Upload folder using huggingface_hub
Browse files- README.md +68 -0
- all_results.json +15 -0
- config.json +40 -0
- eval_results.json +10 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- train_results.json +8 -0
- trainer_state.json +1045 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: GPT2_more_function_53
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# GPT2_more_function_53
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.9183
|
| 19 |
+
- Accuracy: 0.5679
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 128
|
| 40 |
+
- eval_batch_size: 128
|
| 41 |
+
- seed: 53
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 10000
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 51 |
+
| 2.297 | 1.0 | 15568 | 2.2407 | 0.5113 |
|
| 52 |
+
| 2.1414 | 2.0 | 31136 | 2.1019 | 0.5349 |
|
| 53 |
+
| 2.0769 | 3.0 | 46704 | 2.0458 | 0.5440 |
|
| 54 |
+
| 2.0352 | 4.0 | 62272 | 2.0085 | 0.5512 |
|
| 55 |
+
| 2.0034 | 5.0 | 77840 | 1.9856 | 0.5555 |
|
| 56 |
+
| 1.9762 | 6.0 | 93408 | 1.9654 | 0.5584 |
|
| 57 |
+
| 1.9536 | 7.0 | 108976 | 1.9493 | 0.5618 |
|
| 58 |
+
| 1.9281 | 8.0 | 124544 | 1.9358 | 0.5642 |
|
| 59 |
+
| 1.9065 | 9.0 | 140112 | 1.9251 | 0.5664 |
|
| 60 |
+
| 1.8871 | 10.0 | 155680 | 1.9183 | 0.5679 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.30.2
|
| 66 |
+
- Pytorch 2.9.1+cu128
|
| 67 |
+
- Datasets 4.1.1
|
| 68 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.5679064836390543,
|
| 4 |
+
"eval_loss": 1.9183450937271118,
|
| 5 |
+
"eval_runtime": 4.7349,
|
| 6 |
+
"eval_samples": 2852,
|
| 7 |
+
"eval_samples_per_second": 602.332,
|
| 8 |
+
"eval_steps_per_second": 4.858,
|
| 9 |
+
"perplexity": 6.8096797575123444,
|
| 10 |
+
"train_loss": 2.0850467458413293,
|
| 11 |
+
"train_runtime": 67879.3856,
|
| 12 |
+
"train_samples": 1992652,
|
| 13 |
+
"train_samples_per_second": 293.558,
|
| 14 |
+
"train_steps_per_second": 2.293
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "models/GPT2_more_function_53",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 128,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"task_specific_params": {
|
| 31 |
+
"text-generation": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 50
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.30.2",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 32768
|
| 40 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.5679064836390543,
|
| 4 |
+
"eval_loss": 1.9183450937271118,
|
| 5 |
+
"eval_runtime": 4.7349,
|
| 6 |
+
"eval_samples": 2852,
|
| 7 |
+
"eval_samples_per_second": 602.332,
|
| 8 |
+
"eval_steps_per_second": 4.858,
|
| 9 |
+
"perplexity": 6.8096797575123444
|
| 10 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad683c2d6e3575f304286de8096ccc38a7446f0c21c34493c7760f04896aca6
|
| 3 |
+
size 441329395
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"token": null,
|
| 9 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.0850467458413293,
|
| 4 |
+
"train_runtime": 67879.3856,
|
| 5 |
+
"train_samples": 1992652,
|
| 6 |
+
"train_samples_per_second": 293.558,
|
| 7 |
+
"train_steps_per_second": 2.293
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1045 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.9183450937271118,
|
| 3 |
+
"best_model_checkpoint": "models/GPT2_more_function_53/checkpoint-155680",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 155680,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 6.0974,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.13,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 3.7504,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.19,
|
| 24 |
+
"learning_rate": 3e-05,
|
| 25 |
+
"loss": 3.1766,
|
| 26 |
+
"step": 3000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.26,
|
| 30 |
+
"learning_rate": 4e-05,
|
| 31 |
+
"loss": 2.8933,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.32,
|
| 36 |
+
"learning_rate": 5e-05,
|
| 37 |
+
"loss": 2.7463,
|
| 38 |
+
"step": 5000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.39,
|
| 42 |
