Upload with huggingface_hub
Browse files- README.md +100 -0
- all_results.json +15 -0
- checkpoint-13650/config.json +30 -0
- checkpoint-13650/optimizer.pt +3 -0
- checkpoint-13650/pytorch_model.bin +3 -0
- checkpoint-13650/rng_state_0.pth +3 -0
- checkpoint-13650/rng_state_1.pth +3 -0
- checkpoint-13650/scaler.pt +3 -0
- checkpoint-13650/scheduler.pt +3 -0
- checkpoint-13650/special_tokens_map.json +7 -0
- checkpoint-13650/tokenizer_config.json +6 -0
- checkpoint-13650/trainer_state.json +493 -0
- checkpoint-13650/training_args.bin +3 -0
- checkpoint-13650/vocab.txt +33 -0
- checkpoint-14040/config.json +30 -0
- checkpoint-14040/optimizer.pt +3 -0
- checkpoint-14040/pytorch_model.bin +3 -0
- checkpoint-14040/rng_state_0.pth +3 -0
- checkpoint-14040/rng_state_1.pth +3 -0
- checkpoint-14040/scaler.pt +3 -0
- checkpoint-14040/scheduler.pt +3 -0
- checkpoint-14040/special_tokens_map.json +7 -0
- checkpoint-14040/tokenizer_config.json +6 -0
- checkpoint-14040/trainer_state.json +508 -0
- checkpoint-14040/training_args.bin +3 -0
- checkpoint-14040/vocab.txt +33 -0
- config.json +30 -0
- eval_results.json +10 -0
- pytorch_model.bin +3 -0
- runs/Apr26_12-00-12_srvgpu/1682510421.8712294/events.out.tfevents.1682510421.srvgpu.3077809.1 +3 -0
- runs/Apr26_12-00-12_srvgpu/events.out.tfevents.1682510421.srvgpu.3077809.0 +3 -0
- runs/Apr26_12-00-12_srvgpu/events.out.tfevents.1682524144.srvgpu.3077809.2 +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +6 -0
- train_results.json +8 -0
- trainer_state.json +517 -0
- training_args.bin +3 -0
- vocab.txt +33 -0
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: output_AAVESM2_650M_v1
|
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 |
+
# output_AAVESM2_650M_v1
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [facebook/esm2_t33_650M_UR50D](https://huggingface.co/facebook/esm2_t33_650M_UR50D) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3707
|
20 |
+
- Accuracy: 0.8905
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 1e-05
|
40 |
+
- train_batch_size: 1
|
41 |
+
- eval_batch_size: 1
|
42 |
+
- seed: 42
|
43 |
+
- distributed_type: multi-GPU
|
44 |
+
- num_devices: 2
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 8
|
47 |
+
- total_eval_batch_size: 2
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 36.0
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
57 |
+
| No log | 1.0 | 390 | 1.3347 | 0.5993 |
|
58 |
+
| 1.5408 | 2.0 | 780 | 1.0699 | 0.6796 |
|
59 |
+
| 1.1283 | 3.0 | 1170 | 0.8751 | 0.7373 |
|
60 |
+
| 0.9078 | 4.0 | 1560 | 0.7534 | 0.7711 |
|
61 |
+
| 0.9078 | 5.0 | 1950 | 0.6711 | 0.8022 |
|
62 |
+
| 0.7705 | 6.0 | 2340 | 0.6078 | 0.8169 |
|
63 |
+
| 0.6863 | 7.0 | 2730 | 0.5668 | 0.8318 |
|
64 |
+
| 0.6277 | 8.0 | 3120 | 0.5461 | 0.8386 |
|
65 |
+
| 0.5863 | 9.0 | 3510 | 0.5143 | 0.8514 |
|
66 |
+
| 0.5863 | 10.0 | 3900 | 0.4992 | 0.8522 |
|
67 |
+
| 0.5564 | 11.0 | 4290 | 0.4940 | 0.8533 |
|
68 |
+
| 0.5199 | 12.0 | 4680 | 0.4727 | 0.8633 |
|
69 |
+
| 0.5025 | 13.0 | 5070 | 0.4586 | 0.8638 |
|
70 |
+
| 0.5025 | 14.0 | 5460 | 0.4549 | 0.8673 |
|
71 |
+
| 0.4814 | 15.0 | 5850 | 0.4442 | 0.8698 |
|
72 |
+
| 0.4746 | 16.0 | 6240 | 0.4306 | 0.8750 |
|
73 |
+
| 0.4527 | 17.0 | 6630 | 0.4291 | 0.8742 |
|
74 |
+
| 0.4382 | 18.0 | 7020 | 0.4213 | 0.8751 |
|
75 |
+
| 0.4382 | 19.0 | 7410 | 0.4193 | 0.8751 |
|
76 |
+
| 0.4328 | 20.0 | 7800 | 0.4143 | 0.8760 |
|
77 |
+
| 0.4191 | 21.0 | 8190 | 0.4071 | 0.8836 |
|
78 |
+
| 0.4106 | 22.0 | 8580 | 0.3980 | 0.8819 |
|
79 |
+
| 0.4106 | 23.0 | 8970 | 0.3987 | 0.8822 |
|
80 |
+
| 0.4037 | 24.0 | 9360 | 0.4027 | 0.8819 |
|
81 |
+
| 0.3893 | 25.0 | 9750 | 0.3868 | 0.8893 |
|
82 |
+
| 0.3991 | 26.0 | 10140 | 0.3882 | 0.8846 |
|
83 |
+
| 0.3786 | 27.0 | 10530 | 0.3939 | 0.8859 |
|
84 |
+
| 0.3786 | 28.0 | 10920 | 0.3959 | 0.8848 |
|
85 |
+
| 0.38 | 29.0 | 11310 | 0.3950 | 0.8850 |
|
86 |
+
| 0.3764 | 30.0 | 11700 | 0.3783 | 0.8893 |
|
87 |
+
| 0.3708 | 31.0 | 12090 | 0.3799 | 0.8891 |
|
88 |
+
| 0.3708 | 32.0 | 12480 | 0.3915 | 0.8867 |
|
89 |
+
| 0.3656 | 33.0 | 12870 | 0.3780 | 0.8903 |
|
90 |
+
| 0.3617 | 34.0 | 13260 | 0.3805 | 0.8874 |
|
91 |
+
| 0.361 | 35.0 | 13650 | 0.3776 | 0.8920 |
|
92 |
+
| 0.3595 | 36.0 | 14040 | 0.3712 | 0.8888 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.26.1
|
98 |
+
- Pytorch 1.13.1+cu117
|
99 |
+
- Datasets 2.9.0
|
100 |
+
- Tokenizers 0.13.2
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 36.0,
|
3 |
+
"eval_accuracy": 0.8905318152693578,
|
4 |
+
"eval_loss": 0.3707260489463806,
|
5 |
+
"eval_runtime": 5.8253,
|
6 |
+
"eval_samples": 171,
|
7 |
+
"eval_samples_per_second": 29.355,
|
8 |
+
"eval_steps_per_second": 14.763,
|
9 |
+
"perplexity": 1.448786122531838,
|
10 |
+
"train_loss": 0.5379996796958467,
|
11 |
+
"train_runtime": 13714.1823,
|
12 |
+
"train_samples": 3120,
|
13 |
+
"train_samples_per_second": 8.19,
|
14 |
+
"train_steps_per_second": 1.024
|
15 |
+
}
|
checkpoint-13650/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/esm2_t33_650M_UR50D",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 1280,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 32,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 33,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"token_dropout": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.26.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_list": null,
|
29 |
+
"vocab_size": 33
|
30 |
+
}
|
checkpoint-13650/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47906c5bdfd21f3c1def1fff088870f34a611e9072ba44f92f8945901a5ed84b
|
3 |
+
size 5219162243
|
checkpoint-13650/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72ea0df553d4c0d01a0dcb8c038c6a302c744033b0b2326f16875b92199db24f
|
3 |
+
size 2609524829
|
checkpoint-13650/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a90d7656620c27b5f0a3cc9bf82045add3872287b52b0e4d7a821d9cbc93563
|
3 |
+
size 14583
|
checkpoint-13650/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc77f294d04ff7f88102ed8463d22301bd8233d77afd2d90cad8d2babaf94fb6
|
3 |
+
size 14583
|
checkpoint-13650/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea5476f54bdb6a23fa5620ad0532c467c086b58ae9fe7eafc8ff2d62a37b1b89
|
3 |
+
size 557
|
checkpoint-13650/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55022d9dcbbef78486034062d55f0f0896988b0f3ec0147598f1ed7a8e3734d6
|
3 |
+
size 627
|
checkpoint-13650/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "<cls>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-13650/tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"name_or_path": "facebook/esm2_t33_650M_UR50D",
|
4 |
+
"special_tokens_map_file": "/home/avuhong/.cache/huggingface/hub/models--facebook--esm2_t33_650M_UR50D/snapshots/08e4846e537177426273712802403f7ba8261b6c/special_tokens_map.json",
|
5 |
+
"tokenizer_class": "EsmTokenizer"
|
6 |
+
}
|
checkpoint-13650/trainer_state.json
ADDED
@@ -0,0 +1,493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 35.0,
|
5 |
+
"global_step": 13650,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.5992906078421846,
|
13 |
+
"eval_loss": 1.33469557762146,
|
14 |
+
"eval_runtime": 5.8169,
|
15 |
+
"eval_samples_per_second": 29.397,
|
16 |
+
"eval_steps_per_second": 14.785,
|
17 |
+
"step": 390
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.28,
|
21 |
+
"learning_rate": 9.644586894586896e-06,
|
22 |
+
