Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- checkpoint-322/config.json +31 -0
- checkpoint-322/model.safetensors +3 -0
- checkpoint-322/optimizer.pt +3 -0
- checkpoint-322/rng_state.pth +3 -0
- checkpoint-322/scaler.pt +3 -0
- checkpoint-322/scheduler.pt +3 -0
- checkpoint-322/tokenizer.json +3 -0
- checkpoint-322/tokenizer_config.json +14 -0
- checkpoint-322/trainer_state.json +266 -0
- checkpoint-322/training_args.bin +3 -0
- checkpoint-644/config.json +31 -0
- checkpoint-644/model.safetensors +3 -0
- checkpoint-644/optimizer.pt +3 -0
- checkpoint-644/rng_state.pth +3 -0
- checkpoint-644/scaler.pt +3 -0
- checkpoint-644/scheduler.pt +3 -0
- checkpoint-644/tokenizer.json +3 -0
- checkpoint-644/tokenizer_config.json +14 -0
- checkpoint-644/trainer_state.json +498 -0
- checkpoint-644/training_args.bin +3 -0
- config.json +31 -0
- model.safetensors +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -39,3 +39,6 @@ xlmr_spam_final/checkpoint-2814/tokenizer.json filter=lfs diff=lfs merge=lfs -te
|
|
| 39 |
xlmr_v1/checkpoint-322/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
xlmr_v1/checkpoint-644/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
xlmr_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
xlmr_v1/checkpoint-322/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
xlmr_v1/checkpoint-644/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
xlmr_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
checkpoint-322/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-644/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-322/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.1.0",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
checkpoint-322/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f741b4925aca4d07257786c0c16d8dd1ab6d8d96730995f7b753f94e423a87bb
|
| 3 |
+
size 1112204984
|
checkpoint-322/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4942b5a303e11c1e12f1ec3e38cb77f52d813c2a3b6c36af6914aa4b1fbf311e
|
| 3 |
+
size 2224529658
|
checkpoint-322/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04f779af80b021b161268ac30c9b56ff5d34fbece9bc553e4ff656cfe52ffdd
|
| 3 |
+
size 14244
|
checkpoint-322/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2725633a61db79106970482748454641c9161b5d2d378c0df56fe53a583e772d
|
| 3 |
+
size 988
|
checkpoint-322/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c9d0bfb7e7c3b9b19e70bb550549ae06f83a172d04342c9f707356c25a12f99
|
| 3 |
+
size 1064
|
checkpoint-322/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2464f9721707cb3d5edcf9a3d73454b13e8a7b3bb8fdba94b3de3d843f30e946
|
| 3 |
+
size 16781584
|
checkpoint-322/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|
checkpoint-322/trainer_state.json
ADDED
|
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 322,
|
| 3 |
+
"best_metric": 0.18244007229804993,
|
| 4 |
+
"best_model_checkpoint": "D:\\Major Project\\SpamX\\ml\\xlmr\\xlmr_v1\\checkpoint-322",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 322,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.03108003108003108,
|
| 14 |
+
"grad_norm": 29.43787956237793,
|
| 15 |
+
"learning_rate": 4.945652173913044e-06,
|
| 16 |
+
"loss": 1.2356471061706542,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06216006216006216,
|
| 21 |
+
"grad_norm": 36.178550720214844,
|
| 22 |
+
"learning_rate": 4.875776397515528e-06,
|
| 23 |
+
"loss": 1.1817050933837892,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09324009324009325,
|
| 28 |
+
"grad_norm": 29.694974899291992,
|
| 29 |
+
"learning_rate": 4.798136645962733e-06,
|
| 30 |
+
"loss": 1.0811898231506347,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.12432012432012432,
|
| 35 |
+
"grad_norm": 8.485957145690918,
|
| 36 |
+
"learning_rate": 4.7204968944099384e-06,
|
| 37 |
+
"loss": 0.876597785949707,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1554001554001554,
|
| 42 |
+
"grad_norm": 21.316192626953125,
|
| 43 |