+
"learning_rate": 6e-05,
|
| 43 |
+
"loss": 2.6511,
|
| 44 |
+
"step": 6000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.45,
|
| 48 |
+
"learning_rate": 7e-05,
|
| 49 |
+
"loss": 2.5785,
|
| 50 |
+
"step": 7000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.51,
|
| 54 |
+
"learning_rate": 8e-05,
|
| 55 |
+
"loss": 2.5222,
|
| 56 |
+
"step": 8000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.58,
|
| 60 |
+
"learning_rate": 9e-05,
|
| 61 |
+
"loss": 2.4721,
|
| 62 |
+
"step": 9000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.64,
|
| 66 |
+
"learning_rate": 0.0001,
|
| 67 |
+
"loss": 2.4349,
|
| 68 |
+
"step": 10000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.71,
|
| 72 |
+
"learning_rate": 9.931425041186162e-05,
|
| 73 |
+
"loss": 2.4,
|
| 74 |
+
"step": 11000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.77,
|
| 78 |
+
"learning_rate": 9.862781438769907e-05,
|
| 79 |
+
"loss": 2.3671,
|
| 80 |
+
"step": 12000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.84,
|
| 84 |
+
"learning_rate": 9.794206479956069e-05,
|
| 85 |
+
"loss": 2.3407,
|
| 86 |
+
"step": 13000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.9,
|
| 90 |
+
"learning_rate": 9.725562877539814e-05,
|
| 91 |
+
"loss": 2.3166,
|
| 92 |
+
"step": 14000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.96,
|
| 96 |
+
"learning_rate": 9.656987918725975e-05,
|
| 97 |
+
"loss": 2.297,
|
| 98 |
+
"step": 15000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.0,
|
| 102 |
+
"eval_accuracy": 0.5112671312299146,
|
| 103 |
+
"eval_loss": 2.240675687789917,
|
| 104 |
+
"eval_runtime": 4.688,
|
| 105 |
+
"eval_samples_per_second": 608.363,
|
| 106 |
+
"eval_steps_per_second": 4.906,
|
| 107 |
+
"step": 15568
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.03,
|
| 111 |
+
"learning_rate": 9.58834431630972e-05,
|
| 112 |
+
"loss": 2.2735,
|
| 113 |
+
"step": 16000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.09,
|
| 117 |
+
"learning_rate": 9.519769357495882e-05,
|
| 118 |
+
"loss": 2.2539,
|
| 119 |
+
"step": 17000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.16,
|
| 123 |
+
"learning_rate": 9.451125755079627e-05,
|
| 124 |
+
"loss": 2.2432,
|
| 125 |
+
"step": 18000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.22,
|
| 129 |
+
"learning_rate": 9.382550796265789e-05,
|
| 130 |
+
"loss": 2.231,
|
| 131 |
+
"step": 19000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.28,
|
| 135 |
+
"learning_rate": 9.313907193849534e-05,
|
| 136 |
+
"loss": 2.2216,
|
| 137 |
+
"step": 20000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.35,
|
| 141 |
+
"learning_rate": 9.245332235035696e-05,
|
| 142 |
+
"loss": 2.2111,
|
| 143 |
+
"step": 21000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.41,
|
| 147 |
+
"learning_rate": 9.17668863261944e-05,
|
| 148 |
+
"loss": 2.205,
|
| 149 |
+
"step": 22000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.48,
|
| 153 |
+
"learning_rate": 9.108113673805602e-05,
|
| 154 |
+
"loss": 2.1938,
|
| 155 |
+
"step": 23000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.54,
|
| 159 |
+
"learning_rate": 9.039470071389346e-05,
|
| 160 |
+
"loss": 2.1852,
|
| 161 |
+
"step": 24000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.61,
|
| 165 |
+
"learning_rate": 8.970895112575508e-05,
|
| 166 |
+
"loss": 2.1784,
|
| 167 |
+
"step": 25000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.67,
|
| 171 |
+
"learning_rate": 8.902251510159254e-05,
|
| 172 |
+
"loss": 2.1713,
|
| 173 |
+
"step": 26000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.73,
|
| 177 |
+
"learning_rate": 8.833676551345414e-05,
|
| 178 |
+
"loss": 2.1637,
|
| 179 |
+
"step": 27000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.8,
|
| 183 |
+
"learning_rate": 8.765032948929161e-05,
|
| 184 |
+
"loss": 2.1584,
|
| 185 |
+
"step": 28000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.86,
|
| 189 |
+
"learning_rate": 8.696457990115322e-05,
|
| 190 |
+
"loss": 2.1517,
|
| 191 |
+