"loss": 1.5408,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_accuracy": 0.6796235478653008,
|
28 |
+
"eval_loss": 1.0698518753051758,
|
29 |
+
"eval_runtime": 5.8146,
|
30 |
+
"eval_samples_per_second": 29.409,
|
31 |
+
"eval_steps_per_second": 14.79,
|
32 |
+
"step": 780
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.56,
|
36 |
+
"learning_rate": 9.28917378917379e-06,
|
37 |
+
"loss": 1.1283,
|
38 |
+
"step": 1000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_accuracy": 0.7372856151482106,
|
43 |
+
"eval_loss": 0.8751375675201416,
|
44 |
+
"eval_runtime": 5.8077,
|
45 |
+
"eval_samples_per_second": 29.444,
|
46 |
+
"eval_steps_per_second": 14.808,
|
47 |
+
"step": 1170
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.85,
|
51 |
+
"learning_rate": 8.933048433048434e-06,
|
52 |
+
"loss": 0.9078,
|
53 |
+
"step": 1500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"eval_accuracy": 0.7711176956331666,
|
58 |
+
"eval_loss": 0.7534294128417969,
|
59 |
+
"eval_runtime": 5.8229,
|
60 |
+
"eval_samples_per_second": 29.367,
|
61 |
+
"eval_steps_per_second": 14.769,
|
62 |
+
"step": 1560
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 5.0,
|
66 |
+
"eval_accuracy": 0.802166420482521,
|
67 |
+
"eval_loss": 0.6710610389709473,
|
68 |
+
"eval_runtime": 5.6976,
|
69 |
+
"eval_samples_per_second": 30.013,
|
70 |
+
"eval_steps_per_second": 15.094,
|
71 |
+
"step": 1950
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 5.13,
|
75 |
+
"learning_rate": 8.576923076923077e-06,
|
76 |
+
"loss": 0.7705,
|
77 |
+
"step": 2000
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 6.0,
|
81 |
+
"eval_accuracy": 0.8168786692759296,
|
82 |
+
"eval_loss": 0.6077755689620972,
|
83 |
+
"eval_runtime": 5.8114,
|
84 |
+
"eval_samples_per_second": 29.425,
|
85 |
+
"eval_steps_per_second": 14.798,
|
86 |
+
"step": 2340
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 6.41,
|
90 |
+
"learning_rate": 8.220797720797722e-06,
|
91 |
+
"loss": 0.6863,
|
92 |
+
"step": 2500
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"eval_accuracy": 0.831802051431627,
|
97 |
+
"eval_loss": 0.5667673945426941,
|
98 |
+
"eval_runtime": 5.8128,
|
99 |
+
"eval_samples_per_second": 29.418,
|
100 |
+
"eval_steps_per_second": 14.795,
|
101 |
+
"step": 2730
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 7.69,
|
105 |
+
"learning_rate": 7.864672364672366e-06,
|
106 |
+
"loss": 0.6277,
|
107 |
+
"step": 3000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.8386034912718204,
|
112 |
+
"eval_loss": 0.546131432056427,
|
113 |
+
"eval_runtime": 5.8073,
|
114 |
+
"eval_samples_per_second": 29.446,
|
115 |
+
"eval_steps_per_second": 14.809,
|
116 |
+
"step": 3120
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.97,
|
120 |
+
"learning_rate": 7.508547008547009e-06,
|
121 |
+
"loss": 0.5863,
|
122 |
+
"step": 3500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 9.0,
|
126 |
+
"eval_accuracy": 0.8513571943310113,
|
127 |
+
"eval_loss": 0.5142761468887329,
|
128 |
+
"eval_runtime": 5.8058,
|
129 |
+
"eval_samples_per_second": 29.453,
|
130 |
+
"eval_steps_per_second": 14.813,
|
131 |
+
"step": 3510
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 10.0,
|
135 |
+
"eval_accuracy": 0.8522174818930449,
|
136 |
+
"eval_loss": 0.49920225143432617,
|
137 |
+
"eval_runtime": 5.8205,
|
138 |
+
"eval_samples_per_second": 29.379,
|
139 |
+
"eval_steps_per_second": 14.775,
|
140 |
+
"step": 3900
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.26,
|
144 |
+
"learning_rate": 7.152421652421653e-06,
|
145 |
+
"loss": 0.5564,
|
146 |
+
"step": 4000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 11.0,
|
150 |
+
"eval_accuracy": 0.8533209429717304,
|
151 |
+
"eval_loss": 0.49400192499160767,
|
152 |
+
"eval_runtime": 5.8142,
|
153 |
+
"eval_samples_per_second": 29.411,
|
154 |
+
"eval_steps_per_second": 14.791,
|
155 |
+
"step": 4290
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 11.54,
|
159 |
+
"learning_rate": 6.796296296296296e-06,
|
160 |
+
"loss": 0.5199,
|
161 |
+
"step": 4500
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 12.0,
|
165 |
+
"eval_accuracy": 0.8632922665875019,
|
166 |
+
"eval_loss": 0.4726846218109131,
|
167 |
+
"eval_runtime": 5.8155,
|
168 |
+
"eval_samples_per_second": 29.404,
|
169 |
+
"eval_steps_per_second": 14.788,
|
170 |
+
"step": 4680
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 12.82,
|
174 |
+
"learning_rate": 6.440170940170941e-06,
|
175 |
+
"loss": 0.5025,
|
176 |
+
"step": 5000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 13.0,
|
180 |
+
"eval_accuracy": 0.8637540927527733,
|
181 |
+
"eval_loss": 0.4585917592048645,
|
182 |
+
"eval_runtime": 5.8153,
|
183 |
+
"eval_samples_per_second": 29.405,
|
184 |
+
"eval_steps_per_second": 14.789,
|
185 |
+
"step": 5070
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 14.0,
|
189 |
+
"eval_accuracy": 0.8673048600883653,
|
190 |
+
"eval_loss": 0.45485442876815796,
|
191 |
+
"eval_runtime": 5.8178,
|
192 |
+
"eval_samples_per_second": 29.393,
|
193 |
+
"eval_steps_per_second": 14.782,
|
194 |
+
"step": 5460
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 14.1,
|
198 |
+
"learning_rate": 6.084045584045585e-06,
|
199 |
+
"loss": 0.4814,
|
200 |
+
"step": 5500
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 15.0,
|
204 |
+
"eval_accuracy": 0.8698035411108416,
|
205 |
+
"eval_loss": 0.44424179196357727,
|
206 |
+
"eval_runtime": 5.7973,
|
207 |
+
"eval_samples_per_second": 29.496,
|
208 |
+
"eval_steps_per_second": 14.834,
|
209 |
+
"step": 5850
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 15.38,
|
213 |
+
"learning_rate": 5.727920227920228e-06,
|
214 |
+
"loss": 0.4746,
|
215 |
+
"step": 6000
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 16.0,
|
219 |
+
"eval_accuracy": 0.8749573607523999,
|
220 |
+
"eval_loss": 0.43056586384773254,
|
221 |
+
"eval_runtime": 5.6925,
|
222 |
+
"eval_samples_per_second": 30.04,
|
223 |
+
"eval_steps_per_second": 15.108,
|
224 |
+
"step": 6240
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 16.67,
|
228 |
+
"learning_rate": 5.371794871794872e-06,
|
229 |
+
"loss": 0.4527,
|
230 |
+
"step": 6500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 17.0,
|
234 |
+
"eval_accuracy": 0.874227107665129,
|
235 |
+
"eval_loss": 0.42905324697494507,
|
236 |
+
"eval_runtime": 5.8566,
|
237 |
+
"eval_samples_per_second": 29.198,
|
238 |
+
"eval_steps_per_second": 14.684,
|
239 |
+
"step": 6630
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 17.95,
|
243 |
+
"learning_rate": 5.016381766381767e-06,
|
244 |
+
"loss": 0.4382,
|
245 |
+
"step": 7000
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 18.0,
|
249 |
+
"eval_accuracy": 0.8751032706419789,
|
250 |
+
"eval_loss": 0.4213222861289978,
|
251 |
+
"eval_runtime": 5.8093,
|
252 |
+
"eval_samples_per_second": 29.435,
|
253 |
+
"eval_steps_per_second": 14.804,
|
254 |
+
"step": 7020
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 19.0,
|
258 |
+
"eval_accuracy": 0.8751214299591995,
|
259 |
+
"eval_loss": 0.41926833987236023,
|
260 |
+
"eval_runtime": 5.8022,
|
261 |
+
"eval_samples_per_second": 29.472,
|
262 |
+
"eval_steps_per_second": 14.822,
|
263 |
+
"step": 7410
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 19.23,
|
267 |
+
"learning_rate": 4.6602564102564106e-06,
|
268 |
+
"loss": 0.4328,
|
269 |
+
"step": 7500
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 20.0,
