |
"learning_rate": 0.0001,
|
| 1112 |
-
"loss": 2.
|
| 1113 |
"step": 184
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 0.79,
|
| 1117 |
"learning_rate": 0.0001,
|
| 1118 |
-
"loss": 2.
|
| 1119 |
"step": 185
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 0.79,
|
| 1123 |
"learning_rate": 0.0001,
|
| 1124 |
-
"loss": 2.
|
| 1125 |
"step": 186
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 0.8,
|
| 1129 |
"learning_rate": 0.0001,
|
| 1130 |
-
"loss": 2.
|
| 1131 |
"step": 187
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 0.8,
|
| 1135 |
"learning_rate": 0.0001,
|
| 1136 |
-
"loss": 2.
|
| 1137 |
"step": 188
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 0.81,
|
| 1141 |
"learning_rate": 0.0001,
|
| 1142 |
-
"loss": 2.
|
| 1143 |
"step": 189
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.81,
|
| 1147 |
"learning_rate": 0.0001,
|
| 1148 |
-
"loss": 2.
|
| 1149 |
"step": 190
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 0.82,
|
| 1153 |
"learning_rate": 0.0001,
|
| 1154 |
-
"loss": 2.
|
| 1155 |
"step": 191
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 0.82,
|
| 1159 |
"learning_rate": 0.0001,
|
| 1160 |
-
"loss": 2.
|
| 1161 |
"step": 192
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 0.82,
|
| 1165 |
"learning_rate": 0.0001,
|
| 1166 |
-
"loss": 2.
|
| 1167 |
"step": 193
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 0.83,
|
| 1171 |
"learning_rate": 0.0001,
|
| 1172 |
-
"loss": 2.
|
| 1173 |
"step": 194
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 0.83,
|
| 1177 |
"learning_rate": 0.0001,
|
| 1178 |
-
"loss": 2.
|
| 1179 |
"step": 195
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 0.84,
|
| 1183 |
"learning_rate": 0.0001,
|
| 1184 |
-
"loss": 2.
|
| 1185 |
"step": 196
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 0.84,
|
| 1189 |
"learning_rate": 0.0001,
|
| 1190 |
-
"loss": 2.
|
| 1191 |
"step": 197
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 0.85,
|
| 1195 |
"learning_rate": 0.0001,
|
| 1196 |
-
"loss": 2.
|
| 1197 |
"step": 198
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 0.85,
|
| 1201 |
"learning_rate": 0.0001,
|
| 1202 |
-
"loss": 2.
|
| 1203 |
"step": 199
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 0.85,
|
| 1207 |
"learning_rate": 0.0001,
|
| 1208 |
-
"loss": 2.
|
| 1209 |
"step": 200
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 0.86,
|
| 1213 |
"learning_rate": 0.0001,
|
| 1214 |
-
"loss": 2.
|
| 1215 |
"step": 201
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 0.86,
|
| 1219 |
"learning_rate": 0.0001,
|
| 1220 |
-
"loss": 2.
|
| 1221 |
"step": 202
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 0.87,
|
| 1225 |
"learning_rate": 0.0001,
|
| 1226 |
-
"loss": 2.
|
| 1227 |
"step": 203
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 0.87,
|
| 1231 |
"learning_rate": 0.0001,
|
| 1232 |
-
"loss": 2.
|
| 1233 |
"step": 204
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 0.88,
|
| 1237 |
"learning_rate": 0.0001,
|
| 1238 |
-
"loss": 2.
|
| 1239 |
"step": 205
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 0.88,
|
| 1243 |
"learning_rate": 0.0001,
|
| 1244 |
-
"loss": 2.
|
| 1245 |
"step": 206
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 0.88,
|
| 1249 |
"learning_rate": 0.0001,
|
| 1250 |
-
"loss": 2.
|
| 1251 |
"step": 207
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
"epoch": 0.89,
|
| 1255 |
"learning_rate": 0.0001,
|
| 1256 |
-
"loss": 2.
|
| 1257 |
"step": 208
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 0.89,
|
| 1261 |
"learning_rate": 0.0001,
|
| 1262 |
-
"loss": 2.
|
| 1263 |
"step": 209
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 0.9,
|
| 1267 |
"learning_rate": 0.0001,
|
| 1268 |
-
"loss": 2.
|
| 1269 |
"step": 210
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 0.9,
|
| 1273 |
"learning_rate": 0.0001,
|
| 1274 |
-
"loss": 2.
|
| 1275 |
"step": 211
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 0.91,
|
| 1279 |
"learning_rate": 0.0001,
|
| 1280 |
-
"loss": 2.
|
| 1281 |
"step": 212
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 0.91,
|
| 1285 |
"learning_rate": 0.0001,
|
| 1286 |
-
"loss": 2.
|
| 1287 |
"step": 213
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 0.91,
|
| 1291 |
"learning_rate": 0.0001,
|
| 1292 |
-
"loss": 2.
|
| 1293 |
"step": 214
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 0.92,
|
| 1297 |
"learning_rate": 0.0001,
|
| 1298 |
-
"loss": 2.
|
| 1299 |
"step": 215
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.92,
|
| 1303 |
"learning_rate": 0.0001,
|
| 1304 |
-
"loss": 2.
|
| 1305 |
"step": 216
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
"epoch": 0.93,
|
| 1309 |
"learning_rate": 0.0001,
|
| 1310 |
-
"loss": 2.
|
| 1311 |
"step": 217
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 0.93,
|
| 1315 |
"learning_rate": 0.0001,
|
| 1316 |
-
"loss": 2.
|
| 1317 |
"step": 218
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 0.94,
|
| 1321 |
"learning_rate": 0.0001,
|
| 1322 |
-
"loss": 2.
|
| 1323 |
"step": 219
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
"epoch": 0.94,
|
| 1327 |
"learning_rate": 0.0001,
|
| 1328 |
-
"loss": 2.
|
| 1329 |
"step": 220
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 0.94,
|
| 1333 |
"learning_rate": 0.0001,
|
| 1334 |
-
"loss": 2.
