Commit
•
40d9b50
1
Parent(s):
0718a9e
Upload 10 files
Browse files- config.json +32 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- trainer_state.json +373 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../bert/bert-base-multilingual-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_fc_size": 768,
|
| 21 |
+
"pooler_num_attention_heads": 12,
|
| 22 |
+
"pooler_num_fc_layers": 3,
|
| 23 |
+
"pooler_size_per_head": 128,
|
| 24 |
+
"pooler_type": "first_token_transform",
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "single_label_classification",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.40.1",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 119547
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa26f51f5c8da79bac14946824e177b478f8c0efd679a7004cdc4b7ec10ad85b
|
| 3 |
+
size 711443456
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd8766b32c28117ab1e9cb56fff58054d24ba23e768a4a1124fe9cf54ee1ed6
|
| 3 |
+
size 1423007994
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:200bb63df685a51d719a8fee2c6f9b9ba699d7e44eb7fd47832b81313cd2f68f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76320ce4ec97c5c9aba00c5f9ac079ba0900242917453092d9390b52938f00f6
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 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 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11154,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13448090371167296,
|
| 13 |
+
"grad_norm": 4.317680835723877,
|
| 14 |
+
"learning_rate": 1.9103460641922183e-05,
|
| 15 |
+
"loss": 0.2456,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13448090371167296,
|
| 20 |
+
"eval_accuracy": 0.9731038192576654,
|
| 21 |
+
"eval_loss": 0.10059116035699844,
|
| 22 |
+
"eval_runtime": 79.8153,
|
| 23 |
+
"eval_samples_per_second": 93.165,
|
| 24 |
+
"eval_steps_per_second": 11.652,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2689618074233459,
|
| 29 |
+
"grad_norm": 15.100606918334961,
|
| 30 |
+
"learning_rate": 1.8206921283844363e-05,
|
| 31 |
+
"loss": 0.1162,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2689618074233459,
|
| 36 |
+
"eval_accuracy": 0.9665142549757935,
|
| 37 |
+
"eval_loss": 0.17202958464622498,
|
| 38 |
+
"eval_runtime": 77.2682,
|
| 39 |
+
"eval_samples_per_second": 96.236,
|
| 40 |
+
"eval_steps_per_second": 12.036,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.40344271113501884,
|
| 45 |
+
"grad_norm": 0.02275875024497509,
|
| 46 |
+
"learning_rate": 1.731038192576654e-05,
|
| 47 |
+
"loss": 0.0779,
|
| 48 |
+
"step": 1500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.40344271113501884,
|
| 52 |
+
"eval_accuracy": 0.957235072619688,
|
| 53 |
+
"eval_loss": 0.22287946939468384,
|
| 54 |
+
"eval_runtime": 86.088,
|
| 55 |
+
"eval_samples_per_second": 86.377,
|
| 56 |
+
"eval_steps_per_second": 10.803,
|
| 57 |
+
"step": 1500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.5379236148466918,
|
| 61 |
+
"grad_norm": 0.004053408745676279,
|
| 62 |
+
"learning_rate": 1.6413842567688722e-05,
|
| 63 |
+
"loss": 0.082,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.5379236148466918,
|
| 68 |
+
"eval_accuracy": 0.956831629908553,
|
| 69 |
+
"eval_loss": 0.2240680307149887,
|
| 70 |
+
"eval_runtime": 76.9592,
|
| 71 |
+
"eval_samples_per_second": 96.623,
|
| 72 |
+
"eval_steps_per_second": 12.084,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6724045185583647,