|
273 |
+
"eval_accuracy": 0.8759944995580002,
|
274 |
+
"eval_loss": 0.41431769728660583,
|
275 |
+
"eval_runtime": 5.8137,
|
276 |
+
"eval_samples_per_second": 29.413,
|
277 |
+
"eval_steps_per_second": 14.793,
|
278 |
+
"step": 7800
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 20.51,
|
282 |
+
"learning_rate": 4.304131054131054e-06,
|
283 |
+
"loss": 0.4191,
|
284 |
+
"step": 8000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 21.0,
|
288 |
+
"eval_accuracy": 0.8835775987576434,
|
289 |
+
"eval_loss": 0.4071265459060669,
|
290 |
+
"eval_runtime": 5.8164,
|
291 |
+
"eval_samples_per_second": 29.4,
|
292 |
+
"eval_steps_per_second": 14.786,
|
293 |
+
"step": 8190
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 21.79,
|
297 |
+
"learning_rate": 3.948717948717949e-06,
|
298 |
+
"loss": 0.4106,
|
299 |
+
"step": 8500
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 22.0,
|
303 |
+
"eval_accuracy": 0.881939052795031,
|
304 |
+
"eval_loss": 0.3980366587638855,
|
305 |
+
"eval_runtime": 5.875,
|
306 |
+
"eval_samples_per_second": 29.106,
|
307 |
+
"eval_steps_per_second": 14.638,
|
308 |
+
"step": 8580
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 23.0,
|
312 |
+
"eval_accuracy": 0.8821786026625207,
|
313 |
+
"eval_loss": 0.39872363209724426,
|
314 |
+
"eval_runtime": 5.8105,
|
315 |
+
"eval_samples_per_second": 29.43,
|
316 |
+
"eval_steps_per_second": 14.801,
|
317 |
+
"step": 8970
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 23.08,
|
321 |
+
"learning_rate": 3.592592592592593e-06,
|
322 |
+
"loss": 0.4037,
|
323 |
+
"step": 9000
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 24.0,
|
327 |
+
"eval_accuracy": 0.8819395993222366,
|
328 |
+
"eval_loss": 0.40265128016471863,
|
329 |
+
"eval_runtime": 5.8012,
|
330 |
+
"eval_samples_per_second": 29.477,
|
331 |
+
"eval_steps_per_second": 14.824,
|
332 |
+
"step": 9360
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 24.36,
|
336 |
+
"learning_rate": 3.2364672364672365e-06,
|
337 |
+
"loss": 0.3893,
|
338 |
+
"step": 9500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 25.0,
|
342 |
+
"eval_accuracy": 0.8892501819946614,
|
343 |
+
"eval_loss": 0.3867790400981903,
|
344 |
+
"eval_runtime": 5.8209,
|
345 |
+
"eval_samples_per_second": 29.377,
|
346 |
+
"eval_steps_per_second": 14.774,
|
347 |
+
"step": 9750
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 25.64,
|
351 |
+
"learning_rate": 2.8803418803418804e-06,
|
352 |
+
"loss": 0.3991,
|
353 |
+
"step": 10000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 26.0,
|
357 |
+
"eval_accuracy": 0.8846003326484688,
|
358 |
+
"eval_loss": 0.3882477581501007,
|
359 |
+
"eval_runtime": 5.8184,
|
360 |
+
"eval_samples_per_second": 29.389,
|
361 |
+
"eval_steps_per_second": 14.781,
|
362 |
+
"step": 10140
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 26.92,
|
366 |
+
"learning_rate": 2.5242165242165246e-06,
|
367 |
+
"loss": 0.3786,
|
368 |
+
"step": 10500
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 27.0,
|
372 |
+
"eval_accuracy": 0.8858714334822964,
|
373 |
+
"eval_loss": 0.3939129710197449,
|
374 |
+
"eval_runtime": 5.8222,
|
375 |
+
"eval_samples_per_second": 29.37,
|
376 |
+
"eval_steps_per_second": 14.771,
|
377 |
+
"step": 10530
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 28.0,
|
381 |
+
"eval_accuracy": 0.8847989764283254,
|
382 |
+
"eval_loss": 0.39587706327438354,
|
383 |
+
"eval_runtime": 5.8063,
|
384 |
+
"eval_samples_per_second": 29.451,
|
385 |
+
"eval_steps_per_second": 14.812,
|
386 |
+
"step": 10920
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 28.21,
|
390 |
+
"learning_rate": 2.168803418803419e-06,
|
391 |
+
"loss": 0.38,
|
392 |
+
"step": 11000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 29.0,
|
396 |
+
"eval_accuracy": 0.8849687976020835,
|
397 |
+
"eval_loss": 0.3949810862541199,
|
398 |
+
"eval_runtime": 5.8138,
|
399 |
+
"eval_samples_per_second": 29.413,
|
400 |
+
"eval_steps_per_second": 14.792,
|
401 |
+
"step": 11310
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 29.49,
|
405 |
+
"learning_rate": 1.8126780626780629e-06,
|
406 |
+
"loss": 0.3764,
|
407 |
+
"step": 11500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 30.0,
|
411 |
+
"eval_accuracy": 0.8893153879792042,
|
412 |
+
"eval_loss": 0.3783101439476013,
|
413 |
+
"eval_runtime": 5.8039,
|
414 |
+
"eval_samples_per_second": 29.463,
|
415 |
+
"eval_steps_per_second": 14.818,
|
416 |
+
"step": 11700
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 30.77,
|
420 |
+
"learning_rate": 1.4565527065527065e-06,
|
421 |
+
"loss": 0.3708,
|
422 |
+
"step": 12000
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 31.0,
|
426 |
+
"eval_accuracy": 0.8890792500856626,
|
427 |
+
"eval_loss": 0.3798995912075043,
|
428 |
+
"eval_runtime": 5.7021,
|
429 |
+
"eval_samples_per_second": 29.989,
|
430 |
+
"eval_steps_per_second": 15.082,
|
431 |
+
"step": 12090
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 32.0,
|
435 |
+
"eval_accuracy": 0.8867172306495527,
|
436 |
+
"eval_loss": 0.39150363206863403,
|
437 |
+
"eval_runtime": 5.8791,
|
438 |
+
"eval_samples_per_second": 29.086,
|
439 |
+
"eval_steps_per_second": 14.628,
|
440 |
+
"step": 12480
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 32.05,
|
444 |
+
"learning_rate": 1.1004273504273506e-06,
|
445 |
+
"loss": 0.3656,
|
446 |
+
"step": 12500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 33.0,
|
450 |
+
"eval_accuracy": 0.8902530694061639,
|
451 |
+
"eval_loss": 0.3780055344104767,
|
452 |
+
"eval_runtime": 5.8784,
|
453 |
+
"eval_samples_per_second": 29.09,
|
454 |
+
"eval_steps_per_second": 14.63,
|
455 |
+
"step": 12870
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 33.33,
|
459 |
+
"learning_rate": 7.443019943019944e-07,
|
460 |
+
"loss": 0.3617,
|
461 |
+
"step": 13000
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 34.0,
|
465 |
+
"eval_accuracy": 0.8873723487824038,
|
466 |
+
"eval_loss": 0.38049712777137756,
|
467 |
+
"eval_runtime": 5.8779,
|
468 |
+
"eval_samples_per_second": 29.092,
|
469 |
+
"eval_steps_per_second": 14.631,
|
470 |
+
"step": 13260
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 34.62,
|
474 |
+
"learning_rate": 3.8817663817663825e-07,
|
475 |
+
"loss": 0.361,
|
476 |
+
"step": 13500
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 35.0,
|
480 |
+
"eval_accuracy": 0.8919778767559101,
|
481 |
+
"eval_loss": 0.3775971233844757,
|
482 |
+
"eval_runtime": 5.8063,
|
483 |
+
"eval_samples_per_second": 29.451,
|
484 |
+
"eval_steps_per_second": 14.812,
|
485 |
+
"step": 13650
|
486 |
+
}
|
487 |
+
],
|
488 |
+
"max_steps": 14040,
|
489 |
+
"num_train_epochs": 36,
|
490 |
+
"total_flos": 3.412286906774323e+17,
|
491 |
+
"trial_name": null,
|
492 |
+
"trial_params": null
|
493 |
+
}
|
checkpoint-13650/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62f0cca5fa131673e262469dc4be8f9f3fb2048d33c3baf0cda18865991b15f
|
3 |
+
size 3579
|
checkpoint-13650/vocab.txt
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<cls>
|
2 |
+
<pad>
|
3 |
+
<eos>
|
4 |
+
<unk>
|
5 |
+
L
|
6 |
+
A
|
7 |
+
G
|
8 |
+
V
|
9 |
+
S
|
10 |
+
E
|
11 |
+
R
|
12 |
+
T
|
13 |
+
I
|
14 |
+
D
|
15 |
+
P
|
16 |
+
K
|
17 |
+
Q
|
18 |
+
N
|
19 |
+
F
|
20 |
+
Y
|
21 |
+
M
|
22 |
+
H
|
23 |
+
W
|
24 |
+
C
|
25 |
+
X
|
26 |
+
B
|
27 |
+
U
|
28 |
+
Z
|
29 |
+
O
|
30 |
+
.