+
"learning_rate": 4.642857142857144e-06,
|
| 44 |
+
"loss": 0.9505236625671387,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1864801864801865,
|
| 49 |
+
"grad_norm": 34.35721969604492,
|
| 50 |
+
"learning_rate": 4.565217391304348e-06,
|
| 51 |
+
"loss": 1.1337352752685548,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.21756021756021757,
|
| 56 |
+
"grad_norm": 48.13325881958008,
|
| 57 |
+
"learning_rate": 4.487577639751553e-06,
|
| 58 |
+
"loss": 1.063378143310547,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.24864024864024864,
|
| 63 |
+
"grad_norm": 38.45956802368164,
|
| 64 |
+
"learning_rate": 4.4177018633540375e-06,
|
| 65 |
+
"loss": 1.1818448066711427,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.27972027972027974,
|
| 70 |
+
"grad_norm": 18.295886993408203,
|
| 71 |
+
"learning_rate": 4.340062111801243e-06,
|
| 72 |
+
"loss": 0.91037015914917,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3108003108003108,
|
| 77 |
+
"grad_norm": 13.219426155090332,
|
| 78 |
+
"learning_rate": 4.262422360248447e-06,
|
| 79 |
+
"loss": 0.9483179092407227,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3418803418803419,
|
| 84 |
+
"grad_norm": 23.118179321289062,
|
| 85 |
+
"learning_rate": 4.184782608695653e-06,
|
| 86 |
+
"loss": 0.992742919921875,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.372960372960373,
|
| 91 |
+
"grad_norm": 13.910191535949707,
|
| 92 |
+
"learning_rate": 4.107142857142857e-06,
|
| 93 |
+
"loss": 0.8459652900695801,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.40404040404040403,
|
| 98 |
+
"grad_norm": 124.82660675048828,
|
| 99 |
+
"learning_rate": 4.0295031055900625e-06,
|
| 100 |
+
"loss": 0.9497438430786133,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.43512043512043513,
|
| 105 |
+
"grad_norm": 46.57713317871094,
|
| 106 |
+
"learning_rate": 3.951863354037268e-06,
|
| 107 |
+
"loss": 1.1179959297180175,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4662004662004662,
|
| 112 |
+
"grad_norm": 17.421274185180664,
|
| 113 |
+
"learning_rate": 3.874223602484472e-06,
|
| 114 |
+
"loss": 0.7715085983276367,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4972804972804973,
|
| 119 |
+
"grad_norm": 16.492841720581055,
|
| 120 |
+
"learning_rate": 3.7965838509316772e-06,
|
| 121 |
+
"loss": 0.9310503959655761,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5283605283605284,
|
| 126 |
+
"grad_norm": 38.246829986572266,
|
| 127 |
+
"learning_rate": 3.718944099378882e-06,
|
| 128 |
+
"loss": 0.89602632522583,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5594405594405595,
|
| 133 |
+
"grad_norm": 28.985132217407227,
|
| 134 |
+
"learning_rate": 3.6413043478260875e-06,
|
| 135 |
+
"loss": 0.8126945495605469,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5905205905205905,
|
| 140 |
+
"grad_norm": 14.60274600982666,
|
| 141 |
+
"learning_rate": 3.5636645962732924e-06,
|
| 142 |
+
"loss": 0.7371460914611816,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6216006216006216,
|
| 147 |
+
"grad_norm": 30.11294937133789,
|
| 148 |
+
"learning_rate": 3.486024844720497e-06,
|
| 149 |
+
"loss": 1.0865836143493652,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6526806526806527,
|
| 154 |
+
"grad_norm": 17.661558151245117,
|
| 155 |
+
"learning_rate": 3.4083850931677022e-06,
|
| 156 |
+
"loss": 1.0465456008911134,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6837606837606838,
|
| 161 |
+
"grad_norm": 34.937503814697266,
|
| 162 |
+
"learning_rate": 3.3385093167701865e-06,
|
| 163 |
+
"loss": 0.8159684181213379,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7148407148407149,
|
| 168 |
+
"grad_norm": 58.97747802734375,
|
| 169 |
+
"learning_rate": 3.2608695652173914e-06,
|
| 170 |
+
"loss": 0.820067310333252,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.745920745920746,
|
| 175 |
+
"grad_norm": 41.07950973510742,
|
| 176 |
+
"learning_rate": 3.1832298136645968e-06,
|