|
| 1335 |
"step": 221
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 0.95,
|
| 1339 |
"learning_rate": 0.0001,
|
| 1340 |
-
"loss": 2.
|
| 1341 |
"step": 222
|
| 1342 |
},
|
| 1343 |
{
|
| 1344 |
"epoch": 0.95,
|
| 1345 |
"learning_rate": 0.0001,
|
| 1346 |
-
"loss": 2.
|
| 1347 |
"step": 223
|
| 1348 |
},
|
| 1349 |
{
|
| 1350 |
"epoch": 0.96,
|
| 1351 |
"learning_rate": 0.0001,
|
| 1352 |
-
"loss": 2.
|
| 1353 |
"step": 224
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 0.96,
|
| 1357 |
"learning_rate": 0.0001,
|
| 1358 |
-
"loss": 2.
|
| 1359 |
"step": 225
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 0.97,
|
| 1363 |
"learning_rate": 0.0001,
|
| 1364 |
-
"loss": 2.
|
| 1365 |
"step": 226
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
"epoch": 0.97,
|
| 1369 |
"learning_rate": 0.0001,
|
| 1370 |
-
"loss": 2.
|
| 1371 |
"step": 227
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
"epoch": 0.97,
|
| 1375 |
"learning_rate": 0.0001,
|
| 1376 |
-
"loss": 2.
|
| 1377 |
"step": 228
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 0.98,
|
| 1381 |
"learning_rate": 0.0001,
|
| 1382 |
-
"loss": 2.
|
| 1383 |
"step": 229
|
| 1384 |
},
|
| 1385 |
{
|
| 1386 |
"epoch": 0.98,
|
| 1387 |
"learning_rate": 0.0001,
|
| 1388 |
-
"loss": 2.
|
| 1389 |
"step": 230
|
| 1390 |
},
|
| 1391 |
{
|
| 1392 |
"epoch": 0.99,
|
| 1393 |
"learning_rate": 0.0001,
|
| 1394 |
-
"loss": 2.
|
| 1395 |
"step": 231
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 0.99,
|
| 1399 |
"learning_rate": 0.0001,
|
| 1400 |
-
"loss": 2.
|
| 1401 |
"step": 232
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 1.0,
|
| 1405 |
"learning_rate": 0.0001,
|
| 1406 |
-
"loss": 2.
|
| 1407 |
"step": 233
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
"epoch": 1.0,
|
| 1411 |
"learning_rate": 0.0001,
|
| 1412 |
-
"loss": 2.
|
| 1413 |
"step": 234
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 1.0,
|
| 1417 |
"step": 234,
|
| 1418 |
"total_flos": 2.668899657056256e+17,
|
| 1419 |
-
"train_loss":
|
| 1420 |
-
"train_runtime":
|
| 1421 |
-
"train_samples_per_second": 9.
|
| 1422 |
-
"train_steps_per_second": 0.
|
| 1423 |
}
|
| 1424 |
],
|
| 1425 |
"logging_steps": 1.0,
|
| 1426 |
"max_steps": 234,
|
| 1427 |
"num_train_epochs": 1,
|
| 1428 |
-
"save_steps":
|
| 1429 |
"total_flos": 2.668899657056256e+17,
|
| 1430 |
"trial_name": null,
|
| 1431 |
"trial_params": null
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
"learning_rate": 0.0001,
|
| 14 |
+
"loss": 2.3832,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.01,
|
| 19 |
"learning_rate": 0.0001,
|
| 20 |
+
"loss": 5.648,
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.01,
|
| 25 |
"learning_rate": 0.0001,
|
| 26 |
+
"loss": 4.5146,
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.02,
|
| 31 |
"learning_rate": 0.0001,
|
| 32 |
+
"loss": 3.6589,
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.02,
|
| 37 |
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 3.2564,
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.03,
|
| 43 |
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 3.0312,
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.03,
|
| 49 |
"learning_rate": 0.0001,
|
| 50 |
+
"loss": 2.8748,
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.03,
|
| 55 |
"learning_rate": 0.0001,
|
| 56 |
+
"loss": 2.8477,
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.04,
|
| 61 |
"learning_rate": 0.0001,
|
| 62 |
+
"loss": 2.7413,
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.04,
|
| 67 |
"learning_rate": 0.0001,
|
| 68 |
+
"loss": 2.7057,
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.05,
|
| 73 |
"learning_rate": 0.0001,
|
| 74 |
+
"loss": 2.7216,
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.05,
|
| 79 |
"learning_rate": 0.0001,
|
| 80 |
+
"loss": 2.6576,
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.06,
|
| 85 |
"learning_rate": 0.0001,
|
| 86 |
+
"loss": 2.6287,
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.06,
|
| 91 |
"learning_rate": 0.0001,
|
| 92 |
+
"loss": 2.572,
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.06,
|
| 97 |
"learning_rate": 0.0001,
|
| 98 |
+
"loss": 2.5913,
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.07,
|
| 103 |
"learning_rate": 0.0001,
|
| 104 |
+
"loss": 2.536,
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.07,
|
| 109 |
"learning_rate": 0.0001,
|
| 110 |
+
"loss": 2.5511,
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.08,
|
| 115 |
"learning_rate": 0.0001,
|
| 116 |
+
"loss": 2.4853,
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.08,
|
| 121 |
"learning_rate": 0.0001,
|
| 122 |
+
"loss": 2.5668,
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.09,
|
| 127 |
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 2.535,
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.09,
|
| 133 |
"learning_rate": 0.0001,
|
| 134 |
+
"loss": 2.5287,
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.09,
|
| 139 |
"learning_rate": 0.0001,
|
| 140 |
+
"loss": 2.5263,
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.1,
|
| 145 |
"learning_rate": 0.0001,
|
| 146 |
+
"loss": 2.5046,
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.1,