|
31 |
+
-
|
32 |
+
<null_1>
|
33 |
+
<mask>
|
checkpoint-14040/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/esm2_t33_650M_UR50D",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 1280,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 32,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 33,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"token_dropout": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.26.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_list": null,
|
29 |
+
"vocab_size": 33
|
30 |
+
}
|
checkpoint-14040/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74539603eff61ec2403f3fa04875cce68c8f7c190776b90de13c53f01dff31e2
|
3 |
+
size 5219162243
|
checkpoint-14040/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1f288729c792c2f6a5e683c9206c7652333c3fbc7bdae07606ec895c87b5a03
|
3 |
+
size 2609524829
|
checkpoint-14040/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:537ade68a6593552161018bf2051b9024127d35978be29ce8334872cdba5fa4a
|
3 |
+
size 14583
|
checkpoint-14040/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15dbfdcf2c44f910e294ab5ba8b338eddffa03ec039d7237837bd239d5a739c1
|
3 |
+
size 14583
|
checkpoint-14040/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d74e9e7f7e2d62262547d85c561b50718c1cb2c1ab608d095515ea413ac7b069
|
3 |
+
size 557
|
checkpoint-14040/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:275a4bdd257f5c2b2e9c249486eb13b8c14a0a886a1a497af5c19b0dfe32cfd8
|
3 |
+
size 627
|
checkpoint-14040/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "<cls>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-14040/tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"name_or_path": "facebook/esm2_t33_650M_UR50D",
|
4 |
+
"special_tokens_map_file": "/home/avuhong/.cache/huggingface/hub/models--facebook--esm2_t33_650M_UR50D/snapshots/08e4846e537177426273712802403f7ba8261b6c/special_tokens_map.json",
|
5 |
+
"tokenizer_class": "EsmTokenizer"
|
6 |
+
}
|
checkpoint-14040/trainer_state.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 36.0,
|
5 |
+
"global_step": 14040,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.5992906078421846,
|
13 |
+
"eval_loss": 1.33469557762146,
|
14 |
+
"eval_runtime": 5.8169,
|
15 |
+
"eval_samples_per_second": 29.397,
|
16 |
+
"eval_steps_per_second": 14.785,
|
17 |
+
"step": 390
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.28,
|
21 |
+
"learning_rate": 9.644586894586896e-06,
|
22 |
+
"loss": 1.5408,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_accuracy": 0.6796235478653008,
|
28 |
+
"eval_loss": 1.0698518753051758,
|
29 |
+
"eval_runtime": 5.8146,
|
30 |
+
"eval_samples_per_second": 29.409,
|
31 |
+
"eval_steps_per_second": 14.79,
|
32 |
+
"step": 780
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.56,
|
36 |
+
"learning_rate": 9.28917378917379e-06,
|
37 |
+
"loss": 1.1283,
|
38 |
+
"step": 1000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_accuracy": 0.7372856151482106,
|
43 |
+
"eval_loss": 0.8751375675201416,
|
44 |
+
"eval_runtime": 5.8077,
|
45 |
+
"eval_samples_per_second": 29.444,
|
46 |
+
"eval_steps_per_second": 14.808,
|
47 |
+
"step": 1170
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.85,
|
51 |
+
"learning_rate": 8.933048433048434e-06,
|
52 |
+
"loss": 0.9078,
|
53 |
+
"step": 1500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"eval_accuracy": 0.7711176956331666,
|
58 |
+
"eval_loss": 0.7534294128417969,
|
59 |
+
"eval_runtime": 5.8229,
|
60 |
+
"eval_samples_per_second": 29.367,
|
61 |
+
"eval_steps_per_second": 14.769,
|
62 |
+
"step": 1560
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 5.0,
|
66 |
+
"eval_accuracy": 0.802166420482521,
|
67 |
+
"eval_loss": 0.6710610389709473,
|
68 |
+
"eval_runtime": 5.6976,
|
69 |
+
"eval_samples_per_second": 30.013,
|
70 |
+
"eval_steps_per_second": 15.094,
|
71 |
+
"step": 1950
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 5.13,
|
75 |
+
"learning_rate": 8.576923076923077e-06,
|
76 |
+
"loss": 0.7705,
|
77 |
+
"step": 2000
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 6.0,
|
81 |
+
"eval_accuracy": 0.8168786692759296,
|
82 |
+
"eval_loss": 0.6077755689620972,
|
83 |
+
"eval_runtime": 5.8114,
|
84 |
+
"eval_samples_per_second": 29.425,
|
85 |
+
"eval_steps_per_second": 14.798,
|
86 |
+
"step": 2340
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 6.41,
|
90 |
+
"learning_rate": 8.220797720797722e-06,
|
91 |
+
"loss": 0.6863,
|
92 |
+
"step": 2500
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"eval_accuracy": 0.831802051431627,
|
97 |
+
"eval_loss": 0.5667673945426941,
|
98 |
+
"eval_runtime": 5.8128,
|
99 |
+
"eval_samples_per_second": 29.418,
|
100 |
+
"eval_steps_per_second": 14.795,
|
101 |
+
"step": 2730
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 7.69,
|
105 |
+
"learning_rate": 7.864672364672366e-06,
|
106 |
+
"loss": 0.6277,
|
107 |
+
"step": 3000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.8386034912718204,
|
112 |
+
"eval_loss": 0.546131432056427,
|
113 |
+
"eval_runtime": 5.8073,
|
114 |
+
"eval_samples_per_second": 29.446,
|
115 |
+
"eval_steps_per_second": 14.809,
|
116 |
+
"step": 3120
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.97,
|
120 |
+
"learning_rate": 7.508547008547009e-06,
|
121 |
+
"loss": 0.5863,
|
122 |
+
"step": 3500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 9.0,
|
126 |
+
"eval_accuracy": 0.8513571943310113,
|
127 |
+
"eval_loss": 0.5142761468887329,
|
128 |
+
"eval_runtime": 5.8058,
|
129 |
+
"eval_samples_per_second": 29.453,
|
130 |
+
"eval_steps_per_second": 14.813,
|
131 |
+
"step": 3510
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 10.0,
|
135 |
+
"eval_accuracy": 0.8522174818930449,
|
136 |
+
"eval_loss": 0.49920225143432617,
|
137 |
+
"eval_runtime": 5.8205,
|
138 |
+
"eval_samples_per_second": 29.379,
|
139 |
+
"eval_steps_per_second": 14.775,
|
140 |
+
"step": 3900
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.26,
|
144 |
+
"learning_rate": 7.152421652421653e-06,
|
145 |
+
"loss": 0.5564,
|
146 |
+
"step": 4000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 11.0,
|
150 |
+
"eval_accuracy": 0.8533209429717304,
|
151 |
+
"eval_loss": 0.49400192499160767,
|
152 |
+
"eval_runtime": 5.8142,
|
153 |
+
"eval_samples_per_second": 29.411,
|
154 |
+
"eval_steps_per_second": 14.791,
|
155 |
+
"step": 4290
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 11.54,
|
159 |
+
"learning_rate": 6.796296296296296e-06,
|
160 |
+
"loss": 0.5199,
|
161 |
+
"step": 4500
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 12.0,
|
165 |
+
"eval_accuracy": 0.8632922665875019,
|
166 |
+
"eval_loss": 0.4726846218109131,
|
167 |
+
"eval_runtime": 5.8155,
|
168 |
+
"eval_samples_per_second": 29.404,
|
169 |
+
"eval_steps_per_second": 14.788,
|
170 |
+
"step": 4680
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 12.82,
|
174 |
+
"learning_rate": 6.440170940170941e-06,
|
175 |
+
"loss": 0.5025,
|
176 |
+
"step": 5000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 13.0,
|
180 |
+
"eval_accuracy": 0.8637540927527733,
|
181 |
+
"eval_loss": 0.4585917592048645,
|
182 |
+
"eval_runtime": 5.8153,
|
183 |
+
"eval_samples_per_second": 29.405,
|
184 |
+
