Upload 11 files
Browse files- checkpoint-375/config.json +38 -0
- checkpoint-375/merges.txt +0 -0
- checkpoint-375/optimizer.pt +3 -0
- checkpoint-375/rng_state.pth +3 -0
- checkpoint-375/scheduler.pt +3 -0
- checkpoint-375/special_tokens_map.json +15 -0
- checkpoint-375/tokenizer.json +0 -0
- checkpoint-375/tokenizer_config.json +58 -0
- checkpoint-375/trainer_state.json +317 -0
- checkpoint-375/training_args.bin +3 -0
- checkpoint-375/vocab.json +0 -0
checkpoint-375/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1,
|
| 23 |
+
"LABEL_2": 2,
|
| 24 |
+
"LABEL_3": 3
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"max_position_embeddings": 514,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.51.3",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50265
|
| 38 |
+
}
|
checkpoint-375/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-375/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab894df93f0feec1242e75efed9a418164f413c887f6a7c10227304d9b4457ec
|
| 3 |
+
size 1499066
|
checkpoint-375/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22763e8c44a7ed6a21d4caf3e1170a84f1064628e9d44eab8d9cf4f2e361f5f1
|
| 3 |
+
size 14244
|
checkpoint-375/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44137efcddb1970ad3fd98958a955fef90f883f11e210270f80b87bbb6a957e6
|
| 3 |
+
size 1064
|
checkpoint-375/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-375/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-375/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-375/trainer_state.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 375,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08,
|
| 14 |
+
"grad_norm": 2.356316089630127,
|
| 15 |
+
"learning_rate": 2e-05,
|
| 16 |
+
"loss": 0.9561,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.16,
|
| 21 |
+
"grad_norm": 2.9643399715423584,
|
| 22 |
+
"learning_rate": 2e-05,
|
| 23 |
+
"loss": 0.5253,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.24,
|
| 28 |
+
"grad_norm": 3.6455039978027344,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 0.3936,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.32,
|
| 35 |
+
"grad_norm": 10.778894424438477,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 0.3738,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4,
|
| 42 |
+
"grad_norm": 2.7228519916534424,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 0.3413,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.48,
|
| 49 |
+
"grad_norm": 5.166695594787598,
|
| 50 |
+
"learning_rate": 2e-05,
|
| 51 |
+
"loss": 0.345,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.56,
|
| 56 |
+
"grad_norm": 3.4323439598083496,
|
| 57 |
+
"learning_rate": 2e-05,
|
| 58 |
+
"loss": 0.3115,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.64,
|
| 63 |
+
"grad_norm": 4.534356594085693,
|
| 64 |
+
"learning_rate": 2e-05,
|
| 65 |
+
"loss": 0.2928,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.72,
|
| 70 |
+
"grad_norm": 6.345835208892822,
|
| 71 |
+
"learning_rate": 2e-05,
|
| 72 |
+
"loss": 0.2943,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.8,
|
| 77 |
+
"grad_norm": 5.384378433227539,
|
| 78 |
+
"learning_rate": 2e-05,
|
| 79 |
+
"loss": 0.3092,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.88,
|
| 84 |
+
"grad_norm": 6.48573637008667,
|
| 85 |
+
"learning_rate": 2e-05,