|
| 151 |
"learning_rate": 0.0001,
|
| 152 |
+
"loss": 2.4366,
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.11,
|
| 157 |
"learning_rate": 0.0001,
|
| 158 |
+
"loss": 2.4488,
|
| 159 |
"step": 25
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.11,
|
| 163 |
"learning_rate": 0.0001,
|
| 164 |
+
"loss": 2.4638,
|
| 165 |
"step": 26
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.12,
|
| 169 |
"learning_rate": 0.0001,
|
| 170 |
+
"loss": 2.4546,
|
| 171 |
"step": 27
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.12,
|
| 175 |
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 2.4169,
|
| 177 |
"step": 28
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.12,
|
| 181 |
"learning_rate": 0.0001,
|
| 182 |
+
"loss": 2.4739,
|
| 183 |
"step": 29
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.13,
|
| 187 |
"learning_rate": 0.0001,
|
| 188 |
+
"loss": 2.4074,
|
| 189 |
"step": 30
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.13,
|
| 193 |
"learning_rate": 0.0001,
|
| 194 |
+
"loss": 2.4314,
|
| 195 |
"step": 31
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.14,
|
| 199 |
"learning_rate": 0.0001,
|
| 200 |
+
"loss": 2.3819,
|
| 201 |
"step": 32
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.14,
|
| 205 |
"learning_rate": 0.0001,
|
| 206 |
+
"loss": 2.3524,
|
| 207 |
"step": 33
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.15,
|
| 211 |
"learning_rate": 0.0001,
|
| 212 |
+
"loss": 2.3943,
|
| 213 |
"step": 34
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.15,
|
| 217 |
"learning_rate": 0.0001,
|
| 218 |
+
"loss": 2.4447,
|
| 219 |
"step": 35
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.15,
|
| 223 |
"learning_rate": 0.0001,
|
| 224 |
+
"loss": 2.4112,
|
| 225 |
"step": 36
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 0.16,
|
| 229 |
"learning_rate": 0.0001,
|
| 230 |
+
"loss": 2.3453,
|
| 231 |
"step": 37
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 0.16,
|
| 235 |
"learning_rate": 0.0001,
|
| 236 |
+
"loss": 2.4186,
|
| 237 |
"step": 38
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 0.17,
|
| 241 |
"learning_rate": 0.0001,
|
| 242 |
+
"loss": 2.3761,
|
| 243 |
"step": 39
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 0.17,
|
| 247 |
"learning_rate": 0.0001,
|
| 248 |
+
"loss": 2.3486,
|
| 249 |
"step": 40
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.18,
|
| 253 |
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 2.4314,
|
| 255 |
"step": 41
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.18,
|
| 259 |
"learning_rate": 0.0001,
|
| 260 |
+
"loss": 2.4059,
|
| 261 |
"step": 42
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.18,
|
| 265 |
"learning_rate": 0.0001,
|
| 266 |
+
"loss": 2.3649,
|
| 267 |
"step": 43
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 0.19,
|
| 271 |
"learning_rate": 0.0001,
|
| 272 |
+
"loss": 2.3544,
|
| 273 |
"step": 44
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 0.19,
|
| 277 |
"learning_rate": 0.0001,
|
| 278 |
+
"loss": 2.3959,
|
| 279 |
"step": 45
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 0.2,
|
| 283 |
"learning_rate": 0.0001,
|
| 284 |
+
"loss": 2.3734,
|
| 285 |
"step": 46
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.2,
|
| 289 |
"learning_rate": 0.0001,
|
| 290 |
+
"loss": 2.374,
|
| 291 |
"step": 47
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.21,
|
| 295 |
"learning_rate": 0.0001,
|
| 296 |
+
"loss": 2.3748,
|
| 297 |
"step": 48
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.21,
|
| 301 |
"learning_rate": 0.0001,
|
| 302 |
+
"loss": 2.4016,
|
| 303 |
"step": 49
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.21,
|
| 307 |
"learning_rate": 0.0001,
|
| 308 |
+
"loss": 2.3388,
|
| 309 |
"step": 50
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 0.22,
|
| 313 |
"learning_rate": 0.0001,
|
| 314 |
+
"loss": 2.3851,
|
| 315 |
"step": 51
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 0.22,
|
| 319 |
"learning_rate": 0.0001,
|
| 320 |
+
"loss": 2.4123,
|
| 321 |
"step": 52
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 0.23,
|
| 325 |
"learning_rate": 0.0001,
|
| 326 |
+
"loss": 2.3594,
|
| 327 |
"step": 53
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 0.23,
|
| 331 |
"learning_rate": 0.0001,
|
| 332 |
+
"loss": 2.3476,
|
| 333 |
"step": 54
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 0.23,
|
| 337 |
"learning_rate": 0.0001,
|
| 338 |
+
"loss": 2.3593,
|
| 339 |
"step": 55
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.24,
|
| 343 |
"learning_rate": 0.0001,
|
| 344 |
+
"loss": 2.3253,
|
| 345 |
"step": 56
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.24,
|
| 349 |
"learning_rate": 0.0001,
|
| 350 |
+
"loss": 2.3574,
|
| 351 |
"step": 57
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.25,
|
| 355 |
"learning_rate": 0.0001,
|
| 356 |
+
"loss": 2.3721,
|
| 357 |
"step": 58
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"epoch": 0.25,
|
| 361 |
"learning_rate": 0.0001,
|
| 362 |
+
"loss": 2.3438,
|
| 363 |
"step": 59
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.26,
|
| 367 |
"learning_rate": 0.0001,
|
| 368 |
+
"loss": 2.3575,
|
| 369 |
