Uploaded PeptideGPT soluble model
Browse files- README.md +109 -0
- all_results.json +15 -0
- config.json +39 -0
- eval_results.json +10 -0
- events.out.tfevents.1710909878.lambda-a6000.1646203.0 +3 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- train_results.json +8 -0
- trainer_state.json +780 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: nferruz/ProtGPT2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: output_sol_3
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# output_sol_3
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [nferruz/ProtGPT2](https://huggingface.co/nferruz/ProtGPT2) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 5.6849
|
| 21 |
+
- Accuracy: 0.2249
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-06
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 50.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| 6.7291 | 1.0 | 387 | 6.4419 | 0.1754 |
|
| 53 |
+
| 6.5666 | 2.0 | 774 | 6.2737 | 0.1847 |
|
| 54 |
+
| 6.4479 | 3.0 | 1161 | 6.1396 | 0.1918 |
|
| 55 |
+
| 6.3439 | 4.0 | 1548 | 6.0359 | 0.1974 |
|
| 56 |
+
| 6.2577 | 5.0 | 1935 | 5.9318 | 0.2031 |
|
| 57 |
+
| 6.172 | 6.0 | 2322 | 5.8617 | 0.2083 |
|
| 58 |
+
| 6.0943 | 7.0 | 2709 | 5.8212 | 0.2115 |
|
| 59 |
+
| 6.0318 | 8.0 | 3096 | 5.7983 | 0.2132 |
|
| 60 |
+
| 5.9812 | 9.0 | 3483 | 5.7818 | 0.2151 |
|
| 61 |
+
| 5.9436 | 10.0 | 3870 | 5.7673 | 0.2163 |
|
| 62 |
+
| 5.9144 | 11.0 | 4257 | 5.7563 | 0.2171 |
|
| 63 |
+
| 5.8923 | 12.0 | 4644 | 5.7452 | 0.2185 |
|
| 64 |
+
| 5.8723 | 13.0 | 5031 | 5.7387 | 0.2190 |
|
| 65 |
+
| 5.8549 | 14.0 | 5418 | 5.7320 | 0.2193 |
|
| 66 |
+
| 5.8427 | 15.0 | 5805 | 5.7259 | 0.2199 |
|
| 67 |
+
| 5.8306 | 16.0 | 6192 | 5.7219 | 0.2203 |
|
| 68 |
+
| 5.8176 | 17.0 | 6579 | 5.7186 | 0.2204 |
|
| 69 |
+
| 5.8129 | 18.0 | 6966 | 5.7153 | 0.2206 |
|
| 70 |
+
| 5.8055 | 19.0 | 7353 | 5.7119 | 0.2211 |
|
| 71 |
+
| 5.7954 | 20.0 | 7740 | 5.7097 | 0.2213 |
|
| 72 |
+
| 5.7906 | 21.0 | 8127 | 5.7078 | 0.2219 |
|
| 73 |
+
| 5.7834 | 22.0 | 8514 | 5.7061 | 0.2221 |
|
| 74 |
+
| 5.7779 | 23.0 | 8901 | 5.7042 | 0.2224 |
|
| 75 |
+
| 5.7718 | 24.0 | 9288 | 5.7019 | 0.2226 |
|
| 76 |
+
| 5.7664 | 25.0 | 9675 | 5.7002 | 0.2231 |
|
| 77 |
+
| 5.7616 | 26.0 | 10062 | 5.6989 | 0.2234 |
|
| 78 |
+
| 5.7596 | 27.0 | 10449 | 5.6972 | 0.2234 |
|
| 79 |
+
| 5.7553 | 28.0 | 10836 | 5.6960 | 0.2236 |
|
| 80 |
+
| 5.7525 | 29.0 | 11223 | 5.6948 | 0.2235 |
|
| 81 |
+
| 5.7488 | 30.0 | 11610 | 5.6939 | 0.2236 |
|
| 82 |
+
| 5.7445 | 31.0 | 11997 | 5.6930 | 0.2237 |
|
| 83 |
+
| 5.7409 | 32.0 | 12384 | 5.6919 | 0.2237 |
|
| 84 |
+
| 5.7389 | 33.0 | 12771 | 5.6912 | 0.2237 |
|
| 85 |
+
| 5.739 | 34.0 | 13158 | 5.6904 | 0.2239 |
|
| 86 |
+
| 5.7339 | 35.0 | 13545 | 5.6896 | 0.2239 |
|
| 87 |
+
| 5.731 | 36.0 | 13932 | 5.6891 | 0.2240 |
|
| 88 |
+
| 5.7285 | 37.0 | 14319 | 5.6885 | 0.2240 |
|
| 89 |
+
| 5.724 | 38.0 | 14706 | 5.6881 | 0.2241 |
|
| 90 |
+
| 5.7241 | 39.0 | 15093 | 5.6874 | 0.2242 |
|
| 91 |
+
| 5.724 | 40.0 | 15480 | 5.6871 | 0.2244 |
|
| 92 |
+
| 5.7199 | 41.0 | 15867 | 5.6867 | 0.2245 |
|
| 93 |
+
| 5.7212 | 42.0 | 16254 | 5.6863 | 0.2244 |
|
| 94 |
+
| 5.7209 | 43.0 | 16641 | 5.6859 | 0.2245 |
|
| 95 |
+
| 5.7169 | 44.0 | 17028 | 5.6857 | 0.2245 |
|
| 96 |
+
| 5.7185 | 45.0 | 17415 | 5.6856 | 0.2247 |
|
| 97 |
+
| 5.7165 | 46.0 | 17802 | 5.6853 | 0.2247 |
|
| 98 |
+
| 5.7202 | 47.0 | 18189 | 5.6851 | 0.2248 |
|
| 99 |
+
| 5.7183 | 48.0 | 18576 | 5.6850 | 0.2248 |
|
| 100 |
+
| 5.7179 | 49.0 | 18963 | 5.6849 | 0.2248 |
|
| 101 |
+
| 5.7164 | 50.0 | 19350 | 5.6849 | 0.2249 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.38.0.dev0
|
| 107 |
+
- Pytorch 2.2.0