|
| 77 |
+
"grad_norm": 0.0030935597606003284,
|
| 78 |
+
"learning_rate": 1.5517303209610903e-05,
|
| 79 |
+
"loss": 0.0645,
|
| 80 |
+
"step": 2500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6724045185583647,
|
| 84 |
+
"eval_accuracy": 0.9519903173749328,
|
| 85 |
+
"eval_loss": 0.30673694610595703,
|
| 86 |
+
"eval_runtime": 72.7269,
|
| 87 |
+
"eval_samples_per_second": 102.246,
|
| 88 |
+
"eval_steps_per_second": 12.788,
|
| 89 |
+
"step": 2500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.8068854222700377,
|
| 93 |
+
"grad_norm": 0.019974075257778168,
|
| 94 |
+
"learning_rate": 1.4620763851533084e-05,
|
| 95 |
+
"loss": 0.059,
|
| 96 |
+
"step": 3000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.8068854222700377,
|
| 100 |
+
"eval_accuracy": 0.9909897794513179,
|
| 101 |
+
"eval_loss": 0.050069019198417664,
|
| 102 |
+
"eval_runtime": 79.0838,
|
| 103 |
+
"eval_samples_per_second": 94.027,
|
| 104 |
+
"eval_steps_per_second": 11.76,
|
| 105 |
+
"step": 3000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9413663259817105,
|
| 109 |
+
"grad_norm": 0.008741290308535099,
|
| 110 |
+
"learning_rate": 1.3724224493455265e-05,
|
| 111 |
+
"loss": 0.0582,
|
| 112 |
+
"step": 3500
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9413663259817105,
|
| 116 |
+
"eval_accuracy": 0.9911242603550295,
|
| 117 |
+
"eval_loss": 0.03790881112217903,
|
| 118 |
+
"eval_runtime": 77.0838,
|
| 119 |
+
"eval_samples_per_second": 96.466,
|
| 120 |
+
"eval_steps_per_second": 12.065,
|
| 121 |
+
"step": 3500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0758472296933834,
|
| 125 |
+
"grad_norm": 38.54170608520508,
|
| 126 |
+
"learning_rate": 1.2827685135377444e-05,
|
| 127 |
+
"loss": 0.0338,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0758472296933834,
|
| 132 |
+
"eval_accuracy": 0.9751210328133405,
|
| 133 |
+
"eval_loss": 0.15974809229373932,
|
| 134 |
+
"eval_runtime": 80.1945,
|
| 135 |
+
"eval_samples_per_second": 92.725,
|
| 136 |
+
"eval_steps_per_second": 11.597,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2103281334050564,
|
| 141 |
+
"grad_norm": 29.925457000732422,
|
| 142 |
+
"learning_rate": 1.1931145777299625e-05,
|
| 143 |
+
"loss": 0.03,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2103281334050564,
|
| 148 |
+
"eval_accuracy": 0.9916621839698763,
|
| 149 |
+
"eval_loss": 0.046014368534088135,
|
| 150 |
+
"eval_runtime": 57.8477,
|
| 151 |
+
"eval_samples_per_second": 128.544,
|
| 152 |
+
"eval_steps_per_second": 16.077,
|
| 153 |
+
"step": 4500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.3448090371167294,
|
| 157 |
+
"grad_norm": 0.007805847562849522,
|
| 158 |
+
"learning_rate": 1.1034606419221806e-05,
|
| 159 |
+
"loss": 0.0215,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.3448090371167294,
|
| 164 |
+
"eval_accuracy": 0.9772727272727273,
|
| 165 |
+
"eval_loss": 0.15217718482017517,
|
| 166 |
+
"eval_runtime": 74.0806,
|
| 167 |
+
"eval_samples_per_second": 100.377,
|
| 168 |
+
"eval_steps_per_second": 12.554,
|
| 169 |
+
"step": 5000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.4792899408284024,
|
| 173 |
+
"grad_norm": 0.0005576165858656168,
|
| 174 |
+
"learning_rate": 1.0138067061143987e-05,
|
| 175 |
+
"loss": 0.0144,
|
| 176 |
+
"step": 5500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.4792899408284024,