"step": 29000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.93,
|
| 195 |
+
"learning_rate": 8.627814387699067e-05,
|
| 196 |
+
"loss": 2.1458,
|
| 197 |
+
"step": 30000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.99,
|
| 201 |
+
"learning_rate": 8.559239428885229e-05,
|
| 202 |
+
"loss": 2.1414,
|
| 203 |
+
"step": 31000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0,
|
| 207 |
+
"eval_accuracy": 0.5348781349736612,
|
| 208 |
+
"eval_loss": 2.101914167404175,
|
| 209 |
+
"eval_runtime": 4.8416,
|
| 210 |
+
"eval_samples_per_second": 589.065,
|
| 211 |
+
"eval_steps_per_second": 4.751,
|
| 212 |
+
"step": 31136
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.06,
|
| 216 |
+
"learning_rate": 8.490595826468973e-05,
|
| 217 |
+
"loss": 2.1209,
|
| 218 |
+
"step": 32000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.12,
|
| 222 |
+
"learning_rate": 8.422020867655134e-05,
|
| 223 |
+
"loss": 2.1174,
|
| 224 |
+
"step": 33000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.18,
|
| 228 |
+
"learning_rate": 8.35337726523888e-05,
|
| 229 |
+
"loss": 2.1125,
|
| 230 |
+
"step": 34000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.25,
|
| 234 |
+
"learning_rate": 8.284733662822626e-05,
|
| 235 |
+
"loss": 2.1084,
|
| 236 |
+
"step": 35000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.31,
|
| 240 |
+
"learning_rate": 8.216158704008787e-05,
|
| 241 |
+
"loss": 2.1072,
|
| 242 |
+
"step": 36000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.38,
|
| 246 |
+
"learning_rate": 8.147515101592533e-05,
|
| 247 |
+
"loss": 2.1029,
|
| 248 |
+
"step": 37000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.44,
|
| 252 |
+
"learning_rate": 8.078940142778694e-05,
|
| 253 |
+
"loss": 2.1,
|
| 254 |
+
"step": 38000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.51,
|
| 258 |
+
"learning_rate": 8.010296540362439e-05,
|
| 259 |
+
"loss": 2.097,
|
| 260 |
+
"step": 39000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.57,
|
| 264 |
+
"learning_rate": 7.941652937946183e-05,
|
| 265 |
+
"loss": 2.0943,
|
| 266 |
+
"step": 40000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.63,
|
| 270 |
+
"learning_rate": 7.873077979132345e-05,
|
| 271 |
+
"loss": 2.0907,
|
| 272 |
+
"step": 41000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.7,
|
| 276 |
+
"learning_rate": 7.80443437671609e-05,
|
| 277 |
+
"loss": 2.0887,
|
| 278 |
+
"step": 42000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.76,
|
| 282 |
+
"learning_rate": 7.735859417902251e-05,
|
| 283 |
+
"loss": 2.0848,
|
| 284 |
+
"step": 43000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.83,
|
| 288 |
+
"learning_rate": 7.667215815485998e-05,
|
| 289 |
+
"loss": 2.0833,
|
| 290 |
+
"step": 44000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.89,
|
| 294 |
+
"learning_rate": 7.598640856672159e-05,
|
| 295 |
+
"loss": 2.0794,
|
| 296 |
+
"step": 45000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.95,
|
| 300 |
+
"learning_rate": 7.529997254255904e-05,
|
| 301 |
+
"loss": 2.0769,
|
| 302 |
+
"step": 46000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.0,
|
| 306 |
+
"eval_accuracy": 0.5440276750118718,
|
| 307 |
+
"eval_loss": 2.0458028316497803,
|
| 308 |
+
"eval_runtime": 4.8031,
|
| 309 |
+
"eval_samples_per_second": 593.781,
|
| 310 |
+
"eval_steps_per_second": 4.789,
|
| 311 |
+
"step": 46704
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.02,
|
| 315 |
+
"learning_rate": 7.461422295442066e-05,
|
| 316 |
+
"loss": 2.0689,
|
| 317 |
+
"step": 47000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.08,
|
| 321 |
+
"learning_rate": 7.39277869302581e-05,
|
| 322 |
+
"loss": 2.0524,
|
| 323 |
+
"step": 48000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.15,
|
| 327 |
+
"learning_rate": 7.324203734211971e-05,
|
| 328 |
+
"loss": 2.0519,
|
| 329 |
+
"step": 49000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.21,
|
| 333 |
+
"learning_rate": 7.255560131795716e-05,
|
| 334 |
+
"loss": 2.0508,
|
| 335 |
+
"step": 50000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.28,
