Commit
•
26c2b3b
1
Parent(s):
be9f5ef
Upload folder using huggingface_hub
Browse files- config.json +29 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +603 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 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": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.41.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250002
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f648930d317b4184726e68124127dddc0d362ed203d4c0888d375201dff2f94
|
| 3 |
+
size 2239618672
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b3f978a09075f10f517d7028fa3a71775014fac004f831737adb9c03a9fbd26
|
| 3 |
+
size 4479472721
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:426eee929163985089bdfc82ab9f91f32de1d43ccc566ceb2feea6c91e293bf8
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ba07b87b2cc47ca809f85ebc3817bcabcc3101277396f0c4379a442942ee904
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8774532819983097,
|
| 3 |
+
"best_model_checkpoint": "./XLMR_large2-multif-multi-outputs/checkpoint-30000",
|
| 4 |
+
"epoch": 10.76426264800861,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 30000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.35880875493362036,
|
| 13 |
+
"grad_norm": 3.4893088340759277,
|
| 14 |
+
"learning_rate": 4.484304932735426e-07,
|
| 15 |
+
"loss": 0.7002,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.35880875493362036,
|
| 20 |
+
"eval_accuracy": 0.5438490261378545,
|
| 21 |
+
"eval_f1": 0.4920206788042257,
|
| 22 |
+
"eval_loss": 0.6902989149093628,
|
| 23 |
+
"eval_precision": 0.5630144032921811,
|
| 24 |
+
"eval_recall": 0.4369261477045908,
|
| 25 |
+
"eval_runtime": 102.3266,
|
| 26 |
+
"eval_samples_per_second": 96.837,
|
| 27 |
+
"eval_steps_per_second": 3.03,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.7176175098672407,
|
| 32 |
+
"grad_norm": 5.633336067199707,
|
| 33 |
+
"learning_rate": 8.968609865470852e-07,
|
| 34 |
+
"loss": 0.6925,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.7176175098672407,
|
| 39 |
+
"eval_accuracy": 0.5904733070945605,
|
| 40 |
+
"eval_f1": 0.6161558834657586,
|
| 41 |
+
"eval_loss": 0.6669968366622925,
|
| 42 |
+
"eval_precision": 0.5855807263574254,
|
| 43 |
+
"eval_recall": 0.6500998003992016,
|
| 44 |
+
"eval_runtime": 102.5915,
|
| 45 |
+
"eval_samples_per_second": 96.587,
|
| 46 |
+
"eval_steps_per_second": 3.022,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.0764262648008611,
|
| 51 |
+
"grad_norm": 16.99192237854004,
|
| 52 |
+
"learning_rate": 1.345291479820628e-06,
|
| 53 |
+
"loss": 0.6398,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.0764262648008611,
|
| 58 |
+
"eval_accuracy": 0.6895751337168231,
|
| 59 |
+
"eval_f1": 0.6402339181286549,
|
| 60 |
+
"eval_loss": 0.561053454875946,
|
| 61 |
+
"eval_precision": 0.7731638418079096,
|
| 62 |
+
"eval_recall": 0.5463073852295409,
|
| 63 |
+
"eval_runtime": 102.2496,
|
| 64 |
+
"eval_samples_per_second": 96.91,
|
| 65 |
+
"eval_steps_per_second": 3.032,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.4352350197344816,
|
| 70 |
+
"grad_norm": 41.74417495727539,
|
| 71 |
+
"learning_rate": 1.7937219730941704e-06,
|
| 72 |
+
"loss": 0.5207,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.4352350197344816,
|
| 77 |
+
"eval_accuracy": 0.7366030881017257,
|
| 78 |
+
"eval_f1": 0.739988045427376,
|
| 79 |
+
"eval_loss": 0.4386575520038605,
|
| 80 |
+
"eval_precision": 0.7386634844868735,
|
| 81 |
+
"eval_recall": 0.7413173652694611,
|
| 82 |
+
"eval_runtime": 102.4643,
|
| 83 |
+
"eval_samples_per_second": 96.707,
