Upload 10 files
Browse files- config.json +30 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer_config.json +52 -0
- trainer_state.json +313 -0
- training_args.bin +3 -0
- vocab.txt +33 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ambrim/finetuned-epitope_attempt7_150M_200k_default_accuracy",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"EsmForTokenClassification"
|
| 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": 640,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2560,
|
| 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": 30,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "rotary",
|
| 24 |
+
"token_dropout": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.35.2",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_list": null,
|
| 29 |
+
"vocab_size": 33
|
| 30 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1648697292a8c4e3563c67b275dfb0f0e089c1c37d09597f0775434b598a58d3
|
| 3 |
+
size 593608020
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bc7a7faf857d42317d311596325088dd706d57fc0e5339bdf6d55ef208a8833
|
| 3 |
+
size 1187500938
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c94c375fe5ad2903d244ca6b5cc2a1a6cba4c0c26196f3b9cbd9ddd170bb0b8
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5fb17e31beac1a1a237b0f120fb87c11faabd93b3e04ecc4f17f6741e77ad66
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "<cls>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<eos>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "<mask>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "<unk>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<cls>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<eos>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "<cls>",
|
| 46 |
+
"eos_token": "<eos>",
|
| 47 |
+
"mask_token": "<mask>",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_token": "<pad>",
|
| 50 |
+
"tokenizer_class": "EsmTokenizer",
|
| 51 |
+
"unk_token": "<unk>"
|
| 52 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9404261658430337,
|
| 3 |
+
"best_model_checkpoint": "finetuned-epitope_attempt7_150M_200k_default_accuracy-finetuned-epitope_attempt7_150M_200k_weighted_accuracy_1.5/checkpoint-1716",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 17160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.29,
|
| 13 |
+
"learning_rate": 9.708624708624709e-05,
|
| 14 |
+
"loss": -991.1524,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.58,
|
| 19 |
+
"learning_rate": 9.417249417249418e-05,
|
| 20 |
+
"loss": -2627.8292,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.87,
|
| 25 |
+
"learning_rate": 9.125874125874126e-05,
|
| 26 |
+
"loss": -4819.024,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"eval_accuracy": 0.9404261658430337,
|
| 32 |
+
"eval_loss": -7140.48779296875,
|
| 33 |
+
"eval_runtime": 61.4312,
|
| 34 |
+
"eval_samples_per_second": 74.474,
|
| 35 |
+
"eval_steps_per_second": 3.109,
|
| 36 |
+
"step": 1716
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.17,
|
| 40 |
+
"learning_rate": 8.834498834498835e-05,
|
| 41 |
+
"loss": -7373.8975,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.46,
|
| 46 |
+
"learning_rate": 8.543123543123544e-05,
|
| 47 |
+
"loss": -10190.031,
|
| 48 |
+
"step": 2500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.75,
|
| 52 |
+
"learning_rate": 8.251748251748252e-05,
|
| 53 |
+
"loss": -13358.039,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.0,
|
| 58 |
+
"eval_accuracy": 0.9404261658430337,
|
| 59 |
+
"eval_loss": -18116.330078125,
|
| 60 |
+
"eval_runtime": 61.6525,
|
| 61 |
+
"eval_samples_per_second": 74.206,
|
| 62 |
+
"eval_steps_per_second": 3.098,
|
| 63 |
+
"step": 3432
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.04,
