Push best model used for final benchmarks
Browse files- checkpoint-1648/config.json +40 -0
- checkpoint-1648/model.safetensors +3 -0
- checkpoint-1648/optimizer.pt +3 -0
- checkpoint-1648/rng_state.pth +3 -0
- checkpoint-1648/scheduler.pt +3 -0
- checkpoint-1648/special_tokens_map.json +7 -0
- checkpoint-1648/tokenizer.json +0 -0
- checkpoint-1648/tokenizer_config.json +58 -0
- checkpoint-1648/trainer_state.json +276 -0
- checkpoint-1648/training_args.bin +3 -0
- checkpoint-1648/vocab.txt +0 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-1648/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Seguro",
|
| 13 |
+
"1": "Inseguro"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Inseguro": 1,
|
| 19 |
+
"Seguro": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"pooler_fc_size": 768,
|
| 29 |
+
"pooler_num_attention_heads": 12,
|
| 30 |
+
"pooler_num_fc_layers": 3,
|
| 31 |
+
"pooler_size_per_head": 128,
|
| 32 |
+
"pooler_type": "first_token_transform",
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.55.4",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 29794
|
| 40 |
+
}
|
checkpoint-1648/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16ad92826d9d1a2b46dfe3e8e614c5812fba1eca9dcd191438da5050409d174b
|
| 3 |
+
size 435722224
|
checkpoint-1648/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dec03d7fe7ca82acd3d8a9e81086f1032bbf1d482586cabbaf2b85c2ef519ab9
|
| 3 |
+
size 871568779
|
checkpoint-1648/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44d7ba51d4e979d8213c863f2e5be974c03cc8d2d66930b91f50130915791fb2
|
| 3 |
+
size 14645
|
checkpoint-1648/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db5d8d9d4bad86de0a2e5d55b08b70345344466be951bfd2a614c6f8d29c9696
|
| 3 |
+
size 1465
|
checkpoint-1648/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 |
+
}
|
checkpoint-1648/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1648/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
checkpoint-1648/trainer_state.json
ADDED
|
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1648,
|
| 3 |
+
"best_metric": 0.8445309964297306,
|
| 4 |
+
"best_model_checkpoint": "outputs/final-run/checkpoint-1648",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1648,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06071645415907711,
|
| 14 |
+
"grad_norm": 3.1775882244110107,
|
| 15 |
+
"learning_rate": 4.9993183714305955e-05,
|
| 16 |
+
"loss": 0.542,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12143290831815422,
|
| 21 |
+
"grad_norm": 8.159868240356445,
|
| 22 |
+
"learning_rate": 4.997217948372208e-05,
|
| 23 |
+
"loss": 0.4499,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.18214936247723132,
|
| 28 |
+
"grad_norm": 2.8959903717041016,
|
| 29 |
+
"learning_rate": 4.993699639509482e-05,
|
| 30 |
+
"loss": 0.4707,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.24286581663630843,
|
| 35 |
+
"grad_norm": 4.034249305725098,
|
| 36 |
+
"learning_rate": 4.9887654424895166e-05,
|
| 37 |
+
"loss": 0.4384,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3035822707953855,
|
| 42 |
+
"grad_norm": 2.3457038402557373,
|
| 43 |
+
"learning_rate": 4.982418158881122e-05,
|
| 44 |
+
"loss": 0.4252,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.36429872495446264,
|
| 49 |
+
"grad_norm": 4.431244850158691,
|
| 50 |
+
"learning_rate": 4.974661392584119e-05,
|
| 51 |
+
"loss": 0.4194,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.42501517911353975,
|
| 56 |
+
"grad_norm": 2.9599080085754395,
|
| 57 |
+