|
| 84 |
+
"eval_steps_per_second": 3.025,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.794043774668102,
|
| 89 |
+
"grad_norm": 16.345550537109375,
|
| 90 |
+
"learning_rate": 1.9730888069371073e-06,
|
| 91 |
+
"loss": 0.436,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.794043774668102,
|
| 96 |
+
"eval_accuracy": 0.7618326773640125,
|
| 97 |
+
"eval_f1": 0.7720687656944176,
|
| 98 |
+
"eval_loss": 0.39330193400382996,
|
| 99 |
+
"eval_precision": 0.7479416167664671,
|
| 100 |
+
"eval_recall": 0.7978043912175649,
|
| 101 |
+
"eval_runtime": 102.2033,
|
| 102 |
+
"eval_samples_per_second": 96.954,
|
| 103 |
+
"eval_steps_per_second": 3.033,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.1528525296017222,
|
| 108 |
+
"grad_norm": 28.18199348449707,
|
| 109 |
+
"learning_rate": 1.9232532642280473e-06,
|
| 110 |
+
"loss": 0.4012,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.1528525296017222,
|
| 115 |
+
"eval_accuracy": 0.7686951256433545,
|
| 116 |
+
"eval_f1": 0.7891056312108944,
|
| 117 |
+
"eval_loss": 0.38640400767326355,
|
| 118 |
+
"eval_precision": 0.7319904404233527,
|
| 119 |
+
"eval_recall": 0.8558882235528942,
|
| 120 |
+
"eval_runtime": 102.4147,
|
| 121 |
+
"eval_samples_per_second": 96.754,
|
| 122 |
+
"eval_steps_per_second": 3.027,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.5116612845353425,
|
| 127 |
+
"grad_norm": 27.081764221191406,
|
| 128 |
+
"learning_rate": 1.8734177215189872e-06,
|
| 129 |
+
"loss": 0.3814,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.5116612845353425,
|
| 134 |
+
"eval_accuracy": 0.7880714501967908,
|
| 135 |
+
"eval_f1": 0.8036649214659686,
|
| 136 |
+
"eval_loss": 0.35638731718063354,
|
| 137 |
+
"eval_precision": 0.7558916637354907,
|
| 138 |
+
"eval_recall": 0.8578842315369262,
|
| 139 |
+
"eval_runtime": 102.3233,
|
| 140 |
+
"eval_samples_per_second": 96.84,
|
| 141 |
+
"eval_steps_per_second": 3.03,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.8704700394689633,
|
| 146 |
+
"grad_norm": 10.015326499938965,
|
| 147 |
+
"learning_rate": 1.8235821788099273e-06,
|
| 148 |
+
"loss": 0.357,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.8704700394689633,
|
| 153 |
+
"eval_accuracy": 0.8010899182561307,
|
| 154 |
+
"eval_f1": 0.7871720116618076,
|
| 155 |
+
"eval_loss": 0.34333741664886475,
|
| 156 |
+
"eval_precision": 0.8574453069865914,
|
| 157 |
+
"eval_recall": 0.7275449101796407,
|
| 158 |
+
"eval_runtime": 102.3749,
|
| 159 |
+
"eval_samples_per_second": 96.791,
|
| 160 |
+
"eval_steps_per_second": 3.028,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.2292787944025836,
|
| 165 |
+
"grad_norm": 19.085002899169922,
|
| 166 |
+
"learning_rate": 1.773746636100867e-06,
|
| 167 |
+
"loss": 0.3338,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.2292787944025836,
|
| 172 |
+
"eval_accuracy": 0.8143102230295691,
|
| 173 |
+
"eval_f1": 0.8099173553719008,
|
| 174 |
+
"eval_loss": 0.3247557282447815,
|
| 175 |
+
"eval_precision": 0.8394004282655246,
|
| 176 |
+
"eval_recall": 0.782435129740519,
|
| 177 |
+
"eval_runtime": 102.3517,
|
| 178 |
+
"eval_samples_per_second": 96.813,
|
| 179 |
+
"eval_steps_per_second": 3.029,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.588087549336204,
|
| 184 |
+
"grad_norm": 43.919654846191406,
|
| 185 |
+
"learning_rate": 1.723911093391807e-06,
|
| 186 |
+
"loss": 0.3121,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.588087549336204,
|
| 191 |
+
"eval_accuracy": 0.8244020587344838,
|
| 192 |
+
"eval_f1": 0.8312645461598138,
|
| 193 |
+
"eval_loss": 0.31208017468452454,
