Upload folder using huggingface_hub
Browse files- config.json +28 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +432 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/xlm-v-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.41.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 901629
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9ccdbfa0867a79924388d382a8233ff27668c1729559b60d9d85a68b0ddeb5d
|
| 3 |
+
size 3114003416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed4b2b4d1bb9d823778935e2e89da2cab824b3d9cf062a86d0867fdf4dc4c8f
|
| 3 |
+
size 6228131858
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a36fedb56c18b8956a1a960fd61eee9346a81b45d97785ce8389eb6293135c9a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:936c6f5bbf3a3dbe10feca3e4110e021edb85a659f5354a5f21437182e998a50
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7877622937690213,
|
| 3 |
+
"best_model_checkpoint": "./XLM-V_64-multi-outputs/checkpoint-16000",
|
| 4 |
+
"epoch": 14.8619957537155,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 21000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7077140835102619,
|
| 13 |
+
"grad_norm": 0.7589670419692993,
|
| 14 |
+
"learning_rate": 4.7169811320754717e-07,
|
| 15 |
+
"loss": 0.6944,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.7077140835102619,
|
| 20 |
+
"eval_accuracy": 0.5096086826645425,
|
| 21 |
+
"eval_f1": 0.6748960327414351,
|
| 22 |
+
"eval_loss": 0.6923578381538391,
|
| 23 |
+
"eval_precision": 0.5093155325296403,
|
| 24 |
+
"eval_recall": 1.0,
|
| 25 |
+
"eval_runtime": 57.7937,
|
| 26 |
+
"eval_samples_per_second": 173.773,
|
| 27 |
+
"eval_steps_per_second": 2.717,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.4154281670205238,
|
| 32 |
+
"grad_norm": 6.16334867477417,
|
| 33 |
+
"learning_rate": 9.433962264150943e-07,
|
| 34 |
+
"loss": 0.6848,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.4154281670205238,
|
| 39 |
+
"eval_accuracy": 0.6086826645424674,
|
| 40 |
+
"eval_f1": 0.7141402385801571,
|
| 41 |
+
"eval_loss": 0.6570077538490295,
|
| 42 |
+
"eval_precision": 0.5684344603983326,
|
| 43 |
+
"eval_recall": 0.9602895148669797,
|
| 44 |
+
"eval_runtime": 57.4971,
|
| 45 |
+
"eval_samples_per_second": 174.67,
|
| 46 |
+
"eval_steps_per_second": 2.731,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.1231422505307855,
|
| 51 |
+
"grad_norm": 2.09871768951416,
|
| 52 |
+
"learning_rate": 9.538663171690695e-07,
|
| 53 |
+
"loss": 0.6613,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.1231422505307855,
|
| 58 |
+
"eval_accuracy": 0.6230210096584686,
|
| 59 |
+
"eval_f1": 0.7231241772707327,
|
| 60 |
+
"eval_loss": 0.6287678480148315,
|
| 61 |
+
"eval_precision": 0.5774351786965662,
|
| 62 |
+
"eval_recall": 0.9671361502347418,
|
| 63 |
+
"eval_runtime": 57.6578,
|
| 64 |
+
"eval_samples_per_second": 174.183,
|
| 65 |
+
"eval_steps_per_second": 2.723,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.8308563340410475,
|
| 70 |
+
"grad_norm": 1.726118803024292,
|
| 71 |
+
"learning_rate": 9.014416775884666e-07,
|
| 72 |
+
"loss": 0.6505,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.8308563340410475,
|
| 77 |
+
"eval_accuracy": 0.635965348999303,
|
| 78 |
+
"eval_f1": 0.7311764705882353,
|
| 79 |
+
"eval_loss": 0.615561306476593,
|
| 80 |
+
"eval_precision": 0.5857681432610744,
|
| 81 |
+
"eval_recall": 0.9726134585289515,
|
| 82 |
+
"eval_runtime": 57.6722,
|
| 83 |
+
"eval_samples_per_second": 174.139,
|
| 84 |
+
"eval_steps_per_second": 2.722,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.538570417551309,
|
| 89 |
+
"grad_norm": 18.405258178710938,
|
| 90 |
+
"learning_rate": 8.490170380078637e-07,
|
| 91 |
+
"loss": 0.6453,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.538570417551309,
|
| 96 |
+