|
| 67 |
+
"learning_rate": 7.960372960372961e-05,
|
| 68 |
+
"loss": -16816.902,
|
| 69 |
+
"step": 3500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.33,
|
| 73 |
+
"learning_rate": 7.66899766899767e-05,
|
| 74 |
+
"loss": -20556.736,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.62,
|
| 79 |
+
"learning_rate": 7.377622377622378e-05,
|
| 80 |
+
"loss": -24214.914,
|
| 81 |
+
"step": 4500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.91,
|
| 85 |
+
"learning_rate": 7.086247086247087e-05,
|
| 86 |
+
"loss": -28116.02,
|
| 87 |
+
"step": 5000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.0,
|
| 91 |
+
"eval_accuracy": 0.9404261658430337,
|
| 92 |
+
"eval_loss": -31477.326171875,
|
| 93 |
+
"eval_runtime": 61.4757,
|
| 94 |
+
"eval_samples_per_second": 74.42,
|
| 95 |
+
"eval_steps_per_second": 3.107,
|
| 96 |
+
"step": 5148
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.21,
|
| 100 |
+
"learning_rate": 6.794871794871795e-05,
|
| 101 |
+
"loss": -32552.834,
|
| 102 |
+
"step": 5500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.5,
|
| 106 |
+
"learning_rate": 6.503496503496504e-05,
|
| 107 |
+
"loss": -36651.288,
|
| 108 |
+
"step": 6000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.79,
|
| 112 |
+
"learning_rate": 6.212121212121213e-05,
|
| 113 |
+
"loss": -40514.324,
|
| 114 |
+
"step": 6500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.0,
|
| 118 |
+
"eval_accuracy": 0.9404261658430337,
|
| 119 |
+
"eval_loss": -45798.8046875,
|
| 120 |
+
"eval_runtime": 61.7173,
|
| 121 |
+
"eval_samples_per_second": 74.128,
|
| 122 |
+
"eval_steps_per_second": 3.095,
|
| 123 |
+
"step": 6864
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.08,
|
| 127 |
+
"learning_rate": 5.920745920745921e-05,
|
| 128 |
+
"loss": -44842.148,
|
| 129 |
+
"step": 7000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.37,
|
| 133 |
+
"learning_rate": 5.629370629370629e-05,
|
| 134 |
+
"loss": -49187.524,
|
| 135 |
+
"step": 7500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.66,
|
| 139 |
+
"learning_rate": 5.3379953379953385e-05,
|
| 140 |
+
"loss": -53412.06,
|
| 141 |
+
"step": 8000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.95,
|
| 145 |
+
"learning_rate": 5.0466200466200464e-05,
|
| 146 |
+
"loss": -57251.756,
|
| 147 |
+
"step": 8500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 5.0,
|
| 151 |
+
"eval_accuracy": 0.9404261658430337,
|
| 152 |
+
"eval_loss": -59889.9140625,
|
| 153 |
+
"eval_runtime": 61.4135,
|
| 154 |
+
"eval_samples_per_second": 74.495,
|
| 155 |
+
"eval_steps_per_second": 3.11,
|
| 156 |
+
"step": 8580
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.24,
|
| 160 |
+
"learning_rate": 4.755244755244756e-05,
|
| 161 |
+
"loss": -60731.896,
|
| 162 |
+
"step": 9000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 5.54,
|
| 166 |
+
"learning_rate": 4.463869463869464e-05,
|
| 167 |
+
"loss": -65162.9,
|
| 168 |
+
"step": 9500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.83,
|
| 172 |
+
"learning_rate": 4.172494172494173e-05,
|
| 173 |
+
"loss": -69186.816,
|
| 174 |
+
"step": 10000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.0,
|
| 178 |
+
"eval_accuracy": 0.9404261658430337,
|
| 179 |
+
"eval_loss": -72761.71875,
|
| 180 |
+
"eval_runtime": 61.5973,
|
| 181 |
+
"eval_samples_per_second": 74.273,
|
| 182 |
+
"eval_steps_per_second": 3.101,
|
| 183 |
+
"step": 10296
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.12,
|
| 187 |
+
"learning_rate": 3.8811188811188816e-05,
|
| 188 |
+
"loss": -72763.624,
|
| 189 |
+
"step": 10500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.41,
|
| 193 |
+
"learning_rate": 3.58974358974359e-05,
|
| 194 |
+