|
| 108 |
+
- Datasets 2.16.1
|
| 109 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.22485166746232013,
|
| 4 |
+
"eval_loss": 5.6849164962768555,
|
| 5 |
+
"eval_runtime": 6.5658,
|
| 6 |
+
"eval_samples": 43,
|
| 7 |
+
"eval_samples_per_second": 6.549,
|
| 8 |
+
"eval_steps_per_second": 0.914,
|
| 9 |
+
"perplexity": 294.3932610910054,
|
| 10 |
+
"train_loss": 5.863803761405847,
|
| 11 |
+
"train_runtime": 11632.7911,
|
| 12 |
+
"train_samples": 387,
|
| 13 |
+
"train_samples_per_second": 1.663,
|
| 14 |
+
"train_steps_per_second": 1.663
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nferruz/ProtGPT2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 1280,
|
| 16 |
+
"n_head": 20,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 36,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.38.0.dev0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.22485166746232013,
|
| 4 |
+
"eval_loss": 5.6849164962768555,
|
| 5 |
+
"eval_runtime": 6.5658,
|
| 6 |
+
"eval_samples": 43,
|
| 7 |
+
"eval_samples_per_second": 6.549,
|
| 8 |
+
"eval_steps_per_second": 0.914,
|
| 9 |
+
"perplexity": 294.3932610910054
|
| 10 |
+
}
|
events.out.tfevents.1710909878.lambda-a6000.1646203.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f21fd3b4098488c9e6f6eba6541c77368fcbb25e861942dbce18f7f551031539
|
| 3 |
+
size 29053
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.38.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac9e4c22b506b240bbf2c0b5778878e8f88171b8bcbb3f588b4ffecc3fa0b3e8
|
| 3 |
+
size 3096165928
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": true,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 18 |
+
"unk_token": "<|endoftext|>"
|
| 19 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 5.863803761405847,
|
| 4 |
+
"train_runtime": 11632.7911,
|
| 5 |
+
"train_samples": 387,
|
| 6 |
+
"train_samples_per_second": 1.663,
|
| 7 |
+
"train_steps_per_second": 1.663
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,780 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 5.6849164962768555,
|
| 3 |
+
"best_model_checkpoint": "output_sol_3/checkpoint-19350",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 19350,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 9.8e-07,
|
| 14 |
+
"loss": 6.7291,
|
| 15 |
+
"step": 387
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.1754074882356953,
|
| 20 |
+
"eval_loss": 6.441868782043457,
|
| 21 |
+
"eval_runtime": 6.5661,
|
| 22 |
+
"eval_samples_per_second": 6.549,
|
| 23 |
+
"eval_steps_per_second": 0.914,
|
| 24 |
+
"step": 387
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 9.6e-07,
|
| 29 |
+
"loss": 6.5666,
|
| 30 |
+
"step": 774
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.18468253426993111,
|
| 35 |
+
"eval_loss": 6.273727893829346,
|
| 36 |
+
"eval_runtime": 6.5673,
|
| 37 |
+
"eval_samples_per_second": 6.548,
|
| 38 |
+
"eval_steps_per_second": 0.914,
|
| 39 |
+
"step": 774
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"learning_rate": 9.399999999999999e-07,
|
| 44 |
+
"loss": 6.4479,
|
| 45 |
+
"step": 1161
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"eval_accuracy": 0.1917524835754393,
|
| 50 |
+
"eval_loss": 6.139554023742676,
|
| 51 |
+
"eval_runtime": 6.5469,
|
| 52 |
+
"eval_samples_per_second": 6.568,
|
| 53 |
+
"eval_steps_per_second": 0.916,
|
| 54 |
+
"step": 1161
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.0,
|
| 58 |
+
"learning_rate": 9.2e-07,
|
| 59 |
+
"loss": 6.3439,
|
| 60 |
+
"step": 1548
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"eval_accuracy": 0.1973675236991066,
|
| 65 |
+
"eval_loss": 6.035923480987549,
|
| 66 |
+