| 177 |
+
"loss": 1.0034560203552245,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.777000777000777,
|
| 182 |
+
"grad_norm": 31.760068893432617,
|
| 183 |
+
"learning_rate": 3.1055900621118013e-06,
|
| 184 |
+
"loss": 0.7825074672698975,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.8080808080808081,
|
| 189 |
+
"grad_norm": 29.330337524414062,
|
| 190 |
+
"learning_rate": 3.027950310559006e-06,
|
| 191 |
+
"loss": 0.8985923767089844,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.8391608391608392,
|
| 196 |
+
"grad_norm": 28.913965225219727,
|
| 197 |
+
"learning_rate": 2.9503105590062115e-06,
|
| 198 |
+
"loss": 0.8792219161987305,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8702408702408703,
|
| 203 |
+
"grad_norm": 17.811166763305664,
|
| 204 |
+
"learning_rate": 2.8726708074534164e-06,
|
| 205 |
+
"loss": 0.8635202407836914,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9013209013209014,
|
| 210 |
+
"grad_norm": 19.338523864746094,
|
| 211 |
+
"learning_rate": 2.795031055900621e-06,
|
| 212 |
+
"loss": 0.890287208557129,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.9324009324009324,
|
| 217 |
+
"grad_norm": 18.355663299560547,
|
| 218 |
+
"learning_rate": 2.7173913043478263e-06,
|
| 219 |
+
"loss": 0.9401198387145996,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.9634809634809635,
|
| 224 |
+
"grad_norm": 20.48928451538086,
|
| 225 |
+
"learning_rate": 2.639751552795031e-06,
|
| 226 |
+
"loss": 0.831356430053711,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.9945609945609946,
|
| 231 |
+
"grad_norm": 59.57387161254883,
|
| 232 |
+
"learning_rate": 2.5621118012422365e-06,
|
| 233 |
+
"loss": 0.7133886814117432,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0,
|
| 238 |
+
"eval_loss": 0.18244007229804993,
|
| 239 |
+
"eval_runtime": 4.4097,
|
| 240 |
+
"eval_samples_per_second": 259.426,
|
| 241 |
+
"eval_steps_per_second": 32.428,
|
| 242 |
+
"step": 322
|
| 243 |
+
}
|
| 244 |
+
],
|
| 245 |
+
"logging_steps": 10,
|
| 246 |
+
"max_steps": 644,
|
| 247 |
+
"num_input_tokens_seen": 0,
|
| 248 |
+
"num_train_epochs": 2,
|
| 249 |
+
"save_steps": 500,
|
| 250 |
+
"stateful_callbacks": {
|
| 251 |
+
"TrainerControl": {
|
| 252 |
+
"args": {
|
| 253 |
+
"should_epoch_stop": false,
|
| 254 |
+
"should_evaluate": false,
|
| 255 |
+
"should_log": false,
|
| 256 |
+
"should_save": true,
|
| 257 |
+
"should_training_stop": false
|
| 258 |
+
},
|
| 259 |
+
"attributes": {}
|
| 260 |
+
}
|
| 261 |
+
},
|
| 262 |
+
"total_flos": 391300611531000.0,
|
| 263 |
+
"train_batch_size": 8,
|
| 264 |
+
"trial_name": null,
|
| 265 |
+
"trial_params": null
|
| 266 |
+
}
|
checkpoint-322/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a44da1fe3b83e5bc0b568a24f212da51163e6e6058c33c08f7252f28612d3574
|
| 3 |
+
size 4792
|
checkpoint-644/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.1.0",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
checkpoint-644/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bd8036f3652c5248472577c5be1472e4d09695a46c48a475306888f0ced9d4a
|
| 3 |
+
size 1112204984
|
checkpoint-644/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a21b7921622201f092ce3cdd38b18e9b48040089269df7f65cd969de677f95e
|
| 3 |
+
size 2224529658
|
checkpoint-644/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:743aba1687c315dec910b7953f281e6820bd8053009788bfba4856f84534632f
|
| 3 |
+
size 14244
|
checkpoint-644/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab3be0a5d421e6ee0417ca0578aea14899255b1cd05eb21ef8852f72ca9dee77
|
| 3 |
+
size 988
|
checkpoint-644/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1184452503e1d36a2645049020c04efce12f9872de36ec791c90dbf0159c4a6d
|
| 3 |
+
size 1064
|
checkpoint-644/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2464f9721707cb3d5edcf9a3d73454b13e8a7b3bb8fdba94b3de3d843f30e946
|
| 3 |
+
size 16781584
|
checkpoint-644/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|