|
| 86 |
+
"loss": 0.287,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.96,
|
| 91 |
+
"grad_norm": 5.112663745880127,
|
| 92 |
+
"learning_rate": 2e-05,
|
| 93 |
+
"loss": 0.2571,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.0,
|
| 98 |
+
"eval_accuracy": 0.8957646462084707,
|
| 99 |
+
"eval_f1": 0.8177339901477834,
|
| 100 |
+
"eval_loss": 0.288971871137619,
|
| 101 |
+
"eval_precision": 0.7918902802623733,
|
| 102 |
+
"eval_recall": 0.8453214513049013,
|
| 103 |
+
"eval_runtime": 0.4071,
|
| 104 |
+
"eval_samples_per_second": 368.482,
|
| 105 |
+
"eval_steps_per_second": 24.565,
|
| 106 |
+
"step": 125
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.04,
|
| 110 |
+
"grad_norm": 2.791001558303833,
|
| 111 |
+
"learning_rate": 2e-05,
|
| 112 |
+
"loss": 0.2704,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.12,
|
| 117 |
+
"grad_norm": 5.1042585372924805,
|
| 118 |
+
"learning_rate": 2e-05,
|
| 119 |
+
"loss": 0.2193,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.2,
|
| 124 |
+
"grad_norm": 3.7543392181396484,
|
| 125 |
+
"learning_rate": 2e-05,
|
| 126 |
+
"loss": 0.2822,
|
| 127 |
+
"step": 150
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.28,
|
| 131 |
+
"grad_norm": 3.875131130218506,
|
| 132 |
+
"learning_rate": 2e-05,
|
| 133 |
+
"loss": 0.2661,
|
| 134 |
+
"step": 160
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.3599999999999999,
|
| 138 |
+
"grad_norm": 10.078240394592285,
|
| 139 |
+
"learning_rate": 2e-05,
|
| 140 |
+
"loss": 0.2568,
|
| 141 |
+
"step": 170
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.44,
|
| 145 |
+
"grad_norm": 4.0438055992126465,
|
| 146 |
+
"learning_rate": 2e-05,
|
| 147 |
+
"loss": 0.2369,
|
| 148 |
+
"step": 180
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.52,
|
| 152 |
+
"grad_norm": 2.991152048110962,
|
| 153 |
+
"learning_rate": 2e-05,
|
| 154 |
+
"loss": 0.2568,
|
| 155 |
+
"step": 190
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.6,
|
| 159 |
+
"grad_norm": 5.471771717071533,
|
| 160 |
+
"learning_rate": 2e-05,
|
| 161 |
+
"loss": 0.2741,
|
| 162 |
+
"step": 200
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.6800000000000002,
|
| 166 |
+
"grad_norm": 2.9698643684387207,
|
| 167 |
+
"learning_rate": 2e-05,
|
| 168 |
+
"loss": 0.2338,
|
| 169 |
+
"step": 210
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.76,
|
| 173 |
+
"grad_norm": 2.496001958847046,
|
| 174 |
+
"learning_rate": 2e-05,
|
| 175 |
+
"loss": 0.2254,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.8399999999999999,
|
| 180 |
+
"grad_norm": 2.994489908218384,
|
| 181 |
+
"learning_rate": 2e-05,
|
| 182 |
+
"loss": 0.2305,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.92,
|
| 187 |
+
"grad_norm": 5.702557563781738,
|
| 188 |
+
"learning_rate": 2e-05,
|
| 189 |
+
"loss": 0.2227,
|
| 190 |
+
"step": 240
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.0,
|
| 194 |
+
"grad_norm": 5.2754130363464355,
|
| 195 |
+
"learning_rate": 2e-05,
|
| 196 |
+
"loss": 0.2274,
|
| 197 |
+
"step": 250
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.0,
|
| 201 |
+
"eval_accuracy": 0.8923408572153183,
|
| 202 |
+
"eval_f1": 0.8256227758007116,
|
| 203 |
+
"eval_loss": 0.33088892698287964,
|
| 204 |
+
"eval_precision": 0.7729039422543031,
|
| 205 |
+
"eval_recall": 0.8860598345003182,