"eval_runtime": 6.5514,
|
| 67 |
+
"eval_samples_per_second": 6.563,
|
| 68 |
+
"eval_steps_per_second": 0.916,
|
| 69 |
+
"step": 1548
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"learning_rate": 9e-07,
|
| 74 |
+
"loss": 6.2577,
|
| 75 |
+
"step": 1935
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_accuracy": 0.20305076269067268,
|
| 80 |
+
"eval_loss": 5.931780815124512,
|
| 81 |
+
"eval_runtime": 6.5535,
|
| 82 |
+
"eval_samples_per_second": 6.561,
|
| 83 |
+
"eval_steps_per_second": 0.916,
|
| 84 |
+
"step": 1935
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"learning_rate": 8.799999999999999e-07,
|
| 89 |
+
"loss": 6.172,
|
| 90 |
+
"step": 2322
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.0,
|
| 94 |
+
"eval_accuracy": 0.20827934256291344,
|
| 95 |
+
"eval_loss": 5.861706256866455,
|
| 96 |
+
"eval_runtime": 6.5488,
|
| 97 |
+
"eval_samples_per_second": 6.566,
|
| 98 |
+
"eval_steps_per_second": 0.916,
|
| 99 |
+
"step": 2322
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.0,
|
| 103 |
+
"learning_rate": 8.599999999999999e-07,
|
| 104 |
+
"loss": 6.0943,
|
| 105 |
+
"step": 2709
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"eval_accuracy": 0.21153015526608926,
|
| 110 |
+
"eval_loss": 5.821234226226807,
|
| 111 |
+
"eval_runtime": 6.551,
|
| 112 |
+
"eval_samples_per_second": 6.564,
|
| 113 |
+
"eval_steps_per_second": 0.916,
|
| 114 |
+
"step": 2709
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"learning_rate": 8.399999999999999e-07,
|
| 119 |
+
"loss": 6.0318,
|
| 120 |
+
"step": 3096
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.0,
|
| 124 |
+
"eval_accuracy": 0.21318966105162654,
|
| 125 |
+
"eval_loss": 5.7982587814331055,
|
| 126 |
+
"eval_runtime": 6.5518,
|
| 127 |
+
"eval_samples_per_second": 6.563,
|
| 128 |
+
"eval_steps_per_second": 0.916,
|
| 129 |
+
"step": 3096
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.0,
|
| 133 |
+
"learning_rate": 8.199999999999999e-07,
|
| 134 |
+
"loss": 5.9812,
|
| 135 |
+
"step": 3483
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 9.0,
|
| 139 |
+
"eval_accuracy": 0.21512196230875902,
|
| 140 |
+
"eval_loss": 5.781760215759277,
|
| 141 |
+
"eval_runtime": 6.5556,
|
| 142 |
+
"eval_samples_per_second": 6.559,
|
| 143 |
+
"eval_steps_per_second": 0.915,
|
| 144 |
+
"step": 3483
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 10.0,
|
| 148 |
+
"learning_rate": 8e-07,
|
| 149 |
+
"loss": 5.9436,
|
| 150 |
+
"step": 3870
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 10.0,
|
| 154 |
+
"eval_accuracy": 0.21634954193093728,
|
| 155 |
+
"eval_loss": 5.767332553863525,
|
| 156 |
+
"eval_runtime": 6.5502,
|
| 157 |
+
"eval_samples_per_second": 6.565,
|
| 158 |
+
"eval_steps_per_second": 0.916,
|
| 159 |
+
"step": 3870
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.0,
|
| 163 |
+
"learning_rate": 7.799999999999999e-07,
|
| 164 |
+
"loss": 5.9144,
|
| 165 |
+
"step": 4257
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 11.0,
|
| 169 |
+
"eval_accuracy": 0.21714519538975652,
|
| 170 |
+
"eval_loss": 5.75629997253418,
|
| 171 |
+
"eval_runtime": 6.5503,
|
| 172 |
+
"eval_samples_per_second": 6.565,
|
| 173 |
+
"eval_steps_per_second": 0.916,
|
| 174 |
+
"step": 4257
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 12.0,
|
| 178 |
+
"learning_rate": 7.599999999999999e-07,
|
| 179 |
+
"loss": 5.8923,
|
| 180 |
+
"step": 4644
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.0,
|
| 184 |
+
"eval_accuracy": 0.21846370683579985,
|
| 185 |
+
"eval_loss": 5.745217323303223,
|
| 186 |
+
"eval_runtime": 6.557,
|
| 187 |
+
"eval_samples_per_second": 6.558,
|
| 188 |
+