checkpoint-644/trainer_state.json
ADDED
|
@@ -0,0 +1,498 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 644,
|
| 3 |
+
"best_metric": 0.17823560535907745,
|
| 4 |
+
"best_model_checkpoint": "D:\\Major Project\\SpamX\\ml\\xlmr\\xlmr_v1\\checkpoint-644",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 644,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.03108003108003108,
|
| 14 |
+
"grad_norm": 29.43787956237793,
|
| 15 |
+
"learning_rate": 4.945652173913044e-06,
|
| 16 |
+
"loss": 1.2356471061706542,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06216006216006216,
|
| 21 |
+
"grad_norm": 36.178550720214844,
|
| 22 |
+
"learning_rate": 4.875776397515528e-06,
|
| 23 |
+
"loss": 1.1817050933837892,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09324009324009325,
|
| 28 |
+
"grad_norm": 29.694974899291992,
|
| 29 |
+
"learning_rate": 4.798136645962733e-06,
|
| 30 |
+
"loss": 1.0811898231506347,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.12432012432012432,
|
| 35 |
+
"grad_norm": 8.485957145690918,
|
| 36 |
+
"learning_rate": 4.7204968944099384e-06,
|
| 37 |
+
"loss": 0.876597785949707,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1554001554001554,
|
| 42 |
+
"grad_norm": 21.316192626953125,
|
| 43 |
+
"learning_rate": 4.642857142857144e-06,
|
| 44 |
+
"loss": 0.9505236625671387,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1864801864801865,
|
| 49 |
+
"grad_norm": 34.35721969604492,
|
| 50 |
+
"learning_rate": 4.565217391304348e-06,
|
| 51 |
+
"loss": 1.1337352752685548,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.21756021756021757,
|
| 56 |
+
"grad_norm": 48.13325881958008,
|
| 57 |
+
"learning_rate": 4.487577639751553e-06,
|
| 58 |
+
"loss": 1.063378143310547,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.24864024864024864,
|
| 63 |
+
"grad_norm": 38.45956802368164,
|
| 64 |
+
"learning_rate": 4.4177018633540375e-06,
|
| 65 |
+
"loss": 1.1818448066711427,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.27972027972027974,
|
| 70 |
+
"grad_norm": 18.295886993408203,
|
| 71 |
+
"learning_rate": 4.340062111801243e-06,
|
| 72 |
+
"loss": 0.91037015914917,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3108003108003108,
|
| 77 |
+
"grad_norm": 13.219426155090332,
|
| 78 |
+
"learning_rate": 4.262422360248447e-06,
|
| 79 |
+
"loss": 0.9483179092407227,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3418803418803419,
|
| 84 |
+
"grad_norm": 23.118179321289062,
|
| 85 |
+
"learning_rate": 4.184782608695653e-06,
|
| 86 |
+
"loss": 0.992742919921875,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.372960372960373,
|
| 91 |
+
"grad_norm": 13.910191535949707,
|
| 92 |
+
"learning_rate": 4.107142857142857e-06,
|
| 93 |
+
"loss": 0.8459652900695801,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.40404040404040403,
|
| 98 |
+
"grad_norm": 124.82660675048828,
|
| 99 |
+
"learning_rate": 4.0295031055900625e-06,
|
| 100 |
+
"loss": 0.9497438430786133,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.43512043512043513,
|
| 105 |
+
"grad_norm": 46.57713317871094,
|
| 106 |
+
"learning_rate": 3.951863354037268e-06,
|
| 107 |
+
"loss": 1.1179959297180175,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4662004662004662,
|
| 112 |
+
"grad_norm": 17.421274185180664,
|
| 113 |
+
"learning_rate": 3.874223602484472e-06,
|
| 114 |
+
"loss": 0.7715085983276367,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4972804972804973,
|
| 119 |
+
"grad_norm": 16.492841720581055,
|
| 120 |
+
"learning_rate": 3.7965838509316772e-06,
|
| 121 |
+
"loss": 0.9310503959655761,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5283605283605284,
|
| 126 |
+
"grad_norm": 38.246829986572266,
|
| 127 |
+
"learning_rate": 3.718944099378882e-06,
|
| 128 |
+
"loss": 0.89602632522583,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5594405594405595,
|
| 133 |
+
"grad_norm": 28.985132217407227,
|
| 134 |
+
"learning_rate": 3.6413043478260875e-06,