|
| 339 |
+
"learning_rate": 7.186985172981878e-05,
|
| 340 |
+
"loss": 2.0502,
|
| 341 |
+
"step": 51000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.34,
|
| 345 |
+
"learning_rate": 7.118341570565623e-05,
|
| 346 |
+
"loss": 2.0495,
|
| 347 |
+
"step": 52000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.4,
|
| 351 |
+
"learning_rate": 7.049766611751785e-05,
|
| 352 |
+
"loss": 2.0476,
|
| 353 |
+
"step": 53000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.47,
|
| 357 |
+
"learning_rate": 6.981123009335531e-05,
|
| 358 |
+
"loss": 2.0457,
|
| 359 |
+
"step": 54000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.53,
|
| 363 |
+
"learning_rate": 6.912548050521693e-05,
|
| 364 |
+
"loss": 2.0455,
|
| 365 |
+
"step": 55000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.6,
|
| 369 |
+
"learning_rate": 6.843904448105436e-05,
|
| 370 |
+
"loss": 2.0432,
|
| 371 |
+
"step": 56000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.66,
|
| 375 |
+
"learning_rate": 6.775329489291598e-05,
|
| 376 |
+
"loss": 2.0418,
|
| 377 |
+
"step": 57000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.73,
|
| 381 |
+
"learning_rate": 6.706685886875343e-05,
|
| 382 |
+
"loss": 2.0401,
|
| 383 |
+
"step": 58000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.79,
|
| 387 |
+
"learning_rate": 6.638042284459088e-05,
|
| 388 |
+
"loss": 2.0394,
|
| 389 |
+
"step": 59000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.85,
|
| 393 |
+
"learning_rate": 6.56946732564525e-05,
|
| 394 |
+
"loss": 2.0376,
|
| 395 |
+
"step": 60000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.92,
|
| 399 |
+
"learning_rate": 6.500823723228996e-05,
|
| 400 |
+
"loss": 2.0354,
|
| 401 |
+
"step": 61000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.98,
|
| 405 |
+
"learning_rate": 6.432248764415157e-05,
|
| 406 |
+
"loss": 2.0352,
|
| 407 |
+
"step": 62000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.0,
|
| 411 |
+
"eval_accuracy": 0.5512446024892049,
|
| 412 |
+
"eval_loss": 2.008540391921997,
|
| 413 |
+
"eval_runtime": 4.7884,
|
| 414 |
+
"eval_samples_per_second": 595.602,
|
| 415 |
+
"eval_steps_per_second": 4.803,
|
| 416 |
+
"step": 62272
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.05,
|
| 420 |
+
"learning_rate": 6.363605161998903e-05,
|
| 421 |
+
"loss": 2.0153,
|
| 422 |
+
"step": 63000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.11,
|
| 426 |
+
"learning_rate": 6.295030203185063e-05,
|
| 427 |
+
"loss": 2.0116,
|
| 428 |
+
"step": 64000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.18,
|
| 432 |
+
"learning_rate": 6.226386600768808e-05,
|
| 433 |
+
"loss": 2.0113,
|
| 434 |
+
"step": 65000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.24,
|
| 438 |
+
"learning_rate": 6.15781164195497e-05,
|
| 439 |
+
"loss": 2.0106,
|
| 440 |
+
"step": 66000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.3,
|
| 444 |
+
"learning_rate": 6.089168039538715e-05,
|
| 445 |
+
"loss": 2.0116,
|
| 446 |
+
"step": 67000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.37,
|
| 450 |
+
"learning_rate": 6.0205930807248766e-05,
|
| 451 |
+
"loss": 2.0118,
|
| 452 |
+
"step": 68000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.43,
|
| 456 |
+
"learning_rate": 5.951949478308622e-05,
|
| 457 |
+
"loss": 2.0089,
|
| 458 |
+
"step": 69000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.5,
|
| 462 |
+
"learning_rate": 5.883374519494783e-05,
|
| 463 |
+
"loss": 2.0095,
|
| 464 |
+
"step": 70000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.56,
|
| 468 |
+
"learning_rate": 5.814730917078528e-05,
|
| 469 |
+
"loss": 2.0088,
|
| 470 |
+
"step": 71000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.62,
|
| 474 |
+
"learning_rate": 5.746155958264689e-05,
|
| 475 |
+
"loss": 2.0074,
|
| 476 |
+
"step": 72000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.69,
|
| 480 |
+
"learning_rate": 5.677512355848436e-05,
|
| 481 |
+
"loss": 2.007,
|
| 482 |
+