|
| 180 |
+
"eval_accuracy": 0.9413663259817105,
|
| 181 |
+
"eval_loss": 0.4672979414463043,
|
| 182 |
+
"eval_runtime": 74.077,
|
| 183 |
+
"eval_samples_per_second": 100.382,
|
| 184 |
+
"eval_steps_per_second": 12.555,
|
| 185 |
+
"step": 5500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.6137708445400754,
|
| 189 |
+
"grad_norm": 0.5596923232078552,
|
| 190 |
+
"learning_rate": 9.241527703066166e-06,
|
| 191 |
+
"loss": 0.0357,
|
| 192 |
+
"step": 6000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.6137708445400754,
|
| 196 |
+
"eval_accuracy": 0.991393222162453,
|
| 197 |
+
"eval_loss": 0.05371003597974777,
|
| 198 |
+
"eval_runtime": 91.3598,
|
| 199 |
+
"eval_samples_per_second": 81.392,
|
| 200 |
+
"eval_steps_per_second": 10.18,
|
| 201 |
+
"step": 6000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.7482517482517483,
|
| 205 |
+
"grad_norm": 0.0050299325957894325,
|
| 206 |
+
"learning_rate": 8.344988344988347e-06,
|
| 207 |
+
"loss": 0.0282,
|
| 208 |
+
"step": 6500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.7482517482517483,
|
| 212 |
+
"eval_accuracy": 0.9795589026358257,
|
| 213 |
+
"eval_loss": 0.10718287527561188,
|
| 214 |
+
"eval_runtime": 63.8039,
|
| 215 |
+
"eval_samples_per_second": 116.545,
|
| 216 |
+
"eval_steps_per_second": 14.576,
|
| 217 |
+
"step": 6500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.8827326519634213,
|
| 221 |
+
"grad_norm": 0.1358013153076172,
|
| 222 |
+
"learning_rate": 7.448448986910526e-06,
|
| 223 |
+
"loss": 0.0271,
|
| 224 |
+
"step": 7000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.8827326519634213,
|
| 228 |
+
"eval_accuracy": 0.9616729424421732,
|
| 229 |
+
"eval_loss": 0.21952089667320251,
|
| 230 |
+
"eval_runtime": 62.6082,
|
| 231 |
+
"eval_samples_per_second": 118.77,
|
| 232 |
+
"eval_steps_per_second": 14.854,
|
| 233 |
+
"step": 7000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.0172135556750943,
|
| 237 |
+
"grad_norm": 0.0005359902861528099,
|
| 238 |
+
"learning_rate": 6.551909628832707e-06,
|
| 239 |
+
"loss": 0.0151,
|
| 240 |
+
"step": 7500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.0172135556750943,
|
| 244 |
+
"eval_accuracy": 0.972027972027972,
|
| 245 |
+
"eval_loss": 0.18190746009349823,
|
| 246 |
+
"eval_runtime": 75.7313,
|
| 247 |
+
"eval_samples_per_second": 98.189,
|
| 248 |
+
"eval_steps_per_second": 12.28,
|
| 249 |
+
"step": 7500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.151694459386767,
|
| 253 |
+
"grad_norm": 0.0002543228620197624,
|
| 254 |
+
"learning_rate": 5.655370270754886e-06,
|
| 255 |
+
"loss": 0.0124,
|
| 256 |
+
"step": 8000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.151694459386767,
|
| 260 |
+
"eval_accuracy": 0.9796933835395374,
|
| 261 |
+
"eval_loss": 0.12187998741865158,
|
| 262 |
+
"eval_runtime": 73.9844,
|
| 263 |
+
"eval_samples_per_second": 100.508,
|
| 264 |
+
"eval_steps_per_second": 12.57,
|
| 265 |
+
"step": 8000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.28617536309844,
|
| 269 |
+
"grad_norm": 0.017442911863327026,
|
| 270 |
+
"learning_rate": 4.758830912677067e-06,
|
| 271 |
+
"loss": 0.0084,
|
| 272 |
+
"step": 8500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.28617536309844,
|
| 276 |
+
"eval_accuracy": 0.9803657880580957,
|
| 277 |
+
"eval_loss": 0.133524090051651,
|
| 278 |
+
"eval_runtime": 72.5895,