|
| 135 |
+
"loss": 0.8126945495605469,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5905205905205905,
|
| 140 |
+
"grad_norm": 14.60274600982666,
|
| 141 |
+
"learning_rate": 3.5636645962732924e-06,
|
| 142 |
+
"loss": 0.7371460914611816,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6216006216006216,
|
| 147 |
+
"grad_norm": 30.11294937133789,
|
| 148 |
+
"learning_rate": 3.486024844720497e-06,
|
| 149 |
+
"loss": 1.0865836143493652,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6526806526806527,
|
| 154 |
+
"grad_norm": 17.661558151245117,
|
| 155 |
+
"learning_rate": 3.4083850931677022e-06,
|
| 156 |
+
"loss": 1.0465456008911134,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6837606837606838,
|
| 161 |
+
"grad_norm": 34.937503814697266,
|
| 162 |
+
"learning_rate": 3.3385093167701865e-06,
|
| 163 |
+
"loss": 0.8159684181213379,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7148407148407149,
|
| 168 |
+
"grad_norm": 58.97747802734375,
|
| 169 |
+
"learning_rate": 3.2608695652173914e-06,
|
| 170 |
+
"loss": 0.820067310333252,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.745920745920746,
|
| 175 |
+
"grad_norm": 41.07950973510742,
|
| 176 |
+
"learning_rate": 3.1832298136645968e-06,
|
| 177 |
+
"loss": 1.0034560203552245,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.777000777000777,
|
| 182 |
+
"grad_norm": 31.760068893432617,
|
| 183 |
+
"learning_rate": 3.1055900621118013e-06,
|
| 184 |
+
"loss": 0.7825074672698975,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.8080808080808081,
|
| 189 |
+
"grad_norm": 29.330337524414062,
|
| 190 |
+
"learning_rate": 3.027950310559006e-06,
|
| 191 |
+
"loss": 0.8985923767089844,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.8391608391608392,
|
| 196 |
+
"grad_norm": 28.913965225219727,
|
| 197 |
+
"learning_rate": 2.9503105590062115e-06,
|
| 198 |
+
"loss": 0.8792219161987305,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8702408702408703,
|
| 203 |
+
"grad_norm": 17.811166763305664,
|
| 204 |
+
"learning_rate": 2.8726708074534164e-06,
|
| 205 |
+
"loss": 0.8635202407836914,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.9013209013209014,
|
| 210 |
+
"grad_norm": 19.338523864746094,
|
| 211 |
+
"learning_rate": 2.795031055900621e-06,
|
| 212 |
+
"loss": 0.890287208557129,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.9324009324009324,
|
| 217 |
+
"grad_norm": 18.355663299560547,
|
| 218 |
+
"learning_rate": 2.7173913043478263e-06,
|
| 219 |
+
"loss": 0.9401198387145996,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.9634809634809635,
|
| 224 |
+
"grad_norm": 20.48928451538086,
|
| 225 |
+
"learning_rate": 2.639751552795031e-06,
|
| 226 |
+
"loss": 0.831356430053711,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.9945609945609946,
|
| 231 |
+
"grad_norm": 59.57387161254883,
|
| 232 |
+
"learning_rate": 2.5621118012422365e-06,
|
| 233 |
+
"loss": 0.7133886814117432,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0,
|
| 238 |
+
"eval_loss": 0.18244007229804993,
|
| 239 |
+
"eval_runtime": 4.4097,
|
| 240 |
+
"eval_samples_per_second": 259.426,
|
| 241 |
+
"eval_steps_per_second": 32.428,
|
| 242 |
+
"step": 322
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.0248640248640248,
|
| 246 |
+
"grad_norm": 39.35393524169922,
|
| 247 |
+
"learning_rate": 2.484472049689441e-06,
|
| 248 |
+
"loss": 0.7849094867706299,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.055944055944056,
|
| 253 |
+
"grad_norm": 39.5618896484375,
|
| 254 |
+
"learning_rate": 2.4068322981366464e-06,
|
| 255 |
+
"loss": 0.5631073474884033,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.087024087024087,
|
| 260 |
+
"grad_norm": 27.039840698242188,
|
| 261 |
+
"learning_rate": 2.3291925465838513e-06,
|
| 262 |
+
"loss": 0.8551163673400879,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.118104118104118,
|
| 267 |
+
"grad_norm": 31.069948196411133,
|
| 268 |