"loss": -76222.128,
|
| 195 |
+
"step": 11000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.7,
|
| 199 |
+
"learning_rate": 3.298368298368298e-05,
|
| 200 |
+
"loss": -78716.456,
|
| 201 |
+
"step": 11500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.99,
|
| 205 |
+
"learning_rate": 3.0069930069930068e-05,
|
| 206 |
+
"loss": -82078.184,
|
| 207 |
+
"step": 12000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.0,
|
| 211 |
+
"eval_accuracy": 0.9404261658430337,
|
| 212 |
+
"eval_loss": -83606.6171875,
|
| 213 |
+
"eval_runtime": 61.5161,
|
| 214 |
+
"eval_samples_per_second": 74.371,
|
| 215 |
+
"eval_steps_per_second": 3.105,
|
| 216 |
+
"step": 12012
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 7.28,
|
| 220 |
+
"learning_rate": 2.715617715617716e-05,
|
| 221 |
+
"loss": -84137.776,
|
| 222 |
+
"step": 12500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 7.58,
|
| 226 |
+
"learning_rate": 2.4242424242424244e-05,
|
| 227 |
+
"loss": -88317.616,
|
| 228 |
+
"step": 13000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 7.87,
|
| 232 |
+
"learning_rate": 2.132867132867133e-05,
|
| 233 |
+
"loss": -90301.752,
|
| 234 |
+
"step": 13500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.0,
|
| 238 |
+
"eval_accuracy": 0.9404261658430337,
|
| 239 |
+
"eval_loss": -91807.8203125,
|
| 240 |
+
"eval_runtime": 61.5191,
|
| 241 |
+
"eval_samples_per_second": 74.367,
|
| 242 |
+
"eval_steps_per_second": 3.105,
|
| 243 |
+
"step": 13728
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.16,
|
| 247 |
+
"learning_rate": 1.8414918414918416e-05,
|
| 248 |
+
"loss": -91880.464,
|
| 249 |
+
"step": 14000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.45,
|
| 253 |
+
"learning_rate": 1.5501165501165503e-05,
|
| 254 |
+
"loss": -94262.232,
|
| 255 |
+
"step": 14500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.74,
|
| 259 |
+
"learning_rate": 1.2587412587412589e-05,
|
| 260 |
+
"loss": -95277.608,
|
| 261 |
+
"step": 15000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.0,
|
| 265 |
+
"eval_accuracy": 0.9404261658430337,
|
| 266 |
+
"eval_loss": -96907.4296875,
|
| 267 |
+
"eval_runtime": 61.3968,
|
| 268 |
+
"eval_samples_per_second": 74.515,
|
| 269 |
+
"eval_steps_per_second": 3.111,
|
| 270 |
+
"step": 15444
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.03,
|
| 274 |
+
"learning_rate": 9.673659673659673e-06,
|
| 275 |
+
"loss": -97058.592,
|
| 276 |
+
"step": 15500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.32,
|
| 280 |
+
"learning_rate": 6.7599067599067605e-06,
|
| 281 |
+
"loss": -97791.208,
|
| 282 |
+
"step": 16000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 9.62,
|
| 286 |
+
"learning_rate": 3.846153846153847e-06,
|
| 287 |
+
"loss": -98873.392,
|
| 288 |
+
"step": 16500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 9.91,
|
| 292 |
+
"learning_rate": 9.324009324009324e-07,
|
| 293 |
+
"loss": -98503.392,
|
| 294 |
+
"step": 17000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 10.0,
|
| 298 |
+
"eval_accuracy": 0.9404261658430337,
|
| 299 |
+
"eval_loss": -98637.3671875,
|
| 300 |
+
"eval_runtime": 61.2106,
|
| 301 |
+
"eval_samples_per_second": 74.742,
|
| 302 |
+
"eval_steps_per_second": 3.12,
|
| 303 |
+
"step": 17160
|
| 304 |
+
}
|
| 305 |
+
],
|
| 306 |
+
"logging_steps": 500,
|
| 307 |
+
"max_steps": 17160,
|
| 308 |
+
"num_train_epochs": 10,
|
| 309 |
+
"save_steps": 500,
|
| 310 |
+
"total_flos": 3.3502108609523e+17,
|
| 311 |
+
"trial_name": null,
|
| 312 |
+
"trial_params": null
|
| 313 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93b8feeace9b37557963d3c878a57e4e428d7f100f10dafa62c1ad6a56b8f3ba
|
| 3 |
+
size 4728
|
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>
|