"eval_steps_per_second": 14.789,
|
185 |
+
"step": 5070
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 14.0,
|
189 |
+
"eval_accuracy": 0.8673048600883653,
|
190 |
+
"eval_loss": 0.45485442876815796,
|
191 |
+
"eval_runtime": 5.8178,
|
192 |
+
"eval_samples_per_second": 29.393,
|
193 |
+
"eval_steps_per_second": 14.782,
|
194 |
+
"step": 5460
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 14.1,
|
198 |
+
"learning_rate": 6.084045584045585e-06,
|
199 |
+
"loss": 0.4814,
|
200 |
+
"step": 5500
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 15.0,
|
204 |
+
"eval_accuracy": 0.8698035411108416,
|
205 |
+
"eval_loss": 0.44424179196357727,
|
206 |
+
"eval_runtime": 5.7973,
|
207 |
+
"eval_samples_per_second": 29.496,
|
208 |
+
"eval_steps_per_second": 14.834,
|
209 |
+
"step": 5850
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 15.38,
|
213 |
+
"learning_rate": 5.727920227920228e-06,
|
214 |
+
"loss": 0.4746,
|
215 |
+
"step": 6000
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 16.0,
|
219 |
+
"eval_accuracy": 0.8749573607523999,
|
220 |
+
"eval_loss": 0.43056586384773254,
|
221 |
+
"eval_runtime": 5.6925,
|
222 |
+
"eval_samples_per_second": 30.04,
|
223 |
+
"eval_steps_per_second": 15.108,
|
224 |
+
"step": 6240
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 16.67,
|
228 |
+
"learning_rate": 5.371794871794872e-06,
|
229 |
+
"loss": 0.4527,
|
230 |
+
"step": 6500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 17.0,
|
234 |
+
"eval_accuracy": 0.874227107665129,
|
235 |
+
"eval_loss": 0.42905324697494507,
|
236 |
+
"eval_runtime": 5.8566,
|
237 |
+
"eval_samples_per_second": 29.198,
|
238 |
+
"eval_steps_per_second": 14.684,
|
239 |
+
"step": 6630
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 17.95,
|
243 |
+
"learning_rate": 5.016381766381767e-06,
|
244 |
+
"loss": 0.4382,
|
245 |
+
"step": 7000
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 18.0,
|
249 |
+
"eval_accuracy": 0.8751032706419789,
|
250 |
+
"eval_loss": 0.4213222861289978,
|
251 |
+
"eval_runtime": 5.8093,
|
252 |
+
"eval_samples_per_second": 29.435,
|
253 |
+
"eval_steps_per_second": 14.804,
|
254 |
+
"step": 7020
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 19.0,
|
258 |
+
"eval_accuracy": 0.8751214299591995,
|
259 |
+
"eval_loss": 0.41926833987236023,
|
260 |
+
"eval_runtime": 5.8022,
|
261 |
+
"eval_samples_per_second": 29.472,
|
262 |
+
"eval_steps_per_second": 14.822,
|
263 |
+
"step": 7410
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 19.23,
|
267 |
+
"learning_rate": 4.6602564102564106e-06,
|
268 |
+
"loss": 0.4328,
|
269 |
+
"step": 7500
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 20.0,
|
273 |
+
"eval_accuracy": 0.8759944995580002,
|
274 |
+
"eval_loss": 0.41431769728660583,
|
275 |
+
"eval_runtime": 5.8137,
|
276 |
+
"eval_samples_per_second": 29.413,
|
277 |
+
"eval_steps_per_second": 14.793,
|
278 |
+
"step": 7800
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 20.51,
|
282 |
+
"learning_rate": 4.304131054131054e-06,
|
283 |
+
"loss": 0.4191,
|
284 |
+
"step": 8000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 21.0,
|
288 |
+
"eval_accuracy": 0.8835775987576434,
|
289 |
+
"eval_loss": 0.4071265459060669,
|
290 |
+
"eval_runtime": 5.8164,
|
291 |
+
"eval_samples_per_second": 29.4,
|
292 |
+
"eval_steps_per_second": 14.786,
|
293 |
+
"step": 8190
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 21.79,
|
297 |
+
"learning_rate": 3.948717948717949e-06,
|
298 |
+
"loss": 0.4106,
|
299 |
+
"step": 8500
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 22.0,
|
303 |
+
"eval_accuracy": 0.881939052795031,
|
304 |
+
"eval_loss": 0.3980366587638855,
|
305 |
+
"eval_runtime": 5.875,
|
306 |
+
"eval_samples_per_second": 29.106,
|
307 |
+
"eval_steps_per_second": 14.638,
|
308 |
+
"step": 8580
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 23.0,
|
312 |
+
"eval_accuracy": 0.8821786026625207,
|
313 |
+
"eval_loss": 0.39872363209724426,
|
314 |
+
"eval_runtime": 5.8105,
|
315 |
+
"eval_samples_per_second": 29.43,
|
316 |
+
"eval_steps_per_second": 14.801,
|
317 |
+
"step": 8970
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 23.08,
|
321 |
+
"learning_rate": 3.592592592592593e-06,
|
322 |
+
"loss": 0.4037,
|
323 |
+
"step": 9000
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 24.0,
|
327 |
+
"eval_accuracy": 0.8819395993222366,
|
328 |
+
"eval_loss": 0.40265128016471863,
|
329 |
+
"eval_runtime": 5.8012,
|
330 |
+
"eval_samples_per_second": 29.477,
|
331 |
+
"eval_steps_per_second": 14.824,
|
332 |
+
"step": 9360
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 24.36,
|
336 |
+
"learning_rate": 3.2364672364672365e-06,
|
337 |
+
"loss": 0.3893,
|
338 |
+
"step": 9500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 25.0,
|
342 |
+
"eval_accuracy": 0.8892501819946614,
|
343 |
+
"eval_loss": 0.3867790400981903,
|
344 |
+
"eval_runtime": 5.8209,
|
345 |
+
"eval_samples_per_second": 29.377,
|
346 |
+
"eval_steps_per_second": 14.774,
|
347 |
+
"step": 9750
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 25.64,
|
351 |
+
"learning_rate": 2.8803418803418804e-06,
|
352 |
+
"loss": 0.3991,
|
353 |
+
"step": 10000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 26.0,
|
357 |
+
"eval_accuracy": 0.8846003326484688,
|
358 |
+
"eval_loss": 0.3882477581501007,
|
359 |
+
"eval_runtime": 5.8184,
|
360 |
+
"eval_samples_per_second": 29.389,
|
361 |
+
"eval_steps_per_second": 14.781,
|
362 |
+
"step": 10140
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 26.92,
|
366 |
+
"learning_rate": 2.5242165242165246e-06,
|
367 |
+
"loss": 0.3786,
|
368 |
+
"step": 10500
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 27.0,
|
372 |
+
"eval_accuracy": 0.8858714334822964,
|
373 |
+
"eval_loss": 0.3939129710197449,
|
374 |
+
"eval_runtime": 5.8222,
|
375 |
+
"eval_samples_per_second": 29.37,
|
376 |
+
"eval_steps_per_second": 14.771,
|
377 |
+
"step": 10530
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 28.0,
|
381 |
+
"eval_accuracy": 0.8847989764283254,
|
382 |
+
"eval_loss": 0.39587706327438354,
|
383 |
+
"eval_runtime": 5.8063,
|
384 |
+
"eval_samples_per_second": 29.451,
|
385 |
+
"eval_steps_per_second": 14.812,
|
386 |
+
"step": 10920
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 28.21,
|
390 |
+
"learning_rate": 2.168803418803419e-06,
|
391 |
+
"loss": 0.38,
|
392 |
+
"step": 11000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 29.0,
|
396 |
+
"eval_accuracy": 0.8849687976020835,
|
397 |
+
"eval_loss": 0.3949810862541199,
|
398 |
+
"eval_runtime": 5.8138,
|
399 |
+
"eval_samples_per_second": 29.413,
|
400 |
+
"eval_steps_per_second": 14.792,
|
401 |
+
"step": 11310
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 29.49,
|
405 |
+
"learning_rate": 1.8126780626780629e-06,
|
406 |
+
"loss": 0.3764,
|
407 |
+
"step": 11500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 30.0,
|
411 |
+
"eval_accuracy": 0.8893153879792042,
|
412 |
+
"eval_loss": 0.3783101439476013,
|
413 |
+
"eval_runtime": 5.8039,
|
414 |
+
"eval_samples_per_second": 29.463,
|
415 |
+
"eval_steps_per_second": 14.818,
|
416 |
+
"step": 11700
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 30.77,
|
420 |
+