"eval_steps_per_second": 0.915,
|
| 189 |
+
"step": 4644
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 13.0,
|
| 193 |
+
"learning_rate": 7.4e-07,
|
| 194 |
+
"loss": 5.8723,
|
| 195 |
+
"step": 5031
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 13.0,
|
| 199 |
+
"eval_accuracy": 0.2190092977789902,
|
| 200 |
+
"eval_loss": 5.73870325088501,
|
| 201 |
+
"eval_runtime": 6.5631,
|
| 202 |
+
"eval_samples_per_second": 6.552,
|
| 203 |
+
"eval_steps_per_second": 0.914,
|
| 204 |
+
"step": 5031
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 14.0,
|
| 208 |
+
"learning_rate": 7.2e-07,
|
| 209 |
+
"loss": 5.8549,
|
| 210 |
+
"step": 5418
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 14.0,
|
| 214 |
+
"eval_accuracy": 0.21930482620655165,
|
| 215 |
+
"eval_loss": 5.7320146560668945,
|
| 216 |
+
"eval_runtime": 6.5518,
|
| 217 |
+
"eval_samples_per_second": 6.563,
|
| 218 |
+
"eval_steps_per_second": 0.916,
|
| 219 |
+
"step": 5418
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 15.0,
|
| 223 |
+
"learning_rate": 7e-07,
|
| 224 |
+
"loss": 5.8427,
|
| 225 |
+
"step": 5805
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 15.0,
|
| 229 |
+
"eval_accuracy": 0.219850417149742,
|
| 230 |
+
"eval_loss": 5.725865364074707,
|
| 231 |
+
"eval_runtime": 6.5565,
|
| 232 |
+
"eval_samples_per_second": 6.558,
|
| 233 |
+
"eval_steps_per_second": 0.915,
|
| 234 |
+
"step": 5805
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 16.0,
|
| 238 |
+
"learning_rate": 6.800000000000001e-07,
|
| 239 |
+
"loss": 5.8306,
|
| 240 |
+
"step": 6192
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 16.0,
|
| 244 |
+
"eval_accuracy": 0.220282343313101,
|
| 245 |
+
"eval_loss": 5.721892833709717,
|
| 246 |
+
"eval_runtime": 6.5537,
|
| 247 |
+
"eval_samples_per_second": 6.561,
|
| 248 |
+
"eval_steps_per_second": 0.916,
|
| 249 |
+
"step": 6192
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 17.0,
|
| 253 |
+
"learning_rate": 6.6e-07,
|
| 254 |
+
"loss": 5.8176,
|
| 255 |
+
"step": 6579
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 17.0,
|
| 259 |
+
"eval_accuracy": 0.22041874104889858,
|
| 260 |
+
"eval_loss": 5.718621253967285,
|
| 261 |
+
"eval_runtime": 6.5536,
|
| 262 |
+
"eval_samples_per_second": 6.561,
|
| 263 |
+
"eval_steps_per_second": 0.916,
|
| 264 |
+
"step": 6579
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 18.0,
|
| 268 |
+
"learning_rate": 6.4e-07,
|
| 269 |
+
"loss": 5.8129,
|
| 270 |
+
"step": 6966
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 18.0,
|
| 274 |
+
"eval_accuracy": 0.22062333765259498,
|
| 275 |
+
"eval_loss": 5.7153215408325195,
|
| 276 |
+
"eval_runtime": 6.5502,
|
| 277 |
+
"eval_samples_per_second": 6.565,
|
| 278 |
+
"eval_steps_per_second": 0.916,
|
| 279 |
+
"step": 6966
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 19.0,
|
| 283 |
+
"learning_rate": 6.2e-07,
|
| 284 |
+
"loss": 5.8055,
|
| 285 |
+
"step": 7353
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 19.0,
|
| 289 |
+
"eval_accuracy": 0.22112346268385277,
|
| 290 |
+
"eval_loss": 5.7118988037109375,
|
| 291 |
+
"eval_runtime": 6.5485,
|
| 292 |
+
"eval_samples_per_second": 6.566,
|
| 293 |
+
"eval_steps_per_second": 0.916,
|
| 294 |
+
"step": 7353
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 20.0,
|
| 298 |
+
"learning_rate": 6e-07,
|
| 299 |
+
"loss": 5.7954,
|
| 300 |
+
"step": 7740
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 20.0,
|
| 304 |
+
"eval_accuracy": 0.2213053263315829,
|
| 305 |
+
"eval_loss": 5.709749698638916,
|
| 306 |
+
"eval_runtime": 6.5556,
|
| 307 |
+
"eval_samples_per_second": 6.559,
|
| 308 |
+
"eval_steps_per_second": 0.915,