"learning_rate": 4.965499547783105e-05,
|
| 58 |
+
"loss": 0.4278,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.48573163327261687,
|
| 63 |
+
"grad_norm": 2.453009843826294,
|
| 64 |
+
"learning_rate": 4.954937826446812e-05,
|
| 65 |
+
"loss": 0.4102,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.546448087431694,
|
| 70 |
+
"grad_norm": 4.7085442543029785,
|
| 71 |
+
"learning_rate": 4.942982225374503e-05,
|
| 72 |
+
"loss": 0.4003,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.607164541590771,
|
| 77 |
+
"grad_norm": 2.347684621810913,
|
| 78 |
+
"learning_rate": 4.9296395327910704e-05,
|
| 79 |
+
"loss": 0.4021,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6678809957498482,
|
| 84 |
+
"grad_norm": 2.545522689819336,
|
| 85 |
+
"learning_rate": 4.914917324492781e-05,
|
| 86 |
+
"loss": 0.4012,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7285974499089253,
|
| 91 |
+
"grad_norm": 2.2640328407287598,
|
| 92 |
+
"learning_rate": 4.8988239595458375e-05,
|
| 93 |
+
"loss": 0.3945,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.7893139040680024,
|
| 98 |
+
"grad_norm": 3.549863815307617,
|
| 99 |
+
"learning_rate": 4.881368575540219e-05,
|
| 100 |
+
"loss": 0.3987,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.8500303582270795,
|
| 105 |
+
"grad_norm": 2.2821035385131836,
|
| 106 |
+
"learning_rate": 4.8625610834014855e-05,
|
| 107 |
+
"loss": 0.4139,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.9107468123861566,
|
| 112 |
+
"grad_norm": 2.2632572650909424,
|
| 113 |
+
"learning_rate": 4.8424121617634884e-05,
|
| 114 |
+
"loss": 0.3868,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.9714632665452337,
|
| 119 |
+
"grad_norm": 2.499703884124756,
|
| 120 |
+
"learning_rate": 4.820933250905191e-05,
|
| 121 |
+
"loss": 0.4055,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.0,
|
| 126 |
+
"eval_f1": 0.8411822020136408,
|
| 127 |
+
"eval_loss": 0.38803601264953613,
|
| 128 |
+
"eval_runtime": 7.8685,
|
| 129 |
+
"eval_samples_per_second": 743.853,
|
| 130 |
+
"eval_steps_per_second": 23.257,
|
| 131 |
+
"step": 824
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.03157255616272,
|
| 135 |
+
"grad_norm": 2.6810269355773926,
|
| 136 |
+
"learning_rate": 4.798136546255038e-05,
|
| 137 |
+
"loss": 0.3408,
|
| 138 |
+
"step": 850
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.0922890103217973,
|
| 142 |
+
"grad_norm": 3.898928642272949,
|
| 143 |
+
"learning_rate": 4.774034991466558e-05,
|
| 144 |
+
"loss": 0.301,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.1530054644808743,
|
| 149 |
+
"grad_norm": 2.426880121231079,
|
| 150 |
+
"learning_rate": 4.7486422710691366e-05,
|
| 151 |
+
"loss": 0.3031,
|
| 152 |
+
"step": 950
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.2137219186399515,
|
| 156 |
+
"grad_norm": 2.5744643211364746,
|
| 157 |
+
"learning_rate": 4.7219728026981314e-05,
|
| 158 |
+
"loss": 0.3097,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.2744383727990285,
|
| 163 |
+
"grad_norm": 3.3714475631713867,
|
| 164 |
+
"learning_rate": 4.694041728908733e-05,
|
| 165 |
+
"loss": 0.3268,
|
| 166 |
+
"step": 1050
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.3351548269581057,
|
| 170 |
+
"grad_norm": 3.3059871196746826,
|
| 171 |
+
"learning_rate": 4.66486490857824e-05,
|
| 172 |
+
"loss": 0.3091,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.3958712811171827,
|
| 177 |
+
"grad_norm": 2.7642199993133545,
|
| 178 |
+
"learning_rate": 4.6344589079016e-05,
|
| 179 |
+
"loss": 0.3072,
|