"eval_accuracy": 0.6402469381658867,
|
| 97 |
+
"eval_f1": 0.7314353675760054,
|
| 98 |
+
"eval_loss": 0.6071421504020691,
|
| 99 |
+
"eval_precision": 0.5898573312552452,
|
| 100 |
+
"eval_recall": 0.9624413145539906,
|
| 101 |
+
"eval_runtime": 57.5099,
|
| 102 |
+
"eval_samples_per_second": 174.631,
|
| 103 |
+
"eval_steps_per_second": 2.73,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.246284501061571,
|
| 108 |
+
"grad_norm": 1.6453580856323242,
|
| 109 |
+
"learning_rate": 7.965923984272608e-07,
|
| 110 |
+
"loss": 0.632,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.246284501061571,
|
| 115 |
+
"eval_accuracy": 0.6659364731653888,
|
| 116 |
+
"eval_f1": 0.7478770571879462,
|
| 117 |
+
"eval_loss": 0.5868598222732544,
|
| 118 |
+
"eval_precision": 0.6071995118974984,
|
| 119 |
+
"eval_recall": 0.97339593114241,
|
| 120 |
+
"eval_runtime": 58.3002,
|
| 121 |
+
"eval_samples_per_second": 172.263,
|
| 122 |
+
"eval_steps_per_second": 2.693,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.953998584571833,
|
| 127 |
+
"grad_norm": 3.636608362197876,
|
| 128 |
+
"learning_rate": 7.44167758846658e-07,
|
| 129 |
+
"loss": 0.6232,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 4.953998584571833,
|
| 134 |
+
"eval_accuracy": 0.6733047894055562,
|
| 135 |
+
"eval_f1": 0.7526200708738596,
|
| 136 |
+
"eval_loss": 0.5761261582374573,
|
| 137 |
+
"eval_precision": 0.6123175070543492,
|
| 138 |
+
"eval_recall": 0.9763302034428795,
|
| 139 |
+
"eval_runtime": 57.6672,
|
| 140 |
+
"eval_samples_per_second": 174.154,
|
| 141 |
+
"eval_steps_per_second": 2.723,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.661712668082095,
|
| 146 |
+
"grad_norm": 24.744699478149414,
|
| 147 |
+
"learning_rate": 6.91743119266055e-07,
|
| 148 |
+
"loss": 0.6141,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.661712668082095,
|
| 153 |
+
"eval_accuracy": 0.688140993726974,
|
| 154 |
+
"eval_f1": 0.7601837672281776,
|
| 155 |
+
"eval_loss": 0.5643310546875,
|
| 156 |
+
"eval_precision": 0.6245596376446905,
|
| 157 |
+
"eval_recall": 0.9710485133020345,
|
| 158 |
+
"eval_runtime": 57.5859,
|
| 159 |
+
"eval_samples_per_second": 174.4,
|
| 160 |
+
"eval_steps_per_second": 2.726,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.369426751592357,
|
| 165 |
+
"grad_norm": 9.586795806884766,
|
| 166 |
+
"learning_rate": 6.393184796854522e-07,
|
| 167 |
+
"loss": 0.605,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 6.369426751592357,
|
| 172 |
+
"eval_accuracy": 0.6972020312655581,
|
| 173 |
+
"eval_f1": 0.7631066448547168,
|
| 174 |
+
"eval_loss": 0.553417980670929,
|
| 175 |
+
"eval_precision": 0.6340453074433657,
|
| 176 |
+
"eval_recall": 0.9581377151799687,
|
| 177 |
+
"eval_runtime": 57.7405,
|
| 178 |
+
"eval_samples_per_second": 173.933,
|
| 179 |
+
"eval_steps_per_second": 2.719,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 7.077140835102618,
|
| 184 |
+
"grad_norm": 8.45578384399414,
|
| 185 |
+
"learning_rate": 5.868938401048492e-07,
|
| 186 |
+
"loss": 0.6021,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 7.077140835102618,
|
| 191 |
+
"eval_accuracy": 0.7043712038235587,
|
| 192 |
+
"eval_f1": 0.7691829277773459,
|
| 193 |
+
"eval_loss": 0.5444474816322327,
|
| 194 |
+
"eval_precision": 0.6382402270674752,
|
| 195 |
+
"eval_recall": 0.9677230046948356,
|
| 196 |
+
"eval_runtime": 57.654,
|
| 197 |
+
"eval_samples_per_second": 174.194,
|
| 198 |
+
"eval_steps_per_second": 2.723,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 7.78485491861288,
|
| 203 |
+
"grad_norm": 10.198156356811523,
|
| 204 |
+
"learning_rate": 5.344692005242464e-07,
|
| 205 |
+
"loss": 0.5934,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.78485491861288,
|
| 210 |
+
"eval_accuracy": 0.7097480832420592,
|
| 211 |
+