"learning_rate": 1.4565527065527065e-06,
|
421 |
+
"loss": 0.3708,
|
422 |
+
"step": 12000
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 31.0,
|
426 |
+
"eval_accuracy": 0.8890792500856626,
|
427 |
+
"eval_loss": 0.3798995912075043,
|
428 |
+
"eval_runtime": 5.7021,
|
429 |
+
"eval_samples_per_second": 29.989,
|
430 |
+
"eval_steps_per_second": 15.082,
|
431 |
+
"step": 12090
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 32.0,
|
435 |
+
"eval_accuracy": 0.8867172306495527,
|
436 |
+
"eval_loss": 0.39150363206863403,
|
437 |
+
"eval_runtime": 5.8791,
|
438 |
+
"eval_samples_per_second": 29.086,
|
439 |
+
"eval_steps_per_second": 14.628,
|
440 |
+
"step": 12480
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 32.05,
|
444 |
+
"learning_rate": 1.1004273504273506e-06,
|
445 |
+
"loss": 0.3656,
|
446 |
+
"step": 12500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 33.0,
|
450 |
+
"eval_accuracy": 0.8902530694061639,
|
451 |
+
"eval_loss": 0.3780055344104767,
|
452 |
+
"eval_runtime": 5.8784,
|
453 |
+
"eval_samples_per_second": 29.09,
|
454 |
+
"eval_steps_per_second": 14.63,
|
455 |
+
"step": 12870
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 33.33,
|
459 |
+
"learning_rate": 7.443019943019944e-07,
|
460 |
+
"loss": 0.3617,
|
461 |
+
"step": 13000
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 34.0,
|
465 |
+
"eval_accuracy": 0.8873723487824038,
|
466 |
+
"eval_loss": 0.38049712777137756,
|
467 |
+
"eval_runtime": 5.8779,
|
468 |
+
"eval_samples_per_second": 29.092,
|
469 |
+
"eval_steps_per_second": 14.631,
|
470 |
+
"step": 13260
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 34.62,
|
474 |
+
"learning_rate": 3.8817663817663825e-07,
|
475 |
+
"loss": 0.361,
|
476 |
+
"step": 13500
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 35.0,
|
480 |
+
"eval_accuracy": 0.8919778767559101,
|
481 |
+
"eval_loss": 0.3775971233844757,
|
482 |
+
"eval_runtime": 5.8063,
|
483 |
+
"eval_samples_per_second": 29.451,
|
484 |
+
"eval_steps_per_second": 14.812,
|
485 |
+
"step": 13650
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 35.9,
|
489 |
+
"learning_rate": 3.205128205128205e-08,
|
490 |
+
"loss": 0.3595,
|
491 |
+
"step": 14000
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 36.0,
|
495 |
+
"eval_accuracy": 0.8888084202394747,
|
496 |
+
"eval_loss": 0.3711872100830078,
|
497 |
+
"eval_runtime": 5.8621,
|
498 |
+
"eval_samples_per_second": 29.171,
|
499 |
+
"eval_steps_per_second": 14.671,
|
500 |
+
"step": 14040
|
501 |
+
}
|
502 |
+
],
|
503 |
+
"max_steps": 14040,
|
504 |
+
"num_train_epochs": 36,
|
505 |
+
"total_flos": 3.509780816886497e+17,
|
506 |
+
"trial_name": null,
|
507 |
+
"trial_params": null
|
508 |
+
}
|
checkpoint-14040/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62f0cca5fa131673e262469dc4be8f9f3fb2048d33c3baf0cda18865991b15f
|
3 |
+
size 3579
|
checkpoint-14040/vocab.txt
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<cls>
|
2 |
+
<pad>
|
3 |
+
<eos>
|
4 |
+
<unk>
|
5 |
+
L
|
6 |
+
A
|
7 |
+
G
|
8 |
+
V
|
9 |
+
S
|
10 |
+
E
|
11 |
+
R
|
12 |
+
T
|
13 |
+
I
|
14 |
+
D
|
15 |
+
P
|
16 |
+
K
|
17 |
+
Q
|
18 |
+
N
|
19 |
+
F
|
20 |
+
Y
|
21 |
+
M
|
22 |
+
H
|
23 |
+
W
|
24 |
+
C
|
25 |
+
X
|
26 |
+
B
|
27 |
+
U
|
28 |
+
Z
|
29 |
+
O
|
30 |
+
.
|
31 |
+
-
|
32 |
+
<null_1>
|
33 |
+
<mask>
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/esm2_t33_650M_UR50D",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 1280,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 32,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 33,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"token_dropout": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.26.1",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_list": null,
|
29 |
+
"vocab_size": 33
|
30 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 36.0,
|
3 |
+
"eval_accuracy": 0.8905318152693578,
|
4 |
+
"eval_loss": 0.3707260489463806,
|
5 |
+
"eval_runtime": 5.8253,
|
6 |
+
"eval_samples": 171,
|
7 |
+
"eval_samples_per_second": 29.355,
|
8 |
+
"eval_steps_per_second": 14.763,
|
9 |
+
"perplexity": 1.448786122531838
|
10 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1f288729c792c2f6a5e683c9206c7652333c3fbc7bdae07606ec895c87b5a03
|
3 |
+
size 2609524829
|
runs/Apr26_12-00-12_srvgpu/1682510421.8712294/events.out.tfevents.1682510421.srvgpu.3077809.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91cf0149c9cdf0c5878eea2813b3bc0b71f0577fc423468e593e5588cee6aff3
|
3 |
+
size 5688
|
runs/Apr26_12-00-12_srvgpu/events.out.tfevents.1682510421.srvgpu.3077809.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4765859d81060ca2c805656dcd79226754725821890cc8b27f964a16487e0b6
|
3 |
+
size 20340
|
runs/Apr26_12-00-12_srvgpu/events.out.tfevents.1682524144.srvgpu.3077809.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dbeb63262a0cd34567d2e14c7ab41e7712ba596938b712994795fae04637926
|
3 |
+
size 363
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "<cls>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"name_or_path": "facebook/esm2_t33_650M_UR50D",
|
4 |
+
"special_tokens_map_file": "/home/avuhong/.cache/huggingface/hub/models--facebook--esm2_t33_650M_UR50D/snapshots/08e4846e537177426273712802403f7ba8261b6c/special_tokens_map.json",
|
5 |
+
"tokenizer_class": "EsmTokenizer"
|
6 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 36.0,
|
3 |
+
"train_loss": 0.5379996796958467,
|
4 |
+
"train_runtime": 13714.1823,
|
5 |
+
"train_samples": 3120,
|
6 |
+
"train_samples_per_second": 8.19,
|
7 |
+
"train_steps_per_second": 1.024
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,517 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 36.0,
|
5 |
+
"global_step": 14040,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.5992906078421846,
|
13 |
+
"eval_loss": 1.33469557762146,
|
14 |
+
"eval_runtime": 5.8169,
|
15 |
+
"eval_samples_per_second": 29.397,
|
16 |
+
"eval_steps_per_second": 14.785,
|
17 |
+
"step": 390
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.28,
|
21 |
+
"learning_rate": 9.644586894586896e-06,
|
22 |
+
"loss": 1.5408,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_accuracy": 0.6796235478653008,
|
28 |
+
"eval_loss": 1.0698518753051758,
|
29 |
+
"eval_runtime": 5.8146,
|
30 |
+
"eval_samples_per_second": 29.409,
|
31 |
+
"eval_steps_per_second": 14.79,
|
32 |
+
"step": 780
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.56,
|
36 |
+
"learning_rate": 9.28917378917379e-06,
|
37 |
+
"loss": 1.1283,
|
38 |
+
"step": 1000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"eval_accuracy": 0.7372856151482106,
|
43 |
+
"eval_loss": 0.8751375675201416,
|
44 |
+
"eval_runtime": 5.8077,
|
45 |
+
"eval_samples_per_second": 29.444,
|
46 |
+
"eval_steps_per_second": 14.808,
|
47 |
+
"step": 1170
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.85,
|
51 |
+
"learning_rate": 8.933048433048434e-06,
|
52 |
+
"loss": 0.9078,
|
53 |
+
"step": 1500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"eval_accuracy": 0.7711176956331666,
|
58 |
+
"eval_loss": 0.7534294128417969,
|
59 |
+
"eval_runtime": 5.8229,
|
60 |
+
"eval_samples_per_second": 29.367,
|
61 |
+
"eval_steps_per_second": 14.769,
|
62 |
+
"step": 1560