"step": 73000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.75,
|
| 486 |
+
"learning_rate": 5.60886875343218e-05,
|
| 487 |
+
"loss": 2.0058,
|
| 488 |
+
"step": 74000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.82,
|
| 492 |
+
"learning_rate": 5.540293794618342e-05,
|
| 493 |
+
"loss": 2.0056,
|
| 494 |
+
"step": 75000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.88,
|
| 498 |
+
"learning_rate": 5.471650192202087e-05,
|
| 499 |
+
"loss": 2.005,
|
| 500 |
+
"step": 76000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.95,
|
| 504 |
+
"learning_rate": 5.4030752333882485e-05,
|
| 505 |
+
"loss": 2.0034,
|
| 506 |
+
"step": 77000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.0,
|
| 510 |
+
"eval_accuracy": 0.5555073936234829,
|
| 511 |
+
"eval_loss": 1.9856412410736084,
|
| 512 |
+
"eval_runtime": 4.7852,
|
| 513 |
+
"eval_samples_per_second": 595.998,
|
| 514 |
+
"eval_steps_per_second": 4.806,
|
| 515 |
+
"step": 77840
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 5.01,
|
| 519 |
+
"learning_rate": 5.3344316309719936e-05,
|
| 520 |
+
"loss": 1.9962,
|
| 521 |
+
"step": 78000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 5.07,
|
| 525 |
+
"learning_rate": 5.2658566721581545e-05,
|
| 526 |
+
"loss": 1.9772,
|
| 527 |
+
"step": 79000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 5.14,
|
| 531 |
+
"learning_rate": 5.197213069741901e-05,
|
| 532 |
+
"loss": 1.9792,
|
| 533 |
+
"step": 80000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.2,
|
| 537 |
+
"learning_rate": 5.128638110928061e-05,
|
| 538 |
+
"loss": 1.981,
|
| 539 |
+
"step": 81000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.27,
|
| 543 |
+
"learning_rate": 5.059994508511807e-05,
|
| 544 |
+
"loss": 1.9816,
|
| 545 |
+
"step": 82000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 5.33,
|
| 549 |
+
"learning_rate": 4.9914195496979685e-05,
|
| 550 |
+
"loss": 1.9803,
|
| 551 |
+
"step": 83000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 5.4,
|
| 555 |
+
"learning_rate": 4.9227759472817136e-05,
|
| 556 |
+
"loss": 1.9806,
|
| 557 |
+
"step": 84000
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 5.46,
|
| 561 |
+
"learning_rate": 4.854200988467875e-05,
|
| 562 |
+
"loss": 1.9807,
|
| 563 |
+
"step": 85000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 5.52,
|
| 567 |
+
"learning_rate": 4.78555738605162e-05,
|
| 568 |
+
"loss": 1.9806,
|
| 569 |
+
"step": 86000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.59,
|
| 573 |
+
"learning_rate": 4.716982427237782e-05,
|
| 574 |
+
"loss": 1.9804,
|
| 575 |
+
"step": 87000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.65,
|
| 579 |
+
"learning_rate": 4.648338824821527e-05,
|
| 580 |
+
"loss": 1.9793,
|
| 581 |
+
"step": 88000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 5.72,
|
| 585 |
+
"learning_rate": 4.579763866007688e-05,
|
| 586 |
+
"loss": 1.9783,
|
| 587 |
+
"step": 89000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 5.78,
|
| 591 |
+
"learning_rate": 4.511120263591434e-05,
|
| 592 |
+
"loss": 1.9783,
|
| 593 |
+
"step": 90000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.85,
|
| 597 |
+
"learning_rate": 4.442476661175179e-05,
|
| 598 |
+
"loss": 1.9776,
|
| 599 |
+
"step": 91000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 5.91,
|
| 603 |
+
"learning_rate": 4.37390170236134e-05,
|
| 604 |
+
"loss": 1.9764,
|
| 605 |
+
"step": 92000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.97,
|
| 609 |
+
"learning_rate": 4.3052580999450855e-05,
|
| 610 |
+
"loss": 1.9762,
|
| 611 |
+
"step": 93000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.0,
|
| 615 |
+
"eval_accuracy": 0.5583510949630595,
|
| 616 |
+
"eval_loss": 1.965383768081665,
|
| 617 |
+
"eval_runtime": 4.7681,
|
| 618 |
+
"eval_samples_per_second": 598.141,
|
| 619 |
+
"eval_steps_per_second": 4.824,
|
| 620 |
+
"step": 93408
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 6.04,
|
| 624 |
+
"learning_rate": 4.236683141131247e-05,
|
| 625 |
+
"loss": 1.9612,
|
| 626 |
+