"step": 60
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 0.26,
|
| 373 |
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 2.2803,
|
| 375 |
"step": 61
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 0.26,
|
| 379 |
"learning_rate": 0.0001,
|
| 380 |
+
"loss": 2.3088,
|
| 381 |
"step": 62
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.27,
|
| 385 |
"learning_rate": 0.0001,
|
| 386 |
+
"loss": 2.3436,
|
| 387 |
"step": 63
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.27,
|
| 391 |
"learning_rate": 0.0001,
|
| 392 |
+
"loss": 2.3629,
|
| 393 |
"step": 64
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.28,
|
| 397 |
"learning_rate": 0.0001,
|
| 398 |
+
"loss": 2.3294,
|
| 399 |
"step": 65
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 0.28,
|
| 403 |
"learning_rate": 0.0001,
|
| 404 |
+
"loss": 2.3402,
|
| 405 |
"step": 66
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 0.29,
|
| 409 |
"learning_rate": 0.0001,
|
| 410 |
+
"loss": 2.3273,
|
| 411 |
"step": 67
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 0.29,
|
| 415 |
"learning_rate": 0.0001,
|
| 416 |
+
"loss": 2.3335,
|
| 417 |
"step": 68
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.29,
|
| 421 |
"learning_rate": 0.0001,
|
| 422 |
+
"loss": 2.3013,
|
| 423 |
"step": 69
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 0.3,
|
| 427 |
"learning_rate": 0.0001,
|
| 428 |
+
"loss": 2.3396,
|
| 429 |
"step": 70
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.3,
|
| 433 |
"learning_rate": 0.0001,
|
| 434 |
+
"loss": 2.327,
|
| 435 |
"step": 71
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 0.31,
|
| 439 |
"learning_rate": 0.0001,
|
| 440 |
+
"loss": 2.3231,
|
| 441 |
"step": 72
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 0.31,
|
| 445 |
"learning_rate": 0.0001,
|
| 446 |
+
"loss": 2.3247,
|
| 447 |
"step": 73
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.32,
|
| 451 |
"learning_rate": 0.0001,
|
| 452 |
+
"loss": 2.3163,
|
| 453 |
"step": 74
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 0.32,
|
| 457 |
"learning_rate": 0.0001,
|
| 458 |
+
"loss": 2.3301,
|
| 459 |
"step": 75
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.32,
|
| 463 |
"learning_rate": 0.0001,
|
| 464 |
+
"loss": 2.3598,
|
| 465 |
"step": 76
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 0.33,
|
| 469 |
"learning_rate": 0.0001,
|
| 470 |
+
"loss": 2.3115,
|
| 471 |
"step": 77
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 0.33,
|
| 475 |
"learning_rate": 0.0001,
|
| 476 |
+
"loss": 2.3015,
|
| 477 |
"step": 78
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 0.34,
|
| 481 |
"learning_rate": 0.0001,
|
| 482 |
+
"loss": 2.294,
|
| 483 |
"step": 79
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 0.34,
|
| 487 |
"learning_rate": 0.0001,
|
| 488 |
+
"loss": 2.2731,
|
| 489 |
"step": 80
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 0.35,
|
| 493 |
"learning_rate": 0.0001,
|
| 494 |
+
"loss": 2.3138,
|
| 495 |
"step": 81
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 0.35,
|
| 499 |
"learning_rate": 0.0001,
|
| 500 |
+
"loss": 2.3096,
|
| 501 |
"step": 82
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 0.35,
|
| 505 |
"learning_rate": 0.0001,
|
| 506 |
+
"loss": 2.3133,
|
| 507 |
"step": 83
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 0.36,
|
| 511 |
"learning_rate": 0.0001,
|
| 512 |
+
"loss": 2.2679,
|
| 513 |
"step": 84
|
| 514 |
},
|
| 515 |
{
|
| 516 |
"epoch": 0.36,
|
| 517 |
"learning_rate": 0.0001,
|
| 518 |
+
"loss": 2.2657,
|
| 519 |
"step": 85
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.37,
|
| 523 |
"learning_rate": 0.0001,
|
| 524 |
+
"loss": 2.2958,
|
| 525 |
"step": 86
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.37,
|
| 529 |
"learning_rate": 0.0001,
|
| 530 |
+
"loss": 2.297,
|
| 531 |
"step": 87
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 0.38,
|
| 535 |
"learning_rate": 0.0001,
|
| 536 |
+
"loss": 2.2701,
|
| 537 |
"step": 88
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 0.38,
|
| 541 |
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 2.2889,
|
| 543 |
"step": 89
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 0.38,
|
| 547 |
"learning_rate": 0.0001,
|
| 548 |
+
"loss": 2.2585,
|
| 549 |
"step": 90
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 0.39,
|
| 553 |
"learning_rate": 0.0001,
|
| 554 |
+
"loss": 2.2611,
|
| 555 |
"step": 91
|
| 556 |
},
|
| 557 |
{
|
| 558 |
"epoch": 0.39,
|
| 559 |
"learning_rate": 0.0001,
|
| 560 |
+
"loss": 2.2815,
|
| 561 |
"step": 92
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 0.4,
|
| 565 |
"learning_rate": 0.0001,
|
| 566 |
+
"loss": 2.2778,
|
| 567 |
"step": 93
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 0.4,
|
| 571 |
"learning_rate": 0.0001,
|
| 572 |
+
"loss": 2.2803,
|
| 573 |
"step": 94
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 0.41,
|
| 577 |
"learning_rate": 0.0001,
|
| 578 |
+
"loss": 2.3007,
|
| 579 |
"step": 95
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 0.41,
|
| 583 |
"learning_rate": 0.0001,
|
| 584 |
+
"loss": 2.3045,
|
| 585 |
"step": 96
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 0.41,