+
"learning_rate": 2.251552795031056e-06,
|
| 269 |
+
"loss": 0.940975284576416,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.1491841491841492,
|
| 274 |
+
"grad_norm": 34.83683776855469,
|
| 275 |
+
"learning_rate": 2.173913043478261e-06,
|
| 276 |
+
"loss": 0.8859931945800781,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.1802641802641802,
|
| 281 |
+
"grad_norm": 43.3201789855957,
|
| 282 |
+
"learning_rate": 2.096273291925466e-06,
|
| 283 |
+
"loss": 0.6784295558929443,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.2113442113442114,
|
| 288 |
+
"grad_norm": 26.327808380126953,
|
| 289 |
+
"learning_rate": 2.018633540372671e-06,
|
| 290 |
+
"loss": 0.7212324619293213,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.2424242424242424,
|
| 295 |
+
"grad_norm": 22.891172409057617,
|
| 296 |
+
"learning_rate": 1.940993788819876e-06,
|
| 297 |
+
"loss": 0.8333398818969726,
|
| 298 |
+
"step": 400
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.2735042735042734,
|
| 302 |
+
"grad_norm": 56.2291374206543,
|
| 303 |
+
"learning_rate": 1.8633540372670808e-06,
|
| 304 |
+
"loss": 1.0169650077819825,
|
| 305 |
+
"step": 410
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.3045843045843046,
|
| 309 |
+
"grad_norm": 38.48230743408203,
|
| 310 |
+
"learning_rate": 1.7857142857142859e-06,
|
| 311 |
+
"loss": 0.7382871627807617,
|
| 312 |
+
"step": 420
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.3356643356643356,
|
| 316 |
+
"grad_norm": 38.05250549316406,
|
| 317 |
+
"learning_rate": 1.7080745341614908e-06,
|
| 318 |
+
"loss": 0.8073366165161133,
|
| 319 |
+
"step": 430
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.3667443667443666,
|
| 323 |
+
"grad_norm": 30.15036392211914,
|
| 324 |
+
"learning_rate": 1.6304347826086957e-06,
|
| 325 |
+
"loss": 0.8878802299499512,
|
| 326 |
+
"step": 440
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.3978243978243978,
|
| 330 |
+
"grad_norm": 35.91055679321289,
|
| 331 |
+
"learning_rate": 1.5527950310559006e-06,
|
| 332 |
+
"loss": 0.5926938533782959,
|
| 333 |
+
"step": 450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.428904428904429,
|
| 337 |
+
"grad_norm": 18.346158981323242,
|
| 338 |
+
"learning_rate": 1.4751552795031058e-06,
|
| 339 |
+
"loss": 0.590770959854126,
|
| 340 |
+
"step": 460
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.45998445998446,
|
| 344 |
+
"grad_norm": 31.250991821289062,
|
| 345 |
+
"learning_rate": 1.3975155279503105e-06,
|
| 346 |
+
"loss": 0.7174652099609375,
|
| 347 |
+
"step": 470
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.491064491064491,
|
| 351 |
+
"grad_norm": 35.001522064208984,
|
| 352 |
+
"learning_rate": 1.3198757763975156e-06,
|
| 353 |
+
"loss": 0.8534024238586426,
|
| 354 |
+
"step": 480
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.5221445221445222,
|
| 358 |
+
"grad_norm": 32.24079513549805,
|
| 359 |
+
"learning_rate": 1.2422360248447205e-06,
|
| 360 |
+
"loss": 0.8570188522338867,
|
| 361 |
+
"step": 490
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.5532245532245532,
|
| 365 |
+
"grad_norm": 19.8613224029541,
|
| 366 |
+
"learning_rate": 1.1645962732919256e-06,
|
| 367 |
+
"loss": 0.6434041023254394,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.5843045843045842,
|
| 372 |
+
"grad_norm": 46.252769470214844,
|
| 373 |
+
"learning_rate": 1.0869565217391306e-06,
|
| 374 |
+
"loss": 0.5186689376831055,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.6153846153846154,
|
| 379 |
+
"grad_norm": 20.27726936340332,
|
| 380 |
+
"learning_rate": 1.0093167701863355e-06,
|
| 381 |
+
"loss": 1.0002134323120118,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.6464646464646466,
|
| 386 |
+
"grad_norm": 22.71544075012207,
|
| 387 |
+
"learning_rate": 9.316770186335404e-07,
|
| 388 |
+
"loss": 0.6581085681915283,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.6775446775446774,
|
| 393 |
+