|
| 279 |
+
"eval_samples_per_second": 102.439,
|
| 280 |
+
"eval_steps_per_second": 12.812,
|
| 281 |
+
"step": 8500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.420656266810113,
|
| 285 |
+
"grad_norm": 0.00029117995291016996,
|
| 286 |
+
"learning_rate": 3.862291554599247e-06,
|
| 287 |
+
"loss": 0.0045,
|
| 288 |
+
"step": 9000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.420656266810113,
|
| 292 |
+
"eval_accuracy": 0.9868208714362561,
|
| 293 |
+
"eval_loss": 0.084413081407547,
|
| 294 |
+
"eval_runtime": 71.5341,
|
| 295 |
+
"eval_samples_per_second": 103.95,
|
| 296 |
+
"eval_steps_per_second": 13.001,
|
| 297 |
+
"step": 9000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.555137170521786,
|
| 301 |
+
"grad_norm": 0.0001818160671973601,
|
| 302 |
+
"learning_rate": 2.9657521965214274e-06,
|
| 303 |
+
"loss": 0.0027,
|
| 304 |
+
"step": 9500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.555137170521786,
|
| 308 |
+
"eval_accuracy": 0.9838622915545993,
|
| 309 |
+
"eval_loss": 0.1180611401796341,
|
| 310 |
+
"eval_runtime": 72.5206,
|
| 311 |
+
"eval_samples_per_second": 102.536,
|
| 312 |
+
"eval_steps_per_second": 12.824,
|
| 313 |
+
"step": 9500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.6896180742334588,
|
| 317 |
+
"grad_norm": 0.00021849782206118107,
|
| 318 |
+
"learning_rate": 2.069212838443608e-06,
|
| 319 |
+
"loss": 0.0061,
|
| 320 |
+
"step": 10000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.6896180742334588,
|
| 324 |
+
"eval_accuracy": 0.9842657342657343,
|
| 325 |
+
"eval_loss": 0.11533553153276443,
|
| 326 |
+
"eval_runtime": 72.894,
|
| 327 |
+
"eval_samples_per_second": 102.011,
|
| 328 |
+
"eval_steps_per_second": 12.758,
|
| 329 |
+
"step": 10000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.8240989779451318,
|
| 333 |
+
"grad_norm": 0.0002802180533763021,
|
| 334 |
+
"learning_rate": 1.1726734803657882e-06,
|
| 335 |
+
"loss": 0.0026,
|
| 336 |
+
"step": 10500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.8240989779451318,
|
| 340 |
+
"eval_accuracy": 0.9905863367401829,
|
| 341 |
+
"eval_loss": 0.06259341537952423,
|
| 342 |
+
"eval_runtime": 72.005,
|
| 343 |
+
"eval_samples_per_second": 103.271,
|
| 344 |
+
"eval_steps_per_second": 12.916,
|
| 345 |
+
"step": 10500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.9585798816568047,
|
| 349 |
+
"grad_norm": 0.00011676761641865596,
|
| 350 |
+
"learning_rate": 2.7613412228796843e-07,
|
| 351 |
+
"loss": 0.0008,
|
| 352 |
+
"step": 11000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.9585798816568047,
|
| 356 |
+
"eval_accuracy": 0.983593329747176,
|
| 357 |
+
"eval_loss": 0.13157618045806885,
|
| 358 |
+
"eval_runtime": 95.8085,
|
| 359 |
+
"eval_samples_per_second": 77.613,
|
| 360 |
+
"eval_steps_per_second": 9.707,
|
| 361 |
+
"step": 11000
|
| 362 |
+
}
|
| 363 |
+
],
|
| 364 |
+
"logging_steps": 500,
|
| 365 |
+
"max_steps": 11154,
|
| 366 |
+
"num_input_tokens_seen": 0,
|
| 367 |
+
"num_train_epochs": 3,
|
| 368 |
+
"save_steps": 500,
|
| 369 |
+
"total_flos": 1.8301403760969e+16,
|
| 370 |
+
"train_batch_size": 8,
|
| 371 |
+
"trial_name": null,
|
| 372 |
+
"trial_params": null
|
| 373 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfc7e249f4a7941cc06989f6ec1445b35f11da2753e6b814d6ce30cd3a2190a7
|
| 3 |
+
size 5048
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|