|
| 589 |
"learning_rate": 0.0001,
|
| 590 |
+
"loss": 2.2858,
|
| 591 |
"step": 97
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.42,
|
| 595 |
"learning_rate": 0.0001,
|
| 596 |
+
"loss": 2.2669,
|
| 597 |
"step": 98
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 0.42,
|
| 601 |
"learning_rate": 0.0001,
|
| 602 |
+
"loss": 2.2731,
|
| 603 |
"step": 99
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.43,
|
| 607 |
"learning_rate": 0.0001,
|
| 608 |
+
"loss": 2.2707,
|
| 609 |
"step": 100
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 0.43,
|
| 613 |
"learning_rate": 0.0001,
|
| 614 |
+
"loss": 2.2189,
|
| 615 |
"step": 101
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 0.44,
|
| 619 |
"learning_rate": 0.0001,
|
| 620 |
+
"loss": 2.2506,
|
| 621 |
"step": 102
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 0.44,
|
| 625 |
"learning_rate": 0.0001,
|
| 626 |
+
"loss": 2.3119,
|
| 627 |
"step": 103
|
| 628 |
},
|
| 629 |
{
|
| 630 |
"epoch": 0.44,
|
| 631 |
"learning_rate": 0.0001,
|
| 632 |
+
"loss": 2.2332,
|
| 633 |
"step": 104
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.45,
|
| 637 |
"learning_rate": 0.0001,
|
| 638 |
+
"loss": 2.2583,
|
| 639 |
"step": 105
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 0.45,
|
| 643 |
"learning_rate": 0.0001,
|
| 644 |
+
"loss": 2.2416,
|
| 645 |
"step": 106
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 0.46,
|
| 649 |
"learning_rate": 0.0001,
|
| 650 |
+
"loss": 2.3025,
|
| 651 |
"step": 107
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 0.46,
|
| 655 |
"learning_rate": 0.0001,
|
| 656 |
+
"loss": 2.2889,
|
| 657 |
"step": 108
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 0.47,
|
| 661 |
"learning_rate": 0.0001,
|
| 662 |
+
"loss": 2.2486,
|
| 663 |
"step": 109
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 0.47,
|
| 667 |
"learning_rate": 0.0001,
|
| 668 |
+
"loss": 2.2369,
|
| 669 |
"step": 110
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 0.47,
|
| 673 |
"learning_rate": 0.0001,
|
| 674 |
+
"loss": 2.2634,
|
| 675 |
"step": 111
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.48,
|
| 679 |
"learning_rate": 0.0001,
|
| 680 |
+
"loss": 2.2911,
|
| 681 |
"step": 112
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 0.48,
|
| 685 |
"learning_rate": 0.0001,
|
| 686 |
+
"loss": 2.3223,
|
| 687 |
"step": 113
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 0.49,
|
| 691 |
"learning_rate": 0.0001,
|
| 692 |
+
"loss": 2.2623,
|
| 693 |
"step": 114
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 0.49,
|
| 697 |
"learning_rate": 0.0001,
|
| 698 |
+
"loss": 2.2075,
|
| 699 |
"step": 115
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.5,
|
| 703 |
"learning_rate": 0.0001,
|
| 704 |
+
"loss": 2.2681,
|
| 705 |
"step": 116
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 0.5,
|
| 709 |
"learning_rate": 0.0001,
|
| 710 |
+
"loss": 2.2436,
|
| 711 |
"step": 117
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 0.5,
|
| 715 |
"learning_rate": 0.0001,
|
| 716 |
+
"loss": 2.2396,
|
| 717 |
"step": 118
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.51,
|
| 721 |
"learning_rate": 0.0001,
|
| 722 |
+
"loss": 2.2725,
|
| 723 |
"step": 119
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 0.51,
|
| 727 |
"learning_rate": 0.0001,
|
| 728 |
+
"loss": 2.2974,
|
| 729 |
"step": 120
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 0.52,
|
| 733 |
"learning_rate": 0.0001,
|
| 734 |
+
"loss": 2.266,
|
| 735 |
"step": 121
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 0.52,
|
| 739 |
"learning_rate": 0.0001,
|
| 740 |
+
"loss": 2.258,
|
| 741 |
"step": 122
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 0.53,
|
| 745 |
"learning_rate": 0.0001,
|
| 746 |
+
"loss": 2.2597,
|
| 747 |
"step": 123
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 0.53,
|
| 751 |
"learning_rate": 0.0001,
|
| 752 |
+
"loss": 2.234,
|
| 753 |
"step": 124
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 0.53,
|
| 757 |
"learning_rate": 0.0001,
|
| 758 |
+
"loss": 2.2263,
|
| 759 |
"step": 125
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 0.54,
|
| 763 |
"learning_rate": 0.0001,
|
| 764 |
+
"loss": 2.2325,
|
| 765 |
"step": 126
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.54,
|
| 769 |
"learning_rate": 0.0001,
|
| 770 |
+
"loss": 2.2024,
|
| 771 |
"step": 127
|
| 772 |
},
|
| 773 |
{
|
| 774 |
"epoch": 0.55,
|
| 775 |
"learning_rate": 0.0001,
|
| 776 |
+
"loss": 2.2732,
|
| 777 |
"step": 128
|
| 778 |
},
|
| 779 |
{
|
| 780 |
"epoch": 0.55,
|
| 781 |
"learning_rate": 0.0001,
|
| 782 |
+
"loss": 2.2422,
|
| 783 |
"step": 129
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 0.56,
|
| 787 |
"learning_rate": 0.0001,
|
| 788 |
+
"loss": 2.2325,
|
| 789 |
"step": 130
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 0.56,
|
| 793 |
"learning_rate": 0.0001,
|
| 794 |
+
"loss": 2.2492,
|
| 795 |
"step": 131
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 0.56,
|
| 799 |
"learning_rate": 0.0001,
|
| 800 |
+
"loss": 2.2055,
|
| 801 |
"step": 132
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 0.57,
|
| 805 |
"learning_rate": 0.0001,
|
| 806 |
+