|
| 194 |
+
"eval_precision": 0.8083741984156922,
|
| 195 |
+
"eval_recall": 0.8554890219560878,
|
| 196 |
+
"eval_runtime": 102.3688,
|
| 197 |
+
"eval_samples_per_second": 96.797,
|
| 198 |
+
"eval_steps_per_second": 3.028,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.946896304269824,
|
| 203 |
+
"grad_norm": 17.22640037536621,
|
| 204 |
+
"learning_rate": 1.674075550682747e-06,
|
| 205 |
+
"loss": 0.3073,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.946896304269824,
|
| 210 |
+
"eval_accuracy": 0.8270259360177616,
|
| 211 |
+
"eval_f1": 0.8225672877846791,
|
| 212 |
+
"eval_loss": 0.2976900339126587,
|
| 213 |
+
"eval_precision": 0.8544086021505376,
|
| 214 |
+
"eval_recall": 0.7930139720558882,
|
| 215 |
+
"eval_runtime": 102.258,
|
| 216 |
+
"eval_samples_per_second": 96.902,
|
| 217 |
+
"eval_steps_per_second": 3.032,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.3057050592034445,
|
| 222 |
+
"grad_norm": 12.024229049682617,
|
| 223 |
+
"learning_rate": 1.6242400079736866e-06,
|
| 224 |
+
"loss": 0.28,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.3057050592034445,
|
| 229 |
+
"eval_accuracy": 0.8350994045816934,
|
| 230 |
+
"eval_f1": 0.8450891164201745,
|
| 231 |
+
"eval_loss": 0.29010578989982605,
|
| 232 |
+
"eval_precision": 0.8048031780426147,
|
| 233 |
+
"eval_recall": 0.8896207584830339,
|
| 234 |
+
"eval_runtime": 102.4597,
|
| 235 |
+
"eval_samples_per_second": 96.711,
|
| 236 |
+
"eval_steps_per_second": 3.026,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.664513814137065,
|
| 241 |
+
"grad_norm": 9.77030086517334,
|
| 242 |
+
"learning_rate": 1.5744044652646268e-06,
|
| 243 |
+
"loss": 0.2699,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.664513814137065,
|
| 248 |
+
"eval_accuracy": 0.8451912402866081,
|
| 249 |
+
"eval_f1": 0.8577522255192879,
|
| 250 |
+
"eval_loss": 0.2866370677947998,
|
| 251 |
+
"eval_precision": 0.8010045029442328,
|
| 252 |
+
"eval_recall": 0.9231536926147704,
|
| 253 |
+
"eval_runtime": 102.25,
|
| 254 |
+
"eval_samples_per_second": 96.91,
|
| 255 |
+
"eval_steps_per_second": 3.032,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 5.023322569070685,
|
| 260 |
+
"grad_norm": 26.18376350402832,
|
| 261 |
+
"learning_rate": 1.5245689225555665e-06,
|
| 262 |
+
"loss": 0.2687,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.023322569070685,
|
| 267 |
+
"eval_accuracy": 0.8468059339993945,
|
| 268 |
+
"eval_f1": 0.8382697634775197,
|
| 269 |
+
"eval_loss": 0.28509217500686646,
|
| 270 |
+
"eval_precision": 0.8989945155393053,
|
| 271 |
+
"eval_recall": 0.7852295409181637,
|
| 272 |
+
"eval_runtime": 102.3521,
|
| 273 |
+
"eval_samples_per_second": 96.813,
|
| 274 |
+
"eval_steps_per_second": 3.029,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.382131324004305,
|
| 279 |
+
"grad_norm": 25.679304122924805,
|
| 280 |
+
"learning_rate": 1.4747333798465064e-06,
|
| 281 |
+
"loss": 0.2431,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.382131324004305,
|
| 286 |
+
"eval_accuracy": 0.8506408315672621,
|
| 287 |
+
"eval_f1": 0.8559470508078645,
|
| 288 |
+
"eval_loss": 0.2662178575992584,
|
| 289 |
+
"eval_precision": 0.8352963525835866,
|
| 290 |
+
"eval_recall": 0.8776447105788423,
|
| 291 |
+
"eval_runtime": 103.049,
|
| 292 |
+
"eval_samples_per_second": 96.158,
|
| 293 |
+
"eval_steps_per_second": 3.008,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.740940078937927,
|
| 298 |
+
"grad_norm": 6.820824146270752,
|
| 299 |
+
"learning_rate": 1.4248978371374463e-06,
|
| 300 |
+