"step": 94000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 6.1,
|
| 630 |
+
"learning_rate": 4.1680395387149915e-05,
|
| 631 |
+
"loss": 1.9518,
|
| 632 |
+
"step": 95000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.17,
|
| 636 |
+
"learning_rate": 4.099464579901153e-05,
|
| 637 |
+
"loss": 1.9535,
|
| 638 |
+
"step": 96000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 6.23,
|
| 642 |
+
"learning_rate": 4.030820977484899e-05,
|
| 643 |
+
"loss": 1.9532,
|
| 644 |
+
"step": 97000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.29,
|
| 648 |
+
"learning_rate": 3.9622460186710605e-05,
|
| 649 |
+
"loss": 1.9556,
|
| 650 |
+
"step": 98000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 6.36,
|
| 654 |
+
"learning_rate": 3.893602416254805e-05,
|
| 655 |
+
"loss": 1.9562,
|
| 656 |
+
"step": 99000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 6.42,
|
| 660 |
+
"learning_rate": 3.8250274574409665e-05,
|
| 661 |
+
"loss": 1.955,
|
| 662 |
+
"step": 100000
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.49,
|
| 666 |
+
"learning_rate": 3.756383855024712e-05,
|
| 667 |
+
"loss": 1.9569,
|
| 668 |
+
"step": 101000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 6.55,
|
| 672 |
+
"learning_rate": 3.687808896210873e-05,
|
| 673 |
+
"loss": 1.9532,
|
| 674 |
+
"step": 102000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.62,
|
| 678 |
+
"learning_rate": 3.619165293794618e-05,
|
| 679 |
+
"loss": 1.9554,
|
| 680 |
+
"step": 103000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 6.68,
|
| 684 |
+
"learning_rate": 3.55059033498078e-05,
|
| 685 |
+
"loss": 1.9542,
|
| 686 |
+
"step": 104000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 6.74,
|
| 690 |
+
"learning_rate": 3.481946732564525e-05,
|
| 691 |
+
"loss": 1.954,
|
| 692 |
+
"step": 105000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.81,
|
| 696 |
+
"learning_rate": 3.4133717737506865e-05,
|
| 697 |
+
"loss": 1.9531,
|
| 698 |
+
"step": 106000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 6.87,
|
| 702 |
+
"learning_rate": 3.3447281713344316e-05,
|
| 703 |
+
"loss": 1.9527,
|
| 704 |
+
"step": 107000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.94,
|
| 708 |
+
"learning_rate": 3.276153212520593e-05,
|
| 709 |
+
"loss": 1.9536,
|
| 710 |
+
"step": 108000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 7.0,
|
| 714 |
+
"eval_accuracy": 0.5617856235712472,
|
| 715 |
+
"eval_loss": 1.9492745399475098,
|
| 716 |
+
"eval_runtime": 4.7695,
|
| 717 |
+
"eval_samples_per_second": 597.965,
|
| 718 |
+
"eval_steps_per_second": 4.822,
|
| 719 |
+
"step": 108976
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 7.0,
|
| 723 |
+
"learning_rate": 3.207509610104338e-05,
|
| 724 |
+
"loss": 1.9502,
|
| 725 |
+
"step": 109000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 7.07,
|
| 729 |
+
"learning_rate": 3.138866007688084e-05,
|
| 730 |
+
"loss": 1.9267,
|
| 731 |
+
"step": 110000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 7.13,
|
| 735 |
+
"learning_rate": 3.070291048874245e-05,
|
| 736 |
+
"loss": 1.931,
|
| 737 |
+
"step": 111000
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 7.19,
|
| 741 |
+
"learning_rate": 3.00164744645799e-05,
|
| 742 |
+
"loss": 1.9306,
|
| 743 |
+
"step": 112000
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 7.26,
|
| 747 |
+
"learning_rate": 2.9330724876441517e-05,
|
| 748 |
+
"loss": 1.9327,
|
| 749 |
+
"step": 113000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 7.32,
|
| 753 |
+
"learning_rate": 2.8644288852278968e-05,
|
| 754 |
+
"loss": 1.9317,
|
| 755 |
+
"step": 114000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 7.39,
|
| 759 |
+
"learning_rate": 2.795853926414058e-05,
|
| 760 |
+
"loss": 1.9319,
|
| 761 |
+
"step": 115000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 7.45,
|
| 765 |
+
"learning_rate": 2.7272103239978035e-05,
|
| 766 |
+
"loss": 1.9317,
|
| 767 |
+
"step": 116000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 7.52,
|
| 771 |
+
"learning_rate": 2.658635365183965e-05,