"loss": 2.2735,
|
| 807 |
"step": 133
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 0.57,
|
| 811 |
"learning_rate": 0.0001,
|
| 812 |
+
"loss": 2.202,
|
| 813 |
"step": 134
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 0.58,
|
| 817 |
"learning_rate": 0.0001,
|
| 818 |
+
"loss": 2.195,
|
| 819 |
"step": 135
|
| 820 |
},
|
| 821 |
{
|
| 822 |
"epoch": 0.58,
|
| 823 |
"learning_rate": 0.0001,
|
| 824 |
+
"loss": 2.1999,
|
| 825 |
"step": 136
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"epoch": 0.59,
|
| 829 |
"learning_rate": 0.0001,
|
| 830 |
+
"loss": 2.2033,
|
| 831 |
"step": 137
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.59,
|
| 835 |
"learning_rate": 0.0001,
|
| 836 |
+
"loss": 2.1748,
|
| 837 |
"step": 138
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 0.59,
|
| 841 |
"learning_rate": 0.0001,
|
| 842 |
+
"loss": 2.2025,
|
| 843 |
"step": 139
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 0.6,
|
| 847 |
"learning_rate": 0.0001,
|
| 848 |
+
"loss": 2.1967,
|
| 849 |
"step": 140
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 0.6,
|
| 853 |
"learning_rate": 0.0001,
|
| 854 |
+
"loss": 2.1796,
|
| 855 |
"step": 141
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 0.61,
|
| 859 |
"learning_rate": 0.0001,
|
| 860 |
+
"loss": 2.1929,
|
| 861 |
"step": 142
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 0.61,
|
| 865 |
"learning_rate": 0.0001,
|
| 866 |
+
"loss": 2.2138,
|
| 867 |
"step": 143
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 0.62,
|
| 871 |
"learning_rate": 0.0001,
|
| 872 |
+
"loss": 2.2058,
|
| 873 |
"step": 144
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.62,
|
| 877 |
"learning_rate": 0.0001,
|
| 878 |
+
"loss": 2.2046,
|
| 879 |
"step": 145
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 0.62,
|
| 883 |
"learning_rate": 0.0001,
|
| 884 |
+
"loss": 2.2204,
|
| 885 |
"step": 146
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 0.63,
|
| 889 |
"learning_rate": 0.0001,
|
| 890 |
+
"loss": 2.2028,
|
| 891 |
"step": 147
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 0.63,
|
| 895 |
"learning_rate": 0.0001,
|
| 896 |
+
"loss": 2.2634,
|
| 897 |
"step": 148
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.64,
|
| 901 |
"learning_rate": 0.0001,
|
| 902 |
+
"loss": 2.2382,
|
| 903 |
"step": 149
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 0.64,
|
| 907 |
"learning_rate": 0.0001,
|
| 908 |
+
"loss": 2.1955,
|
| 909 |
"step": 150
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 0.65,
|
| 913 |
"learning_rate": 0.0001,
|
| 914 |
+
"loss": 2.1918,
|
| 915 |
"step": 151
|
| 916 |
},
|
| 917 |
{
|
| 918 |
"epoch": 0.65,
|
| 919 |
"learning_rate": 0.0001,
|
| 920 |
+
"loss": 2.2177,
|
| 921 |
"step": 152
|
| 922 |
},
|
| 923 |
{
|
| 924 |
"epoch": 0.65,
|
| 925 |
"learning_rate": 0.0001,
|
| 926 |
+
"loss": 2.189,
|
| 927 |
"step": 153
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 0.66,
|
| 931 |
"learning_rate": 0.0001,
|
| 932 |
+
"loss": 2.1829,
|
| 933 |
"step": 154
|
| 934 |
},
|
| 935 |
{
|
| 936 |
"epoch": 0.66,
|
| 937 |
"learning_rate": 0.0001,
|
| 938 |
+
"loss": 2.2272,
|
| 939 |
"step": 155
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 0.67,
|
| 943 |
"learning_rate": 0.0001,
|
| 944 |
+
"loss": 2.1924,
|
| 945 |
"step": 156
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 0.67,
|
| 949 |
"learning_rate": 0.0001,
|
| 950 |
+
"loss": 2.1877,
|
| 951 |
"step": 157
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 0.67,
|
| 955 |
"learning_rate": 0.0001,
|
| 956 |
+
"loss": 2.1772,
|
| 957 |
"step": 158
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 0.68,
|
| 961 |
"learning_rate": 0.0001,
|
| 962 |
+
"loss": 2.1338,
|
| 963 |
"step": 159
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 0.68,
|
| 967 |
"learning_rate": 0.0001,
|
| 968 |
+
"loss": 2.1817,
|
| 969 |
"step": 160
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 0.69,
|
| 973 |
"learning_rate": 0.0001,
|
| 974 |
+
"loss": 2.211,
|
| 975 |
"step": 161
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 0.69,
|
| 979 |
"learning_rate": 0.0001,
|
| 980 |
+
"loss": 2.1922,
|
| 981 |
"step": 162
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 0.7,
|
| 985 |
"learning_rate": 0.0001,
|
| 986 |
+
"loss": 2.162,
|
| 987 |
"step": 163
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 0.7,
|
| 991 |
"learning_rate": 0.0001,
|
| 992 |
+
"loss": 2.1906,
|
| 993 |
"step": 164
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 0.7,
|
| 997 |
"learning_rate": 0.0001,
|
| 998 |
+
"loss": 2.1931,
|
| 999 |
"step": 165
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 0.71,
|
| 1003 |
"learning_rate": 0.0001,
|
| 1004 |
+
"loss": 2.1611,
|
| 1005 |
"step": 166
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.71,
|
| 1009 |
"learning_rate": 0.0001,
|
| 1010 |
+
"loss": 2.1913,
|
| 1011 |
"step": 167
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 0.72,
|
| 1015 |
"learning_rate": 0.0001,
|
| 1016 |
+
"loss": 2.2342,
|
| 1017 |
"step": 168
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 0.72,
|
| 1021 |
"learning_rate": 0.0001,
|
| 1022 |
+
"loss": 2.1753,
|
| 1023 |
"step": 169