|
| 309 |
+
"step": 7740
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 21.0,
|
| 313 |
+
"learning_rate": 5.8e-07,
|
| 314 |
+
"loss": 5.7906,
|
| 315 |
+
"step": 8127
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 21.0,
|
| 319 |
+
"eval_accuracy": 0.22185091727477324,
|
| 320 |
+
"eval_loss": 5.70782995223999,
|
| 321 |
+
"eval_runtime": 6.5498,
|
| 322 |
+
"eval_samples_per_second": 6.565,
|
| 323 |
+
"eval_steps_per_second": 0.916,
|
| 324 |
+
"step": 8127
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 22.0,
|
| 328 |
+
"learning_rate": 5.6e-07,
|
| 329 |
+
"loss": 5.7834,
|
| 330 |
+
"step": 8514
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 22.0,
|
| 334 |
+
"eval_accuracy": 0.2221237127463684,
|
| 335 |
+
"eval_loss": 5.706095218658447,
|
| 336 |
+
"eval_runtime": 6.556,
|
| 337 |
+
"eval_samples_per_second": 6.559,
|
| 338 |
+
"eval_steps_per_second": 0.915,
|
| 339 |
+
"step": 8514
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 23.0,
|
| 343 |
+
"learning_rate": 5.4e-07,
|
| 344 |
+
"loss": 5.7779,
|
| 345 |
+
"step": 8901
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 23.0,
|
| 349 |
+
"eval_accuracy": 0.22235104230603106,
|
| 350 |
+
"eval_loss": 5.704181671142578,
|
| 351 |
+
"eval_runtime": 6.5374,
|
| 352 |
+
"eval_samples_per_second": 6.578,
|
| 353 |
+
"eval_steps_per_second": 0.918,
|
| 354 |
+
"step": 8901
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 24.0,
|
| 358 |
+
"learning_rate": 5.2e-07,
|
| 359 |
+
"loss": 5.7718,
|
| 360 |
+
"step": 9288
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 24.0,
|
| 364 |
+
"eval_accuracy": 0.22264657073359248,
|
| 365 |
+
"eval_loss": 5.70188570022583,
|
| 366 |
+
"eval_runtime": 6.5489,
|
| 367 |
+
"eval_samples_per_second": 6.566,
|
| 368 |
+
"eval_steps_per_second": 0.916,
|
| 369 |
+
"step": 9288
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 25.0,
|
| 373 |
+
"learning_rate": 5e-07,
|
| 374 |
+
"loss": 5.7664,
|
| 375 |
+
"step": 9675
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 25.0,
|
| 379 |
+
"eval_accuracy": 0.2231466957648503,
|
| 380 |
+
"eval_loss": 5.700209617614746,
|
| 381 |
+
"eval_runtime": 6.5447,
|
| 382 |
+
"eval_samples_per_second": 6.57,
|
| 383 |
+
"eval_steps_per_second": 0.917,
|
| 384 |
+
"step": 9675
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 26.0,
|
| 388 |
+
"learning_rate": 4.8e-07,
|
| 389 |
+
"loss": 5.7616,
|
| 390 |
+
"step": 10062
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 26.0,
|
| 394 |
+
"eval_accuracy": 0.22335129236854667,
|
| 395 |
+
"eval_loss": 5.698944091796875,
|
| 396 |
+
"eval_runtime": 6.5389,
|
| 397 |
+
"eval_samples_per_second": 6.576,
|
| 398 |
+
"eval_steps_per_second": 0.918,
|
| 399 |
+
"step": 10062
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 27.0,
|
| 403 |
+
"learning_rate": 4.6e-07,
|
| 404 |
+
"loss": 5.7596,
|
| 405 |
+
"step": 10449
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 27.0,
|
| 409 |
+
"eval_accuracy": 0.22341949123644547,
|
| 410 |
+
"eval_loss": 5.697207927703857,
|
| 411 |
+
"eval_runtime": 6.5507,
|
| 412 |
+
"eval_samples_per_second": 6.564,
|
| 413 |
+
"eval_steps_per_second": 0.916,
|
| 414 |
+
"step": 10449
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 28.0,
|
| 418 |
+
"learning_rate": 4.3999999999999997e-07,
|
| 419 |
+
"loss": 5.7553,
|
| 420 |
+
"step": 10836
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 28.0,
|
| 424 |
+
"eval_accuracy": 0.2236013548841756,
|
| 425 |
+
"eval_loss": 5.696023464202881,
|
| 426 |
+
"eval_runtime": 6.5473,
|
| 427 |
+
"eval_samples_per_second": 6.568,
|
| 428 |
+
"eval_steps_per_second": 0.916,