|
| 206 |
+
"eval_runtime": 0.4096,
|
| 207 |
+
"eval_samples_per_second": 366.202,
|
| 208 |
+
"eval_steps_per_second": 24.413,
|
| 209 |
+
"step": 250
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.08,
|
| 213 |
+
"grad_norm": 2.392334461212158,
|
| 214 |
+
"learning_rate": 2e-05,
|
| 215 |
+
"loss": 0.1498,
|
| 216 |
+
"step": 260
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.16,
|
| 220 |
+
"grad_norm": 3.8733561038970947,
|
| 221 |
+
"learning_rate": 2e-05,
|
| 222 |
+
"loss": 0.2306,
|
| 223 |
+
"step": 270
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.24,
|
| 227 |
+
"grad_norm": 1.9787098169326782,
|
| 228 |
+
"learning_rate": 2e-05,
|
| 229 |
+
"loss": 0.1853,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.32,
|
| 234 |
+
"grad_norm": 4.077596187591553,
|
| 235 |
+
"learning_rate": 2e-05,
|
| 236 |
+
"loss": 0.1701,
|
| 237 |
+
"step": 290
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.4,
|
| 241 |
+
"grad_norm": 7.104099750518799,
|
| 242 |
+
"learning_rate": 2e-05,
|
| 243 |
+
"loss": 0.1887,
|
| 244 |
+
"step": 300
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.48,
|
| 248 |
+
"grad_norm": 3.239741086959839,
|
| 249 |
+
"learning_rate": 2e-05,
|
| 250 |
+
"loss": 0.183,
|
| 251 |
+
"step": 310
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.56,
|
| 255 |
+
"grad_norm": 2.7079355716705322,
|
| 256 |
+
"learning_rate": 2e-05,
|
| 257 |
+
"loss": 0.1804,
|
| 258 |
+
"step": 320
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.64,
|
| 262 |
+
"grad_norm": 4.828829288482666,
|
| 263 |
+
"learning_rate": 2e-05,
|
| 264 |
+
"loss": 0.2166,
|
| 265 |
+
"step": 330
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.7199999999999998,
|
| 269 |
+
"grad_norm": 2.2557036876678467,
|
| 270 |
+
"learning_rate": 2e-05,
|
| 271 |
+
"loss": 0.168,
|
| 272 |
+
"step": 340
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.8,
|
| 276 |
+
"grad_norm": 4.428867816925049,
|
| 277 |
+
"learning_rate": 2e-05,
|
| 278 |
+
"loss": 0.296,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.88,
|
| 283 |
+
"grad_norm": 4.281528949737549,
|
| 284 |
+
"learning_rate": 2e-05,
|
| 285 |
+
"loss": 0.2209,
|
| 286 |
+
"step": 360
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.96,
|
| 290 |
+
"grad_norm": 4.2655792236328125,
|
| 291 |
+
"learning_rate": 2e-05,
|
| 292 |
+
"loss": 0.2238,
|
| 293 |
+
"step": 370
|
| 294 |
+
}
|
| 295 |
+
],
|
| 296 |
+
"logging_steps": 10,
|
| 297 |
+
"max_steps": 375,
|
| 298 |
+
"num_input_tokens_seen": 0,
|
| 299 |
+
"num_train_epochs": 3,
|
| 300 |
+
"save_steps": 500,
|
| 301 |
+
"stateful_callbacks": {
|
| 302 |
+
"TrainerControl": {
|
| 303 |
+
"args": {
|
| 304 |
+
"should_epoch_stop": false,
|
| 305 |
+
"should_evaluate": false,
|
| 306 |
+
"should_log": false,
|
| 307 |
+
"should_save": true,
|
| 308 |
+
"should_training_stop": true
|
| 309 |
+
},
|
| 310 |
+
"attributes": {}
|
| 311 |
+
}
|
| 312 |
+
},
|
| 313 |
+
"total_flos": 473453787413376.0,
|
| 314 |
+
"train_batch_size": 16,
|
| 315 |
+
"trial_name": null,
|
| 316 |
+
"trial_params": null
|
| 317 |
+
}
|
checkpoint-375/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69c29f54ec9189ed1c7169ca4ac9211abad2d33ea9ac74e133075a63b1e1132f
|
| 3 |
+
size 5304
|
checkpoint-375/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|