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 0.73,
|
| 1027 |
"learning_rate": 0.0001,
|
| 1028 |
+
"loss": 2.1634,
|
| 1029 |
"step": 170
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 0.73,
|
| 1033 |
"learning_rate": 0.0001,
|
| 1034 |
+
"loss": 2.1628,
|
| 1035 |
"step": 171
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 0.73,
|
| 1039 |
"learning_rate": 0.0001,
|
| 1040 |
+
"loss": 2.1871,
|
| 1041 |
"step": 172
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 0.74,
|
| 1045 |
"learning_rate": 0.0001,
|
| 1046 |
+
"loss": 2.1995,
|
| 1047 |
"step": 173
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 0.74,
|
| 1051 |
"learning_rate": 0.0001,
|
| 1052 |
+
"loss": 2.1537,
|
| 1053 |
"step": 174
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 0.75,
|
| 1057 |
"learning_rate": 0.0001,
|
| 1058 |
+
"loss": 2.2105,
|
| 1059 |
"step": 175
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 0.75,
|
| 1063 |
"learning_rate": 0.0001,
|
| 1064 |
+
"loss": 2.1633,
|
| 1065 |
"step": 176
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 0.76,
|
| 1069 |
"learning_rate": 0.0001,
|
| 1070 |
+
"loss": 2.1315,
|
| 1071 |
"step": 177
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 0.76,
|
| 1075 |
"learning_rate": 0.0001,
|
| 1076 |
+
"loss": 2.1628,
|
| 1077 |
"step": 178
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 0.76,
|
| 1081 |
"learning_rate": 0.0001,
|
| 1082 |
+
"loss": 2.1704,
|
| 1083 |
"step": 179
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 0.77,
|
| 1087 |
"learning_rate": 0.0001,
|
| 1088 |
+
"loss": 2.1696,
|
| 1089 |
"step": 180
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 0.77,
|
| 1093 |
"learning_rate": 0.0001,
|
| 1094 |
+
"loss": 2.1839,
|
| 1095 |
"step": 181
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 0.78,
|
| 1099 |
"learning_rate": 0.0001,
|
| 1100 |
+
"loss": 2.2022,
|
| 1101 |
"step": 182
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 0.78,
|
| 1105 |
"learning_rate": 0.0001,
|
| 1106 |
+
"loss": 2.1568,
|
| 1107 |
"step": 183
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 0.79,
|
| 1111 |
"learning_rate": 0.0001,
|
| 1112 |
+
"loss": 2.1448,
|
| 1113 |
"step": 184
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 0.79,
|
| 1117 |
"learning_rate": 0.0001,
|
| 1118 |
+
"loss": 2.1464,
|
| 1119 |
"step": 185
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 0.79,
|
| 1123 |
"learning_rate": 0.0001,
|
| 1124 |
+
"loss": 2.159,
|
| 1125 |
"step": 186
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
"epoch": 0.8,
|
| 1129 |
"learning_rate": 0.0001,
|
| 1130 |
+
"loss": 2.138,
|
| 1131 |
"step": 187
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 0.8,
|
| 1135 |
"learning_rate": 0.0001,
|
| 1136 |
+
"loss": 2.1726,
|
| 1137 |
"step": 188
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 0.81,
|
| 1141 |
"learning_rate": 0.0001,
|
| 1142 |
+
"loss": 2.107,
|
| 1143 |
"step": 189
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 0.81,
|
| 1147 |
"learning_rate": 0.0001,
|
| 1148 |
+
"loss": 2.1899,
|
| 1149 |
"step": 190
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"epoch": 0.82,
|
| 1153 |
"learning_rate": 0.0001,
|
| 1154 |
+
"loss": 2.1993,
|
| 1155 |
"step": 191
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 0.82,
|
| 1159 |
"learning_rate": 0.0001,
|
| 1160 |
+
"loss": 2.1387,
|
| 1161 |
"step": 192
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
"epoch": 0.82,
|
| 1165 |
"learning_rate": 0.0001,
|
| 1166 |
+
"loss": 2.1257,
|
| 1167 |
"step": 193
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 0.83,
|
| 1171 |
"learning_rate": 0.0001,
|
| 1172 |
+
"loss": 2.1729,
|
| 1173 |
"step": 194
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 0.83,
|
| 1177 |
"learning_rate": 0.0001,
|
| 1178 |
+
"loss": 2.129,
|
| 1179 |
"step": 195
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 0.84,
|
| 1183 |
"learning_rate": 0.0001,
|
| 1184 |
+
"loss": 2.1368,
|
| 1185 |
"step": 196
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 0.84,
|
| 1189 |
"learning_rate": 0.0001,
|
| 1190 |
+
"loss": 2.1185,
|
| 1191 |
"step": 197
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
"epoch": 0.85,
|
| 1195 |
"learning_rate": 0.0001,
|
| 1196 |
+
"loss": 2.1327,
|
| 1197 |
"step": 198
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
"epoch": 0.85,
|
| 1201 |
"learning_rate": 0.0001,
|
| 1202 |
+
"loss": 2.1498,
|
| 1203 |
"step": 199
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
"epoch": 0.85,
|
| 1207 |
"learning_rate": 0.0001,
|
| 1208 |
+
"loss": 2.1094,
|
| 1209 |
"step": 200
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 0.86,
|
| 1213 |
"learning_rate": 0.0001,
|
| 1214 |
+
"loss": 2.1464,
|
| 1215 |
"step": 201
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 0.86,
|
| 1219 |
"learning_rate": 0.0001,
|
| 1220 |
+
"loss": 2.169,
|
| 1221 |
"step": 202
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"epoch": 0.87,
|
| 1225 |
"learning_rate": 0.0001,
|
| 1226 |
+
"loss": 2.1436,
|
| 1227 |
"step": 203
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 0.87,
|
| 1231 |
"learning_rate": 0.0001,
|
| 1232 |
+
"loss": 2.1402,
|
| 1233 |