| 180 |
+
"step": 1150
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.4565877352762597,
|
| 184 |
+
"grad_norm": 3.11942982673645,
|
| 185 |
+
"learning_rate": 4.6028409909853585e-05,
|
| 186 |
+
"loss": 0.3324,
|
| 187 |
+
"step": 1200
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.517304189435337,
|
| 191 |
+
"grad_norm": 2.588369369506836,
|
| 192 |
+
"learning_rate": 4.570029110045335e-05,
|
| 193 |
+
"loss": 0.3268,
|
| 194 |
+
"step": 1250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.5780206435944142,
|
| 198 |
+
"grad_norm": 4.089269161224365,
|
| 199 |
+
"learning_rate": 4.536041895213605e-05,
|
| 200 |
+
"loss": 0.3343,
|
| 201 |
+
"step": 1300
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.6387370977534912,
|
| 205 |
+
"grad_norm": 1.9836137294769287,
|
| 206 |
+
"learning_rate": 4.500898643960567e-05,
|
| 207 |
+
"loss": 0.3305,
|
| 208 |
+
"step": 1350
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.6994535519125682,
|
| 212 |
+
"grad_norm": 3.1558611392974854,
|
| 213 |
+
"learning_rate": 4.4646193101381076e-05,
|
| 214 |
+
"loss": 0.3383,
|
| 215 |
+
"step": 1400
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.7601700060716454,
|
| 219 |
+
"grad_norm": 3.998915672302246,
|
| 220 |
+
"learning_rate": 4.427224492650079e-05,
|
| 221 |
+
"loss": 0.3265,
|
| 222 |
+
"step": 1450
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.8208864602307226,
|
| 226 |
+
"grad_norm": 2.276543617248535,
|
| 227 |
+
"learning_rate": 4.3887354237565295e-05,
|
| 228 |
+
"loss": 0.3368,
|
| 229 |
+
"step": 1500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.8816029143897997,
|
| 233 |
+
"grad_norm": 2.9267208576202393,
|
| 234 |
+
"learning_rate": 4.349173957018313e-05,
|
| 235 |
+
"loss": 0.3125,
|
| 236 |
+
"step": 1550
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.9423193685488767,
|
| 240 |
+
"grad_norm": 2.7525475025177,
|
| 241 |
+
"learning_rate": 4.308562554888948e-05,
|
| 242 |
+
"loss": 0.3132,
|
| 243 |
+
"step": 1600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.0,
|
| 247 |
+
"eval_f1": 0.8445309964297306,
|
| 248 |
+
"eval_loss": 0.4081823527812958,
|
| 249 |
+
"eval_runtime": 7.8688,
|
| 250 |
+
"eval_samples_per_second": 743.825,
|
| 251 |
+
"eval_steps_per_second": 23.256,
|
| 252 |
+
"step": 1648
|
| 253 |
+
}
|
| 254 |
+
],
|
| 255 |
+
"logging_steps": 50,
|
| 256 |
+
"max_steps": 6592,
|
| 257 |
+
"num_input_tokens_seen": 0,
|
| 258 |
+
"num_train_epochs": 8,
|
| 259 |
+
"save_steps": 500,
|
| 260 |
+
"stateful_callbacks": {
|
| 261 |
+
"TrainerControl": {
|
| 262 |
+
"args": {
|
| 263 |
+
"should_epoch_stop": false,
|
| 264 |
+
"should_evaluate": false,
|
| 265 |
+
"should_log": false,
|
| 266 |
+
"should_save": true,
|
| 267 |
+
"should_training_stop": false
|
| 268 |
+
},
|
| 269 |
+
"attributes": {}
|
| 270 |
+
}
|
| 271 |
+
},
|
| 272 |
+
"total_flos": 2.771769723795456e+16,
|
| 273 |
+
"train_batch_size": 32,
|
| 274 |
+
"trial_name": null,
|
| 275 |
+
"trial_params": null
|
| 276 |
+
}
|
checkpoint-1648/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3771198bf2e7919b145bd70347691951f295fe0aedba9e1d794fa281c8e0b274
|
| 3 |
+
size 5841
|
checkpoint-1648/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435722224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16ad92826d9d1a2b46dfe3e8e614c5812fba1eca9dcd191438da5050409d174b
|
| 3 |
size 435722224
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3771198bf2e7919b145bd70347691951f295fe0aedba9e1d794fa281c8e0b274
|
| 3 |
size 5841
|