|
| 772 |
+
"loss": 1.9319,
|
| 773 |
+
"step": 117000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 7.58,
|
| 777 |
+
"learning_rate": 2.5899917627677102e-05,
|
| 778 |
+
"loss": 1.9321,
|
| 779 |
+
"step": 118000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 7.64,
|
| 783 |
+
"learning_rate": 2.5214168039538714e-05,
|
| 784 |
+
"loss": 1.9316,
|
| 785 |
+
"step": 119000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 7.71,
|
| 789 |
+
"learning_rate": 2.452773201537617e-05,
|
| 790 |
+
"loss": 1.9311,
|
| 791 |
+
"step": 120000
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 7.77,
|
| 795 |
+
"learning_rate": 2.384198242723778e-05,
|
| 796 |
+
"loss": 1.9314,
|
| 797 |
+
"step": 121000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.84,
|
| 801 |
+
"learning_rate": 2.3155546403075236e-05,
|
| 802 |
+
"loss": 1.9297,
|
| 803 |
+
"step": 122000
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 7.9,
|
| 807 |
+
"learning_rate": 2.2469110378912686e-05,
|
| 808 |
+
"loss": 1.9302,
|
| 809 |
+
"step": 123000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 7.97,
|
| 813 |
+
"learning_rate": 2.1783360790774302e-05,
|
| 814 |
+
"loss": 1.9281,
|
| 815 |
+
"step": 124000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 8.0,
|
| 819 |
+
"eval_accuracy": 0.5641958675221699,
|
| 820 |
+
"eval_loss": 1.9358315467834473,
|
| 821 |
+
"eval_runtime": 4.7877,
|
| 822 |
+
"eval_samples_per_second": 595.693,
|
| 823 |
+
"eval_steps_per_second": 4.804,
|
| 824 |
+
"step": 124544
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 8.03,
|
| 828 |
+
"learning_rate": 2.1096924766611753e-05,
|
| 829 |
+
"loss": 1.9201,
|
| 830 |
+
"step": 125000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 8.09,
|
| 834 |
+
"learning_rate": 2.041117517847337e-05,
|
| 835 |
+
"loss": 1.9086,
|
| 836 |
+
"step": 126000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 8.16,
|
| 840 |
+
"learning_rate": 1.972473915431082e-05,
|
| 841 |
+
"loss": 1.9107,
|
| 842 |
+
"step": 127000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 8.22,
|
| 846 |
+
"learning_rate": 1.903830313014827e-05,
|
| 847 |
+
"loss": 1.9099,
|
| 848 |
+
"step": 128000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 8.29,
|
| 852 |
+
"learning_rate": 1.8352553542009884e-05,
|
| 853 |
+
"loss": 1.9112,
|
| 854 |
+
"step": 129000
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 8.35,
|
| 858 |
+
"learning_rate": 1.7666117517847338e-05,
|
| 859 |
+
"loss": 1.9099,
|
| 860 |
+
"step": 130000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 8.41,
|
| 864 |
+
"learning_rate": 1.697968149368479e-05,
|
| 865 |
+
"loss": 1.9092,
|
| 866 |
+
"step": 131000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 8.48,
|
| 870 |
+
"learning_rate": 1.62939319055464e-05,
|
| 871 |
+
"loss": 1.9101,
|
| 872 |
+
"step": 132000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.54,
|
| 876 |
+
"learning_rate": 1.5607495881383856e-05,
|
| 877 |
+
"loss": 1.9104,
|
| 878 |
+
"step": 133000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 8.61,
|
| 882 |
+
"learning_rate": 1.492174629324547e-05,
|
| 883 |
+
"loss": 1.909,
|
| 884 |
+
"step": 134000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 8.67,
|
| 888 |
+
"learning_rate": 1.4235310269082921e-05,
|
| 889 |
+
"loss": 1.9087,
|
| 890 |
+
"step": 135000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 8.74,
|
| 894 |
+
"learning_rate": 1.3549560680944537e-05,
|
| 895 |
+
"loss": 1.9079,
|
| 896 |
+
"step": 136000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 8.8,
|
| 900 |
+
"learning_rate": 1.2863124656781988e-05,
|
| 901 |
+
"loss": 1.9074,
|
| 902 |
+
"step": 137000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 8.86,
|
| 906 |
+
"learning_rate": 1.217668863261944e-05,
|
| 907 |
+
"loss": 1.9087,
|
| 908 |
+
"step": 138000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 8.93,
|
| 912 |
+
"learning_rate": 1.1490939044481055e-05,
|
| 913 |
+
"loss": 1.9076,
|
| 914 |
+
"step": 139000