"step": 204
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
"epoch": 0.88,
|
| 1237 |
"learning_rate": 0.0001,
|
| 1238 |
+
"loss": 2.1565,
|
| 1239 |
"step": 205
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 0.88,
|
| 1243 |
"learning_rate": 0.0001,
|
| 1244 |
+
"loss": 2.1457,
|
| 1245 |
"step": 206
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 0.88,
|
| 1249 |
"learning_rate": 0.0001,
|
| 1250 |
+
"loss": 2.1236,
|
| 1251 |
"step": 207
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
"epoch": 0.89,
|
| 1255 |
"learning_rate": 0.0001,
|
| 1256 |
+
"loss": 2.1663,
|
| 1257 |
"step": 208
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 0.89,
|
| 1261 |
"learning_rate": 0.0001,
|
| 1262 |
+
"loss": 2.1648,
|
| 1263 |
"step": 209
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
"epoch": 0.9,
|
| 1267 |
"learning_rate": 0.0001,
|
| 1268 |
+
"loss": 2.1348,
|
| 1269 |
"step": 210
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
"epoch": 0.9,
|
| 1273 |
"learning_rate": 0.0001,
|
| 1274 |
+
"loss": 2.1576,
|
| 1275 |
"step": 211
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
"epoch": 0.91,
|
| 1279 |
"learning_rate": 0.0001,
|
| 1280 |
+
"loss": 2.1683,
|
| 1281 |
"step": 212
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 0.91,
|
| 1285 |
"learning_rate": 0.0001,
|
| 1286 |
+
"loss": 2.1241,
|
| 1287 |
"step": 213
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 0.91,
|
| 1291 |
"learning_rate": 0.0001,
|
| 1292 |
+
"loss": 2.1306,
|
| 1293 |
"step": 214
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
"epoch": 0.92,
|
| 1297 |
"learning_rate": 0.0001,
|
| 1298 |
+
"loss": 2.1476,
|
| 1299 |
"step": 215
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
"epoch": 0.92,
|
| 1303 |
"learning_rate": 0.0001,
|
| 1304 |
+
"loss": 2.1477,
|
| 1305 |
"step": 216
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
"epoch": 0.93,
|
| 1309 |
"learning_rate": 0.0001,
|
| 1310 |
+
"loss": 2.1219,
|
| 1311 |
"step": 217
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 0.93,
|
| 1315 |
"learning_rate": 0.0001,
|
| 1316 |
+
"loss": 2.1511,
|
| 1317 |
"step": 218
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
"epoch": 0.94,
|
| 1321 |
"learning_rate": 0.0001,
|
| 1322 |
+
"loss": 2.1431,
|
| 1323 |
"step": 219
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
"epoch": 0.94,
|
| 1327 |
"learning_rate": 0.0001,
|
| 1328 |
+
"loss": 2.1811,
|
| 1329 |
"step": 220
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 0.94,
|
| 1333 |
"learning_rate": 0.0001,
|
| 1334 |
+
"loss": 2.1417,
|
| 1335 |
"step": 221
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 0.95,
|
| 1339 |
"learning_rate": 0.0001,
|
| 1340 |
+
"loss": 2.1237,
|
| 1341 |
"step": 222
|
| 1342 |
},
|
| 1343 |
{
|
| 1344 |
"epoch": 0.95,
|
| 1345 |
"learning_rate": 0.0001,
|
| 1346 |
+
"loss": 2.1476,
|
| 1347 |
"step": 223
|
| 1348 |
},
|
| 1349 |
{
|
| 1350 |
"epoch": 0.96,
|
| 1351 |
"learning_rate": 0.0001,
|
| 1352 |
+
"loss": 2.1791,
|
| 1353 |
"step": 224
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 0.96,
|
| 1357 |
"learning_rate": 0.0001,
|
| 1358 |
+
"loss": 2.1521,
|
| 1359 |
"step": 225
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 0.97,
|
| 1363 |
"learning_rate": 0.0001,
|
| 1364 |
+
"loss": 2.1258,
|
| 1365 |
"step": 226
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
"epoch": 0.97,
|
| 1369 |
"learning_rate": 0.0001,
|
| 1370 |
+
"loss": 2.1568,
|
| 1371 |
"step": 227
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
"epoch": 0.97,
|
| 1375 |
"learning_rate": 0.0001,
|
| 1376 |
+
"loss": 2.1518,
|
| 1377 |
"step": 228
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 0.98,
|
| 1381 |
"learning_rate": 0.0001,
|
| 1382 |
+
"loss": 2.1281,
|
| 1383 |
"step": 229
|
| 1384 |
},
|
| 1385 |
{
|
| 1386 |
"epoch": 0.98,
|
| 1387 |
"learning_rate": 0.0001,
|
| 1388 |
+
"loss": 2.1377,
|
| 1389 |
"step": 230
|
| 1390 |
},
|
| 1391 |
{
|
| 1392 |
"epoch": 0.99,
|
| 1393 |
"learning_rate": 0.0001,
|
| 1394 |
+
"loss": 2.1414,
|
| 1395 |
"step": 231
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
"epoch": 0.99,
|
| 1399 |
"learning_rate": 0.0001,
|
| 1400 |
+
"loss": 2.1741,
|
| 1401 |
"step": 232
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 1.0,
|
| 1405 |
"learning_rate": 0.0001,
|
| 1406 |
+
"loss": 2.1614,
|
| 1407 |
"step": 233
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
"epoch": 1.0,
|
| 1411 |
"learning_rate": 0.0001,
|
| 1412 |
+
"loss": 2.1615,
|
| 1413 |
"step": 234
|
| 1414 |
},
|
| 1415 |
{
|
| 1416 |
"epoch": 1.0,
|
| 1417 |
"step": 234,
|
| 1418 |
"total_flos": 2.668899657056256e+17,
|
| 1419 |
+
"train_loss": 2.312185388344985,
|
| 1420 |
+
"train_runtime": 3320.7115,
|
| 1421 |
+
"train_samples_per_second": 9.022,
|
| 1422 |
+
"train_steps_per_second": 0.07
|
| 1423 |
}
|
| 1424 |
],
|
| 1425 |
"logging_steps": 1.0,
|
| 1426 |
"max_steps": 234,
|
| 1427 |
"num_train_epochs": 1,
|
| 1428 |
+
"save_steps": 100,
|
| 1429 |
"total_flos": 2.668899657056256e+17,
|
| 1430 |
"trial_name": null,
|
| 1431 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb60254b1b35ccab57085d05705a4dc75746db1021c7da7d08c0d6f25e6f291c
|
| 3 |
size 4027
|