"eval_f1": 0.7714263310593585,
|
| 212 |
+
"eval_loss": 0.5372178554534912,
|
| 213 |
+
"eval_precision": 0.6437639052480042,
|
| 214 |
+
"eval_recall": 0.962245696400626,
|
| 215 |
+
"eval_runtime": 57.4867,
|
| 216 |
+
"eval_samples_per_second": 174.701,
|
| 217 |
+
"eval_steps_per_second": 2.731,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 8.492569002123142,
|
| 222 |
+
"grad_norm": 34.88262176513672,
|
| 223 |
+
"learning_rate": 4.820445609436435e-07,
|
| 224 |
+
"loss": 0.5842,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.492569002123142,
|
| 229 |
+
"eval_accuracy": 0.7273722991138106,
|
| 230 |
+
"eval_f1": 0.7810650887573964,
|
| 231 |
+
"eval_loss": 0.5250558853149414,
|
| 232 |
+
"eval_precision": 0.6605355693805789,
|
| 233 |
+
"eval_recall": 0.9553990610328639,
|
| 234 |
+
"eval_runtime": 57.6716,
|
| 235 |
+
"eval_samples_per_second": 174.141,
|
| 236 |
+
"eval_steps_per_second": 2.722,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.200283085633403,
|
| 241 |
+
"grad_norm": 63.931617736816406,
|
| 242 |
+
"learning_rate": 4.296199213630406e-07,
|
| 243 |
+
"loss": 0.5775,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 9.200283085633403,
|
| 248 |
+
"eval_accuracy": 0.7322513193268944,
|
| 249 |
+
"eval_f1": 0.7830226740902122,
|
| 250 |
+
"eval_loss": 0.5154615640640259,
|
| 251 |
+
"eval_precision": 0.6663919791237467,
|
| 252 |
+
"eval_recall": 0.9491392801251957,
|
| 253 |
+
"eval_runtime": 57.6583,
|
| 254 |
+
"eval_samples_per_second": 174.181,
|
| 255 |
+
"eval_steps_per_second": 2.723,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 9.907997169143666,
|
| 260 |
+
"grad_norm": 18.855731964111328,
|
| 261 |
+
"learning_rate": 3.771952817824377e-07,
|
| 262 |
+
"loss": 0.5694,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.907997169143666,
|
| 267 |
+
"eval_accuracy": 0.7335457532609778,
|
| 268 |
+
"eval_f1": 0.7848182695400451,
|
| 269 |
+
"eval_loss": 0.5107560157775879,
|
| 270 |
+
"eval_precision": 0.6663025669033316,
|
| 271 |
+
"eval_recall": 0.9546165884194053,
|
| 272 |
+
"eval_runtime": 57.5122,
|
| 273 |
+
"eval_samples_per_second": 174.624,
|
| 274 |
+
"eval_steps_per_second": 2.73,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 10.615711252653927,
|
| 279 |
+
"grad_norm": 5.973861217498779,
|
| 280 |
+
"learning_rate": 3.247706422018349e-07,
|
| 281 |
+
"loss": 0.5645,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 10.615711252653927,
|
| 286 |
+
"eval_accuracy": 0.7354376182415613,
|
| 287 |
+
"eval_f1": 0.7858466994438623,
|
| 288 |
+
"eval_loss": 0.5042764544487,
|
| 289 |
+
"eval_precision": 0.6682659355723098,
|
| 290 |
+
"eval_recall": 0.9536384976525821,
|
| 291 |
+
"eval_runtime": 57.6441,
|
| 292 |
+
"eval_samples_per_second": 174.224,
|
| 293 |
+
"eval_steps_per_second": 2.724,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 11.32342533616419,
|
| 298 |
+
"grad_norm": 13.824345588684082,
|
| 299 |
+
"learning_rate": 2.72346002621232e-07,
|
| 300 |
+
"loss": 0.5555,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 11.32342533616419,
|
| 305 |
+
"eval_accuracy": 0.7361346211291446,
|
| 306 |
+
"eval_f1": 0.7877622937690213,
|
| 307 |
+
"eval_loss": 0.5019333362579346,
|
| 308 |
+
"eval_precision": 0.666937889883374,
|
| 309 |
+
"eval_recall": 0.9620500782472613,
|
| 310 |
+
"eval_runtime": 57.7949,
|
| 311 |
+
"eval_samples_per_second": 173.77,
|
| 312 |
+
"eval_steps_per_second": 2.717,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 12.031139419674451,
|
| 317 |
+
"grad_norm": 12.343938827514648,
|
| 318 |
+
"learning_rate": 2.199213630406291e-07,
|
| 319 |
+
"loss": 0.5517,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 12.031139419674451,
|
| 324 |
+
"eval_accuracy": 0.7386239171562282,
|
| 325 |
+
"eval_f1": 0.786879922058943,
|