|
| 429 |
+
"step": 10836
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 29.0,
|
| 433 |
+
"learning_rate": 4.1999999999999995e-07,
|
| 434 |
+
"loss": 5.7525,
|
| 435 |
+
"step": 11223
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 29.0,
|
| 439 |
+
"eval_accuracy": 0.2235331560162768,
|
| 440 |
+
"eval_loss": 5.694847583770752,
|
| 441 |
+
"eval_runtime": 6.543,
|
| 442 |
+
"eval_samples_per_second": 6.572,
|
| 443 |
+
"eval_steps_per_second": 0.917,
|
| 444 |
+
"step": 11223
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 30.0,
|
| 448 |
+
"learning_rate": 4e-07,
|
| 449 |
+
"loss": 5.7488,
|
| 450 |
+
"step": 11610
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 30.0,
|
| 454 |
+
"eval_accuracy": 0.22355588897224307,
|
| 455 |
+
"eval_loss": 5.693871974945068,
|
| 456 |
+
"eval_runtime": 6.5401,
|
| 457 |
+
"eval_samples_per_second": 6.575,
|
| 458 |
+
"eval_steps_per_second": 0.917,
|
| 459 |
+
"step": 11610
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 31.0,
|
| 463 |
+
"learning_rate": 3.7999999999999996e-07,
|
| 464 |
+
"loss": 5.7445,
|
| 465 |
+
"step": 11997
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 31.0,
|
| 469 |
+
"eval_accuracy": 0.2236695537520744,
|
| 470 |
+
"eval_loss": 5.693030834197998,
|
| 471 |
+
"eval_runtime": 6.5461,
|
| 472 |
+
"eval_samples_per_second": 6.569,
|
| 473 |
+
"eval_steps_per_second": 0.917,
|
| 474 |
+
"step": 11997
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 32.0,
|
| 478 |
+
"learning_rate": 3.6e-07,
|
| 479 |
+
"loss": 5.7409,
|
| 480 |
+
"step": 12384
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 32.0,
|
| 484 |
+
"eval_accuracy": 0.22373775261997317,
|
| 485 |
+
"eval_loss": 5.691904544830322,
|
| 486 |
+
"eval_runtime": 6.5492,
|
| 487 |
+
"eval_samples_per_second": 6.566,
|
| 488 |
+
"eval_steps_per_second": 0.916,
|
| 489 |
+
"step": 12384
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 33.0,
|
| 493 |
+
"learning_rate": 3.4000000000000003e-07,
|
| 494 |
+
"loss": 5.7389,
|
| 495 |
+
"step": 12771
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 33.0,
|
| 499 |
+
"eval_accuracy": 0.22373775261997317,
|
| 500 |
+
"eval_loss": 5.691229343414307,
|
| 501 |
+
"eval_runtime": 6.5417,
|
| 502 |
+
"eval_samples_per_second": 6.573,
|
| 503 |
+
"eval_steps_per_second": 0.917,
|
| 504 |
+
"step": 12771
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 34.0,
|
| 508 |
+
"learning_rate": 3.2e-07,
|
| 509 |
+
"loss": 5.739,
|
| 510 |
+
"step": 13158
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 34.0,
|
| 514 |
+
"eval_accuracy": 0.2238514173998045,
|
| 515 |
+
"eval_loss": 5.690367221832275,
|
| 516 |
+
"eval_runtime": 6.5476,
|
| 517 |
+
"eval_samples_per_second": 6.567,
|
| 518 |
+
"eval_steps_per_second": 0.916,
|
| 519 |
+
"step": 13158
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 35.0,
|
| 523 |
+
"learning_rate": 3e-07,
|
| 524 |
+
"loss": 5.7339,
|
| 525 |
+
"step": 13545
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 35.0,
|
| 529 |
+
"eval_accuracy": 0.22387415035577077,
|
| 530 |
+
"eval_loss": 5.689624309539795,
|
| 531 |
+
"eval_runtime": 6.5489,
|
| 532 |
+
"eval_samples_per_second": 6.566,
|
| 533 |
+
"eval_steps_per_second": 0.916,
|
| 534 |
+
"step": 13545
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 36.0,
|
| 538 |
+
"learning_rate": 2.8e-07,
|
| 539 |
+
"loss": 5.731,
|
| 540 |
+
"step": 13932
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 36.0,
|
| 544 |
+
"eval_accuracy": 0.22401054809156834,
|
| 545 |
+
"eval_loss": 5.6890740394592285,
|
| 546 |
+
"eval_runtime": 6.5461,
|
| 547 |
+
"eval_samples_per_second": 6.569,
|