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 8.99,
|
| 918 |
+
"learning_rate": 1.0804503020318507e-05,
|
| 919 |
+
"loss": 1.9065,
|
| 920 |
+
"step": 140000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 9.0,
|
| 924 |
+
"eval_accuracy": 0.5664294154675266,
|
| 925 |
+
"eval_loss": 1.9251179695129395,
|
| 926 |
+
"eval_runtime": 4.7856,
|
| 927 |
+
"eval_samples_per_second": 595.949,
|
| 928 |
+
"eval_steps_per_second": 4.806,
|
| 929 |
+
"step": 140112
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 9.06,
|
| 933 |
+
"learning_rate": 1.0118753432180122e-05,
|
| 934 |
+
"loss": 1.8912,
|
| 935 |
+
"step": 141000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 9.12,
|
| 939 |
+
"learning_rate": 9.432317408017572e-06,
|
| 940 |
+
"loss": 1.8903,
|
| 941 |
+
"step": 142000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 9.19,
|
| 945 |
+
"learning_rate": 8.745881383855025e-06,
|
| 946 |
+
"loss": 1.8892,
|
| 947 |
+
"step": 143000
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 9.25,
|
| 951 |
+
"learning_rate": 8.059445359692478e-06,
|
| 952 |
+
"loss": 1.8894,
|
| 953 |
+
"step": 144000
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 9.31,
|
| 957 |
+
"learning_rate": 7.373695771554091e-06,
|
| 958 |
+
"loss": 1.8906,
|
| 959 |
+
"step": 145000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 9.38,
|
| 963 |
+
"learning_rate": 6.6879461834157054e-06,
|
| 964 |
+
"loss": 1.8913,
|
| 965 |
+
"step": 146000
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 9.44,
|
| 969 |
+
"learning_rate": 6.001510159253158e-06,
|
| 970 |
+
"loss": 1.8893,
|
| 971 |
+
"step": 147000
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 9.51,
|
| 975 |
+
"learning_rate": 5.31507413509061e-06,
|
| 976 |
+
"loss": 1.889,
|
| 977 |
+
"step": 148000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 9.57,
|
| 981 |
+
"learning_rate": 4.628638110928061e-06,
|
| 982 |
+
"loss": 1.8894,
|
| 983 |
+
"step": 149000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 9.64,
|
| 987 |
+
"learning_rate": 3.942888522789677e-06,
|
| 988 |
+
"loss": 1.8889,
|
| 989 |
+
"step": 150000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 9.7,
|
| 993 |
+
"learning_rate": 3.256452498627128e-06,
|
| 994 |
+
"loss": 1.8899,
|
| 995 |
+
"step": 151000
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 9.76,
|
| 999 |
+
"learning_rate": 2.5707029104887426e-06,
|
| 1000 |
+
"loss": 1.8881,
|
| 1001 |
+
"step": 152000
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 9.83,
|
| 1005 |
+
"learning_rate": 1.8842668863261946e-06,
|
| 1006 |
+
"loss": 1.8868,
|
| 1007 |
+
"step": 153000
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 9.89,
|
| 1011 |
+
"learning_rate": 1.1985172981878091e-06,
|
| 1012 |
+
"loss": 1.8879,
|
| 1013 |
+
"step": 154000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 9.96,
|
| 1017 |
+
"learning_rate": 5.120812740252608e-07,
|
| 1018 |
+
"loss": 1.8871,
|
| 1019 |
+
"step": 155000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 10.0,
|
| 1023 |
+
"eval_accuracy": 0.5679064836390543,
|
| 1024 |
+
"eval_loss": 1.9183450937271118,
|
| 1025 |
+
"eval_runtime": 4.7588,
|
| 1026 |
+
"eval_samples_per_second": 599.309,
|
| 1027 |
+
"eval_steps_per_second": 4.833,
|
| 1028 |
+
"step": 155680
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 10.0,
|
| 1032 |
+
"step": 155680,
|
| 1033 |
+
"total_flos": 1.30166022537216e+18,
|
| 1034 |
+
"train_loss": 2.0850467458413293,
|
| 1035 |
+
"train_runtime": 67879.3856,
|
| 1036 |
+
"train_samples_per_second": 293.558,
|
| 1037 |
+
"train_steps_per_second": 2.293
|
| 1038 |
+
}
|
| 1039 |
+
],
|
| 1040 |
+
"max_steps": 155680,
|
| 1041 |
+
"num_train_epochs": 10,
|
| 1042 |
+
"total_flos": 1.30166022537216e+18,
|
| 1043 |
+
"trial_name": null,
|
| 1044 |
+
"trial_params": null
|
| 1045 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55030472b73f5eb31443d01aec6ba999018665c969013dac8bbd9d86c43b3535
|
| 3 |
+
size 4881
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|