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 5.0,
|
66 |
+
"eval_accuracy": 0.802166420482521,
|
67 |
+
"eval_loss": 0.6710610389709473,
|
68 |
+
"eval_runtime": 5.6976,
|
69 |
+
"eval_samples_per_second": 30.013,
|
70 |
+
"eval_steps_per_second": 15.094,
|
71 |
+
"step": 1950
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 5.13,
|
75 |
+
"learning_rate": 8.576923076923077e-06,
|
76 |
+
"loss": 0.7705,
|
77 |
+
"step": 2000
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 6.0,
|
81 |
+
"eval_accuracy": 0.8168786692759296,
|
82 |
+
"eval_loss": 0.6077755689620972,
|
83 |
+
"eval_runtime": 5.8114,
|
84 |
+
"eval_samples_per_second": 29.425,
|
85 |
+
"eval_steps_per_second": 14.798,
|
86 |
+
"step": 2340
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 6.41,
|
90 |
+
"learning_rate": 8.220797720797722e-06,
|
91 |
+
"loss": 0.6863,
|
92 |
+
"step": 2500
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"eval_accuracy": 0.831802051431627,
|
97 |
+
"eval_loss": 0.5667673945426941,
|
98 |
+
"eval_runtime": 5.8128,
|
99 |
+
"eval_samples_per_second": 29.418,
|
100 |
+
"eval_steps_per_second": 14.795,
|
101 |
+
"step": 2730
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 7.69,
|
105 |
+
"learning_rate": 7.864672364672366e-06,
|
106 |
+
"loss": 0.6277,
|
107 |
+
"step": 3000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.8386034912718204,
|
112 |
+
"eval_loss": 0.546131432056427,
|
113 |
+
"eval_runtime": 5.8073,
|
114 |
+
"eval_samples_per_second": 29.446,
|
115 |
+
"eval_steps_per_second": 14.809,
|
116 |
+
"step": 3120
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.97,
|
120 |
+
"learning_rate": 7.508547008547009e-06,
|
121 |
+
"loss": 0.5863,
|
122 |
+
"step": 3500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 9.0,
|
126 |
+
"eval_accuracy": 0.8513571943310113,
|
127 |
+
"eval_loss": 0.5142761468887329,
|
128 |
+
"eval_runtime": 5.8058,
|
129 |
+
"eval_samples_per_second": 29.453,
|
130 |
+
"eval_steps_per_second": 14.813,
|
131 |
+
"step": 3510
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 10.0,
|
135 |
+
"eval_accuracy": 0.8522174818930449,
|
136 |
+
"eval_loss": 0.49920225143432617,
|
137 |
+
"eval_runtime": 5.8205,
|
138 |
+
"eval_samples_per_second": 29.379,
|
139 |
+
"eval_steps_per_second": 14.775,
|
140 |
+
"step": 3900
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.26,
|
144 |
+
"learning_rate": 7.152421652421653e-06,
|
145 |
+
"loss": 0.5564,
|
146 |
+
"step": 4000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 11.0,
|
150 |
+
"eval_accuracy": 0.8533209429717304,
|
151 |
+
"eval_loss": 0.49400192499160767,
|
152 |
+
"eval_runtime": 5.8142,
|
153 |
+
"eval_samples_per_second": 29.411,
|
154 |
+
"eval_steps_per_second": 14.791,
|
155 |
+
"step": 4290
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 11.54,
|
159 |
+
"learning_rate": 6.796296296296296e-06,
|
160 |
+
"loss": 0.5199,
|
161 |
+
"step": 4500
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 12.0,
|
165 |
+
"eval_accuracy": 0.8632922665875019,
|
166 |
+
"eval_loss": 0.4726846218109131,
|
167 |
+
"eval_runtime": 5.8155,
|
168 |
+
"eval_samples_per_second": 29.404,
|
169 |
+
"eval_steps_per_second": 14.788,
|
170 |
+
"step": 4680
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 12.82,
|
174 |
+
"learning_rate": 6.440170940170941e-06,
|
175 |
+
"loss": 0.5025,
|
176 |
+
"step": 5000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 13.0,
|
180 |
+
"eval_accuracy": 0.8637540927527733,
|
181 |
+
"eval_loss": 0.4585917592048645,
|
182 |
+
"eval_runtime": 5.8153,
|
183 |
+
"eval_samples_per_second": 29.405,
|
184 |
+
"eval_steps_per_second": 14.789,
|
185 |
+
"step": 5070
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 14.0,
|
189 |
+
"eval_accuracy": 0.8673048600883653,
|
190 |
+
"eval_loss": 0.45485442876815796,
|
191 |
+
"eval_runtime": 5.8178,
|
192 |
+
"eval_samples_per_second": 29.393,
|
193 |
+
"eval_steps_per_second": 14.782,
|
194 |
+
"step": 5460
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 14.1,
|
198 |
+
"learning_rate": 6.084045584045585e-06,
|
199 |
+
"loss": 0.4814,
|
200 |
+
"step": 5500
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 15.0,
|
204 |
+
"eval_accuracy": 0.8698035411108416,
|
205 |
+
"eval_loss": 0.44424179196357727,
|
206 |
+
"eval_runtime": 5.7973,
|
207 |
+
"eval_samples_per_second": 29.496,
|
208 |
+
"eval_steps_per_second": 14.834,
|
209 |
+
"step": 5850
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 15.38,
|
213 |
+
"learning_rate": 5.727920227920228e-06,
|
214 |
+
"loss": 0.4746,
|
215 |
+
"step": 6000
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 16.0,
|
219 |
+
"eval_accuracy": 0.8749573607523999,
|
220 |
+
"eval_loss": 0.43056586384773254,
|
221 |
+
"eval_runtime": 5.6925,
|
222 |
+
"eval_samples_per_second": 30.04,
|
223 |
+
"eval_steps_per_second": 15.108,
|
224 |
+
"step": 6240
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 16.67,
|
228 |
+
"learning_rate": 5.371794871794872e-06,
|
229 |
+
"loss": 0.4527,
|
230 |
+
"step": 6500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 17.0,
|
234 |
+
"eval_accuracy": 0.874227107665129,
|
235 |
+
"eval_loss": 0.42905324697494507,
|
236 |
+
"eval_runtime": 5.8566,
|
237 |
+
"eval_samples_per_second": 29.198,
|
238 |
+
"eval_steps_per_second": 14.684,
|
239 |
+
"step": 6630
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 17.95,
|
243 |
+
"learning_rate": 5.016381766381767e-06,
|
244 |
+
"loss": 0.4382,
|
245 |
+
"step": 7000
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 18.0,
|
249 |
+
"eval_accuracy": 0.8751032706419789,
|
250 |
+
"eval_loss": 0.4213222861289978,
|
251 |
+
"eval_runtime": 5.8093,
|
252 |
+
"eval_samples_per_second": 29.435,
|
253 |
+
"eval_steps_per_second": 14.804,
|
254 |
+
"step": 7020
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 19.0,
|
258 |
+
"eval_accuracy": 0.8751214299591995,
|
259 |
+
"eval_loss": 0.41926833987236023,
|
260 |
+
"eval_runtime": 5.8022,
|
261 |
+
"eval_samples_per_second": 29.472,
|
262 |
+
"eval_steps_per_second": 14.822,
|
263 |
+
"step": 7410
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 19.23,
|
267 |
+
"learning_rate": 4.6602564102564106e-06,
|
268 |
+
"loss": 0.4328,
|
269 |
+
"step": 7500
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 20.0,
|
273 |
+
"eval_accuracy": 0.8759944995580002,
|
274 |
+
"eval_loss": 0.41431769728660583,
|
275 |
+
"eval_runtime": 5.8137,
|
276 |
+
"eval_samples_per_second": 29.413,
|
277 |
+
"eval_steps_per_second": 14.793,
|
278 |
+
"step": 7800
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 20.51,
|
282 |
+
"learning_rate": 4.304131054131054e-06,
|
283 |
+
"loss": 0.4191,
|
284 |
+
"step": 8000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 21.0,
|
288 |
+
"eval_accuracy": 0.8835775987576434,
|
289 |
+
"eval_loss": 0.4071265459060669,
|
290 |
+
"eval_runtime": 5.8164,
|
291 |
+
"eval_samples_per_second": 29.4,
|
292 |
+
"eval_steps_per_second": 14.786,
|
293 |
+
"step": 8190
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 21.79,
|
297 |
+
"learning_rate": 3.948717948717949e-06,
|
298 |
+
"loss": 0.4106,
|
299 |
+
"step": 8500
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 22.0,