"grad_norm": 34.64213180541992,
|
| 394 |
+
"learning_rate": 8.540372670807454e-07,
|
| 395 |
+
"loss": 1.042281150817871,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.7086247086247086,
|
| 400 |
+
"grad_norm": 17.567914962768555,
|
| 401 |
+
"learning_rate": 7.763975155279503e-07,
|
| 402 |
+
"loss": 0.7002626419067383,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.7397047397047398,
|
| 407 |
+
"grad_norm": 31.270509719848633,
|
| 408 |
+
"learning_rate": 6.987577639751552e-07,
|
| 409 |
+
"loss": 0.7479125022888183,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.7707847707847708,
|
| 414 |
+
"grad_norm": 33.94447708129883,
|
| 415 |
+
"learning_rate": 6.211180124223603e-07,
|
| 416 |
+
"loss": 0.6186141014099121,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.8018648018648018,
|
| 421 |
+
"grad_norm": 18.601036071777344,
|
| 422 |
+
"learning_rate": 5.434782608695653e-07,
|
| 423 |
+
"loss": 0.6978522777557373,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.832944832944833,
|
| 428 |
+
"grad_norm": 29.79970359802246,
|
| 429 |
+
"learning_rate": 4.658385093167702e-07,
|
| 430 |
+
"loss": 0.838288402557373,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.864024864024864,
|
| 435 |
+
"grad_norm": 15.155320167541504,
|
| 436 |
+
"learning_rate": 3.8819875776397516e-07,
|
| 437 |
+
"loss": 0.4178286552429199,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.895104895104895,
|
| 442 |
+
"grad_norm": 32.92871856689453,
|
| 443 |
+
"learning_rate": 3.1055900621118013e-07,
|
| 444 |
+
"loss": 0.8897994041442872,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.9261849261849262,
|
| 449 |
+
"grad_norm": 6.8692827224731445,
|
| 450 |
+
"learning_rate": 2.329192546583851e-07,
|
| 451 |
+
"loss": 0.6488828659057617,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.9572649572649574,
|
| 456 |
+
"grad_norm": 54.483192443847656,
|
| 457 |
+
"learning_rate": 1.5527950310559006e-07,
|
| 458 |
+
"loss": 1.0308164596557616,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.9883449883449882,
|
| 463 |
+
"grad_norm": 30.52878761291504,
|
| 464 |
+
"learning_rate": 7.763975155279503e-08,
|
| 465 |
+
"loss": 0.7207555294036865,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.0,
|
| 470 |
+
"eval_loss": 0.17823560535907745,
|
| 471 |
+
"eval_runtime": 5.6175,
|
| 472 |
+
"eval_samples_per_second": 203.648,
|
| 473 |
+
"eval_steps_per_second": 25.456,
|
| 474 |
+
"step": 644
|
| 475 |
+
}
|
| 476 |
+
],
|
| 477 |
+
"logging_steps": 10,
|
| 478 |
+
"max_steps": 644,
|
| 479 |
+
"num_input_tokens_seen": 0,
|
| 480 |
+
"num_train_epochs": 2,
|
| 481 |
+
"save_steps": 500,
|
| 482 |
+
"stateful_callbacks": {
|
| 483 |
+
"TrainerControl": {
|
| 484 |
+
"args": {
|
| 485 |
+
"should_epoch_stop": false,
|
| 486 |
+
"should_evaluate": false,
|
| 487 |
+
"should_log": false,
|
| 488 |
+
"should_save": true,
|
| 489 |
+
"should_training_stop": true
|
| 490 |
+
},
|
| 491 |
+
"attributes": {}
|
| 492 |
+
}
|
| 493 |
+
},
|
| 494 |
+
"total_flos": 777428418602520.0,
|
| 495 |
+
"train_batch_size": 8,
|
| 496 |
+
"trial_name": null,
|
| 497 |
+
"trial_params": null
|
| 498 |
+
}
|
checkpoint-644/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a44da1fe3b83e5bc0b568a24f212da51163e6e6058c33c08f7252f28612d3574
|
| 3 |
+
size 4792
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"transformers_version": "5.1.0",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": false,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bd8036f3652c5248472577c5be1472e4d09695a46c48a475306888f0ced9d4a
|
| 3 |
+
size 1112204984
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2464f9721707cb3d5edcf9a3d73454b13e8a7b3bb8fdba94b3de3d843f30e946
|
| 3 |
+
size 16781584
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 13 |
+
"unk_token": "<unk>"
|
| 14 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a44da1fe3b83e5bc0b568a24f212da51163e6e6058c33c08f7252f28612d3574
|
| 3 |
+
size 4792
|