| 548 |
+
"eval_steps_per_second": 0.917,
|
| 549 |
+
"step": 13932
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 37.0,
|
| 553 |
+
"learning_rate": 2.6e-07,
|
| 554 |
+
"loss": 5.7285,
|
| 555 |
+
"step": 14319
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 37.0,
|
| 559 |
+
"eval_accuracy": 0.22403328104753462,
|
| 560 |
+
"eval_loss": 5.688539505004883,
|
| 561 |
+
"eval_runtime": 6.5471,
|
| 562 |
+
"eval_samples_per_second": 6.568,
|
| 563 |
+
"eval_steps_per_second": 0.916,
|
| 564 |
+
"step": 14319
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 38.0,
|
| 568 |
+
"learning_rate": 2.4e-07,
|
| 569 |
+
"loss": 5.724,
|
| 570 |
+
"step": 14706
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 38.0,
|
| 574 |
+
"eval_accuracy": 0.22410147991543342,
|
| 575 |
+
"eval_loss": 5.6880621910095215,
|
| 576 |
+
"eval_runtime": 6.5514,
|
| 577 |
+
"eval_samples_per_second": 6.564,
|
| 578 |
+
"eval_steps_per_second": 0.916,
|
| 579 |
+
"step": 14706
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 39.0,
|
| 583 |
+
"learning_rate": 2.1999999999999998e-07,
|
| 584 |
+
"loss": 5.7241,
|
| 585 |
+
"step": 15093
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 39.0,
|
| 589 |
+
"eval_accuracy": 0.2242151446952647,
|
| 590 |
+
"eval_loss": 5.687371253967285,
|
| 591 |
+
"eval_runtime": 6.5505,
|
| 592 |
+
"eval_samples_per_second": 6.564,
|
| 593 |
+
"eval_steps_per_second": 0.916,
|
| 594 |
+
"step": 15093
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 40.0,
|
| 598 |
+
"learning_rate": 2e-07,
|
| 599 |
+
"loss": 5.724,
|
| 600 |
+
"step": 15480
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 40.0,
|
| 604 |
+
"eval_accuracy": 0.22444247425492736,
|
| 605 |
+
"eval_loss": 5.687062740325928,
|
| 606 |
+
"eval_runtime": 6.5565,
|
| 607 |
+
"eval_samples_per_second": 6.558,
|
| 608 |
+
"eval_steps_per_second": 0.915,
|
| 609 |
+
"step": 15480
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 41.0,
|
| 613 |
+
"learning_rate": 1.8e-07,
|
| 614 |
+
"loss": 5.7199,
|
| 615 |
+
"step": 15867
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 41.0,
|
| 619 |
+
"eval_accuracy": 0.22446520721089364,
|
| 620 |
+
"eval_loss": 5.686655521392822,
|
| 621 |
+
"eval_runtime": 6.5445,
|
| 622 |
+
"eval_samples_per_second": 6.57,
|
| 623 |
+
"eval_steps_per_second": 0.917,
|
| 624 |
+
"step": 15867
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 42.0,
|
| 628 |
+
"learning_rate": 1.6e-07,
|
| 629 |
+
"loss": 5.7212,
|
| 630 |
+
"step": 16254
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 42.0,
|
| 634 |
+
"eval_accuracy": 0.2244197412989611,
|
| 635 |
+
"eval_loss": 5.686285495758057,
|
| 636 |
+
"eval_runtime": 6.5455,
|
| 637 |
+
"eval_samples_per_second": 6.569,
|
| 638 |
+
"eval_steps_per_second": 0.917,
|
| 639 |
+
"step": 16254
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 43.0,
|
| 643 |
+
"learning_rate": 1.4e-07,
|
| 644 |
+
"loss": 5.7209,
|
| 645 |
+
"step": 16641
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 43.0,
|
| 649 |
+
"eval_accuracy": 0.22451067312282616,
|
| 650 |
+
"eval_loss": 5.685915946960449,
|
| 651 |
+
"eval_runtime": 6.5461,
|
| 652 |
+
"eval_samples_per_second": 6.569,
|
| 653 |
+
"eval_steps_per_second": 0.917,
|
| 654 |
+
"step": 16641
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 44.0,
|
| 658 |
+
"learning_rate": 1.2e-07,
|
| 659 |
+
"loss": 5.7169,
|
| 660 |
+
"step": 17028
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 44.0,
|
| 664 |
+
"eval_accuracy": 0.22451067312282616,
|
| 665 |
+
"eval_loss": 5.685729503631592,
|
| 666 |
+
"eval_runtime": 6.5499,
|
| 667 |
+
"eval_samples_per_second": 6.565,