|
303 |
+
"eval_accuracy": 0.881939052795031,
|
304 |
+
"eval_loss": 0.3980366587638855,
|
305 |
+
"eval_runtime": 5.875,
|
306 |
+
"eval_samples_per_second": 29.106,
|
307 |
+
"eval_steps_per_second": 14.638,
|
308 |
+
"step": 8580
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 23.0,
|
312 |
+
"eval_accuracy": 0.8821786026625207,
|
313 |
+
"eval_loss": 0.39872363209724426,
|
314 |
+
"eval_runtime": 5.8105,
|
315 |
+
"eval_samples_per_second": 29.43,
|
316 |
+
"eval_steps_per_second": 14.801,
|
317 |
+
"step": 8970
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 23.08,
|
321 |
+
"learning_rate": 3.592592592592593e-06,
|
322 |
+
"loss": 0.4037,
|
323 |
+
"step": 9000
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 24.0,
|
327 |
+
"eval_accuracy": 0.8819395993222366,
|
328 |
+
"eval_loss": 0.40265128016471863,
|
329 |
+
"eval_runtime": 5.8012,
|
330 |
+
"eval_samples_per_second": 29.477,
|
331 |
+
"eval_steps_per_second": 14.824,
|
332 |
+
"step": 9360
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 24.36,
|
336 |
+
"learning_rate": 3.2364672364672365e-06,
|
337 |
+
"loss": 0.3893,
|
338 |
+
"step": 9500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 25.0,
|
342 |
+
"eval_accuracy": 0.8892501819946614,
|
343 |
+
"eval_loss": 0.3867790400981903,
|
344 |
+
"eval_runtime": 5.8209,
|
345 |
+
"eval_samples_per_second": 29.377,
|
346 |
+
"eval_steps_per_second": 14.774,
|
347 |
+
"step": 9750
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 25.64,
|
351 |
+
"learning_rate": 2.8803418803418804e-06,
|
352 |
+
"loss": 0.3991,
|
353 |
+
"step": 10000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 26.0,
|
357 |
+
"eval_accuracy": 0.8846003326484688,
|
358 |
+
"eval_loss": 0.3882477581501007,
|
359 |
+
"eval_runtime": 5.8184,
|
360 |
+
"eval_samples_per_second": 29.389,
|
361 |
+
"eval_steps_per_second": 14.781,
|
362 |
+
"step": 10140
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 26.92,
|
366 |
+
"learning_rate": 2.5242165242165246e-06,
|
367 |
+
"loss": 0.3786,
|
368 |
+
"step": 10500
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 27.0,
|
372 |
+
"eval_accuracy": 0.8858714334822964,
|
373 |
+
"eval_loss": 0.3939129710197449,
|
374 |
+
"eval_runtime": 5.8222,
|
375 |
+
"eval_samples_per_second": 29.37,
|
376 |
+
"eval_steps_per_second": 14.771,
|
377 |
+
"step": 10530
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 28.0,
|
381 |
+
"eval_accuracy": 0.8847989764283254,
|
382 |
+
"eval_loss": 0.39587706327438354,
|
383 |
+
"eval_runtime": 5.8063,
|
384 |
+
"eval_samples_per_second": 29.451,
|
385 |
+
"eval_steps_per_second": 14.812,
|
386 |
+
"step": 10920
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 28.21,
|
390 |
+
"learning_rate": 2.168803418803419e-06,
|
391 |
+
"loss": 0.38,
|
392 |
+
"step": 11000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 29.0,
|
396 |
+
"eval_accuracy": 0.8849687976020835,
|
397 |
+
"eval_loss": 0.3949810862541199,
|
398 |
+
"eval_runtime": 5.8138,
|
399 |
+
"eval_samples_per_second": 29.413,
|
400 |
+
"eval_steps_per_second": 14.792,
|
401 |
+
"step": 11310
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 29.49,
|
405 |
+
"learning_rate": 1.8126780626780629e-06,
|
406 |
+
"loss": 0.3764,
|
407 |
+
"step": 11500
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 30.0,
|
411 |
+
"eval_accuracy": 0.8893153879792042,
|
412 |
+
"eval_loss": 0.3783101439476013,
|
413 |
+
"eval_runtime": 5.8039,
|
414 |
+
"eval_samples_per_second": 29.463,
|
415 |
+
"eval_steps_per_second": 14.818,
|
416 |
+
"step": 11700
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 30.77,
|
420 |
+
"learning_rate": 1.4565527065527065e-06,
|
421 |
+
"loss": 0.3708,
|
422 |
+
"step": 12000
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 31.0,
|
426 |
+
"eval_accuracy": 0.8890792500856626,
|
427 |
+
"eval_loss": 0.3798995912075043,
|
428 |
+
"eval_runtime": 5.7021,
|
429 |
+
"eval_samples_per_second": 29.989,
|
430 |
+
"eval_steps_per_second": 15.082,
|
431 |
+
"step": 12090
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 32.0,
|
435 |
+
"eval_accuracy": 0.8867172306495527,
|
436 |
+
"eval_loss": 0.39150363206863403,
|
437 |
+
"eval_runtime": 5.8791,
|
438 |
+
"eval_samples_per_second": 29.086,
|
439 |
+
"eval_steps_per_second": 14.628,
|
440 |
+
"step": 12480
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 32.05,
|
444 |
+
"learning_rate": 1.1004273504273506e-06,
|
445 |
+
"loss": 0.3656,
|
446 |
+
"step": 12500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 33.0,
|
450 |
+
"eval_accuracy": 0.8902530694061639,
|
451 |
+
"eval_loss": 0.3780055344104767,
|
452 |
+
"eval_runtime": 5.8784,
|
453 |
+
"eval_samples_per_second": 29.09,
|
454 |
+
"eval_steps_per_second": 14.63,
|
455 |
+
"step": 12870
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 33.33,
|
459 |
+
"learning_rate": 7.443019943019944e-07,
|
460 |
+
"loss": 0.3617,
|
461 |
+
"step": 13000
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 34.0,
|
465 |
+
"eval_accuracy": 0.8873723487824038,
|
466 |
+
"eval_loss": 0.38049712777137756,
|
467 |
+
"eval_runtime": 5.8779,
|
468 |
+
"eval_samples_per_second": 29.092,
|
469 |
+
"eval_steps_per_second": 14.631,
|
470 |
+
"step": 13260
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 34.62,
|
474 |
+
"learning_rate": 3.8817663817663825e-07,
|
475 |
+
"loss": 0.361,
|
476 |
+
"step": 13500
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 35.0,
|
480 |
+
"eval_accuracy": 0.8919778767559101,
|
481 |
+
"eval_loss": 0.3775971233844757,
|
482 |
+
"eval_runtime": 5.8063,
|
483 |
+
"eval_samples_per_second": 29.451,
|
484 |
+
"eval_steps_per_second": 14.812,
|
485 |
+
"step": 13650
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 35.9,
|
489 |
+
"learning_rate": 3.205128205128205e-08,
|
490 |
+
"loss": 0.3595,
|
491 |
+
"step": 14000
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 36.0,
|
495 |
+
"eval_accuracy": 0.8888084202394747,
|
496 |
+
"eval_loss": 0.3711872100830078,
|
497 |
+
"eval_runtime": 5.8621,
|
498 |
+
"eval_samples_per_second": 29.171,
|
499 |
+
"eval_steps_per_second": 14.671,
|
500 |
+
"step": 14040
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 36.0,
|
504 |
+
"step": 14040,
|
505 |
+
"total_flos": 3.509780816886497e+17,
|
506 |
+
"train_loss": 0.5379996796958467,
|
507 |
+
"train_runtime": 13714.1823,
|
508 |
+
"train_samples_per_second": 8.19,
|
509 |
+
"train_steps_per_second": 1.024
|
510 |
+
}
|
511 |
+
],
|
512 |
+
"max_steps": 14040,
|
513 |
+
"num_train_epochs": 36,
|
514 |
+
"total_flos": 3.509780816886497e+17,
|
515 |
+
"trial_name": null,
|
516 |
+
"trial_params": null
|
517 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e62f0cca5fa131673e262469dc4be8f9f3fb2048d33c3baf0cda18865991b15f
|
3 |
+
size 3579
|
vocab.txt
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<cls>
|
2 |
+
<pad>
|
3 |
+
<eos>
|
4 |
+
<unk>
|
5 |
+
L
|
6 |
+
A
|
7 |
+
G
|
8 |
+
V
|
9 |
+
S
|
10 |
+
E
|
11 |
+
R
|
12 |
+
T
|
13 |
+
I
|
14 |
+
D
|
15 |
+
P
|
16 |
+
K
|
17 |
+
Q
|
18 |
+
N
|
19 |
+
F
|
20 |
+
Y
|
21 |
+
M
|
22 |
+
H
|
23 |
+
W
|
24 |
+
C
|
25 |
+
X
|
26 |
+
B
|
27 |
+
U
|
28 |
+
Z
|
29 |
+
O
|
30 |
+
.
|
31 |
+
-
|
32 |
+
<null_1>
|
33 |
+
<mask>
|