| 326 |
+
"eval_loss": 0.4967314302921295,
|
| 327 |
+
"eval_precision": 0.672588480222068,
|
| 328 |
+
"eval_recall": 0.9479655712050078,
|
| 329 |
+
"eval_runtime": 57.6752,
|
| 330 |
+
"eval_samples_per_second": 174.13,
|
| 331 |
+
"eval_steps_per_second": 2.722,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 12.738853503184714,
|
| 336 |
+
"grad_norm": 10.652567863464355,
|
| 337 |
+
"learning_rate": 1.6749672346002622e-07,
|
| 338 |
+
"loss": 0.5485,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 12.738853503184714,
|
| 343 |
+
"eval_accuracy": 0.7389226326794782,
|
| 344 |
+
"eval_f1": 0.7872444011684518,
|
| 345 |
+
"eval_loss": 0.49510088562965393,
|
| 346 |
+
"eval_precision": 0.6726289517470881,
|
| 347 |
+
"eval_recall": 0.948943661971831,
|
| 348 |
+
"eval_runtime": 57.6551,
|
| 349 |
+
"eval_samples_per_second": 174.191,
|
| 350 |
+
"eval_steps_per_second": 2.723,
|
| 351 |
+
"step": 18000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 13.446567586694975,
|
| 355 |
+
"grad_norm": 7.330574035644531,
|
| 356 |
+
"learning_rate": 1.1507208387942332e-07,
|
| 357 |
+
"loss": 0.5448,
|
| 358 |
+
"step": 19000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 13.446567586694975,
|
| 362 |
+
"eval_accuracy": 0.7379269142686449,
|
| 363 |
+
"eval_f1": 0.7868825910931174,
|
| 364 |
+
"eval_loss": 0.49567386507987976,
|
| 365 |
+
"eval_precision": 0.6713180436584691,
|
| 366 |
+
"eval_recall": 0.9505086071987481,
|
| 367 |
+
"eval_runtime": 57.6941,
|
| 368 |
+
"eval_samples_per_second": 174.073,
|
| 369 |
+
"eval_steps_per_second": 2.721,
|
| 370 |
+
"step": 19000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 14.154281670205236,
|
| 374 |
+
"grad_norm": 22.538665771484375,
|
| 375 |
+
"learning_rate": 6.264744429882045e-08,
|
| 376 |
+
"loss": 0.5441,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 14.154281670205236,
|
| 381 |
+
"eval_accuracy": 0.7379269142686449,
|
| 382 |
+
"eval_f1": 0.7872615583575816,
|
| 383 |
+
"eval_loss": 0.4930832087993622,
|
| 384 |
+
"eval_precision": 0.6707988980716253,
|
| 385 |
+
"eval_recall": 0.952660406885759,
|
| 386 |
+
"eval_runtime": 57.6062,
|
| 387 |
+
"eval_samples_per_second": 174.339,
|
| 388 |
+
"eval_steps_per_second": 2.725,
|
| 389 |
+
"step": 20000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 14.8619957537155,
|
| 393 |
+
"grad_norm": 11.810145378112793,
|
| 394 |
+
"learning_rate": 1.0222804718217562e-08,
|
| 395 |
+
"loss": 0.5416,
|
| 396 |
+
"step": 21000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 14.8619957537155,
|
| 400 |
+
"eval_accuracy": 0.7375286269043114,
|
| 401 |
+
"eval_f1": 0.7866968765172357,
|
| 402 |
+
"eval_loss": 0.4928380250930786,
|
| 403 |
+
"eval_precision": 0.6708528843499862,
|
| 404 |
+
"eval_recall": 0.9508998435054773,
|
| 405 |
+
"eval_runtime": 57.6166,
|
| 406 |
+
"eval_samples_per_second": 174.308,
|
| 407 |
+
"eval_steps_per_second": 2.725,
|
| 408 |
+
"step": 21000
|
| 409 |
+
}
|
| 410 |
+
],
|
| 411 |
+
"logging_steps": 1000,
|
| 412 |
+
"max_steps": 21195,
|
| 413 |
+
"num_input_tokens_seen": 0,
|
| 414 |
+
"num_train_epochs": 15,
|
| 415 |
+
"save_steps": 1000,
|
| 416 |
+
"stateful_callbacks": {
|
| 417 |
+
"TrainerControl": {
|
| 418 |
+
"args": {
|
| 419 |
+
"should_epoch_stop": false,
|
| 420 |
+
"should_evaluate": false,
|
| 421 |
+
"should_log": false,
|
| 422 |
+
"should_save": true,
|
| 423 |
+
"should_training_stop": false
|
| 424 |
+
},
|
| 425 |
+
"attributes": {}
|
| 426 |
+
}
|
| 427 |
+
},
|
| 428 |
+
"total_flos": 3.173409489802339e+17,
|
| 429 |
+
"train_batch_size": 64,
|
| 430 |
+
"trial_name": null,
|
| 431 |
+
"trial_params": null
|
| 432 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6b36f62b0edb9b7f5539033fb40b0e4058b128ea7755e1d2e55a763b3dd6243
|
| 3 |
+
size 5048
|