|
| 668 |
+
"eval_steps_per_second": 0.916,
|
| 669 |
+
"step": 17028
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 45.0,
|
| 673 |
+
"learning_rate": 1e-07,
|
| 674 |
+
"loss": 5.7185,
|
| 675 |
+
"step": 17415
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 45.0,
|
| 679 |
+
"eval_accuracy": 0.22469253677055628,
|
| 680 |
+
"eval_loss": 5.68557071685791,
|
| 681 |
+
"eval_runtime": 6.5567,
|
| 682 |
+
"eval_samples_per_second": 6.558,
|
| 683 |
+
"eval_steps_per_second": 0.915,
|
| 684 |
+
"step": 17415
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 46.0,
|
| 688 |
+
"learning_rate": 8e-08,
|
| 689 |
+
"loss": 5.7165,
|
| 690 |
+
"step": 17802
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 46.0,
|
| 694 |
+
"eval_accuracy": 0.22469253677055628,
|
| 695 |
+
"eval_loss": 5.685311317443848,
|
| 696 |
+
"eval_runtime": 6.5512,
|
| 697 |
+
"eval_samples_per_second": 6.564,
|
| 698 |
+
"eval_steps_per_second": 0.916,
|
| 699 |
+
"step": 17802
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 47.0,
|
| 703 |
+
"learning_rate": 6e-08,
|
| 704 |
+
"loss": 5.7202,
|
| 705 |
+
"step": 18189
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 47.0,
|
| 709 |
+
"eval_accuracy": 0.2248062015503876,
|
| 710 |
+
"eval_loss": 5.685103416442871,
|
| 711 |
+
"eval_runtime": 6.5558,
|
| 712 |
+
"eval_samples_per_second": 6.559,
|
| 713 |
+
"eval_steps_per_second": 0.915,
|
| 714 |
+
"step": 18189
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 48.0,
|
| 718 |
+
"learning_rate": 4e-08,
|
| 719 |
+
"loss": 5.7183,
|
| 720 |
+
"step": 18576
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 48.0,
|
| 724 |
+
"eval_accuracy": 0.22482893450635386,
|
| 725 |
+
"eval_loss": 5.684987545013428,
|
| 726 |
+
"eval_runtime": 6.5482,
|
| 727 |
+
"eval_samples_per_second": 6.567,
|
| 728 |
+
"eval_steps_per_second": 0.916,
|
| 729 |
+
"step": 18576
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 49.0,
|
| 733 |
+
"learning_rate": 2e-08,
|
| 734 |
+
"loss": 5.7179,
|
| 735 |
+
"step": 18963
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 49.0,
|
| 739 |
+
"eval_accuracy": 0.22482893450635386,
|
| 740 |
+
"eval_loss": 5.684926509857178,
|
| 741 |
+
"eval_runtime": 6.5478,
|
| 742 |
+
"eval_samples_per_second": 6.567,
|
| 743 |
+
"eval_steps_per_second": 0.916,
|
| 744 |
+
"step": 18963
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 50.0,
|
| 748 |
+
"learning_rate": 0.0,
|
| 749 |
+
"loss": 5.7164,
|
| 750 |
+
"step": 19350
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 50.0,
|
| 754 |
+
"eval_accuracy": 0.22485166746232013,
|
| 755 |
+
"eval_loss": 5.6849164962768555,
|
| 756 |
+
"eval_runtime": 6.5482,
|
| 757 |
+
"eval_samples_per_second": 6.567,
|
| 758 |
+
"eval_steps_per_second": 0.916,
|
| 759 |
+
"step": 19350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 50.0,
|
| 763 |
+
"step": 19350,
|
| 764 |
+
"total_flos": 8.421798445056e+16,
|
| 765 |
+
"train_loss": 5.863803761405847,
|
| 766 |
+
"train_runtime": 11632.7911,
|
| 767 |
+
"train_samples_per_second": 1.663,
|
| 768 |
+
"train_steps_per_second": 1.663
|
| 769 |
+
}
|
| 770 |
+
],
|
| 771 |
+
"logging_steps": 500,
|
| 772 |
+
"max_steps": 19350,
|
| 773 |
+
"num_input_tokens_seen": 0,
|
| 774 |
+
"num_train_epochs": 50,
|
| 775 |
+
"save_steps": 500,
|
| 776 |
+
"total_flos": 8.421798445056e+16,
|
| 777 |
+
"train_batch_size": 1,
|
| 778 |
+
"trial_name": null,
|
| 779 |
+
"trial_params": null
|
| 780 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40e3c0ce1b7b0467c8a2568c8b373138ebb09b1bd3ff12279897a7d041b7e039
|
| 3 |
+
size 4728
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|