"loss": 0.2381,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.740940078937927,
|
| 305 |
+
"eval_accuracy": 0.8564940962761126,
|
| 306 |
+
"eval_f1": 0.8545417348608838,
|
| 307 |
+
"eval_loss": 0.2637253403663635,
|
| 308 |
+
"eval_precision": 0.8764162819974821,
|
| 309 |
+
"eval_recall": 0.8337325349301398,
|
| 310 |
+
"eval_runtime": 102.1936,
|
| 311 |
+
"eval_samples_per_second": 96.963,
|
| 312 |
+
"eval_steps_per_second": 3.033,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 6.099748833871547,
|
| 317 |
+
"grad_norm": 9.834541320800781,
|
| 318 |
+
"learning_rate": 1.3750622944283863e-06,
|
| 319 |
+
"loss": 0.2358,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.099748833871547,
|
| 324 |
+
"eval_accuracy": 0.856695932990211,
|
| 325 |
+
"eval_f1": 0.8512154233025985,
|
| 326 |
+
"eval_loss": 0.28067293763160706,
|
| 327 |
+
"eval_precision": 0.8958976621085134,
|
| 328 |
+
"eval_recall": 0.8107784431137725,
|
| 329 |
+
"eval_runtime": 102.2904,
|
| 330 |
+
"eval_samples_per_second": 96.871,
|
| 331 |
+
"eval_steps_per_second": 3.031,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.458557588805167,
|
| 336 |
+
"grad_norm": 18.847471237182617,
|
| 337 |
+
"learning_rate": 1.325226751719326e-06,
|
| 338 |
+
"loss": 0.2217,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.458557588805167,
|
| 343 |
+
"eval_accuracy": 0.8537693006357856,
|
| 344 |
+
"eval_f1": 0.8575081128921231,
|
| 345 |
+
"eval_loss": 0.27961644530296326,
|
| 346 |
+
"eval_precision": 0.8451250242295019,
|
| 347 |
+
"eval_recall": 0.8702594810379242,
|
| 348 |
+
"eval_runtime": 102.118,
|
| 349 |
+
"eval_samples_per_second": 97.035,
|
| 350 |
+
"eval_steps_per_second": 3.036,
|
| 351 |
+
"step": 18000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.8173663437387875,
|
| 355 |
+
"grad_norm": 34.42753982543945,
|
| 356 |
+
"learning_rate": 1.2753912090102661e-06,
|
| 357 |
+
"loss": 0.2199,
|
| 358 |
+
"step": 19000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.8173663437387875,
|
| 362 |
+
"eval_accuracy": 0.8600262387728328,
|
| 363 |
+
"eval_f1": 0.8621409402643873,
|
| 364 |
+
"eval_loss": 0.2587447166442871,
|
| 365 |
+
"eval_precision": 0.8586418530983964,
|
| 366 |
+
"eval_recall": 0.8656686626746507,
|
| 367 |
+
"eval_runtime": 102.0704,
|
| 368 |
+
"eval_samples_per_second": 97.08,
|
| 369 |
+
"eval_steps_per_second": 3.037,
|
| 370 |
+
"step": 19000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 7.176175098672408,
|
| 374 |
+
"grad_norm": 19.31267547607422,
|
| 375 |
+
"learning_rate": 1.2255556663012058e-06,
|
| 376 |
+
"loss": 0.2101,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 7.176175098672408,
|
| 381 |
+
"eval_accuracy": 0.8607326672721768,
|
| 382 |
+
"eval_f1": 0.863013698630137,
|
| 383 |
+
"eval_loss": 0.26872456073760986,
|
| 384 |
+
"eval_precision": 0.8584123222748815,
|
| 385 |
+
"eval_recall": 0.8676646706586826,
|
| 386 |
+
"eval_runtime": 101.8878,
|
| 387 |
+
"eval_samples_per_second": 97.254,
|
| 388 |
+
"eval_steps_per_second": 3.043,
|
| 389 |
+
"step": 20000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.534983853606028,
|
| 393 |
+
"grad_norm": 3.868898630142212,
|
| 394 |
+
"learning_rate": 1.175720123592146e-06,
|
| 395 |
+
"loss": 0.2088,
|
| 396 |
+
"step": 21000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 7.534983853606028,
|
| 400 |
+
"eval_accuracy": 0.8628519527702089,
|
| 401 |
+
"eval_f1": 0.8607724618379264,
|
| 402 |
+
"eval_loss": 0.26908883452415466,
|
| 403 |
+
"eval_precision": 0.8842348979162281,
|
| 404 |
+
"eval_recall": 0.8385229540918163,
|
| 405 |
+
"eval_runtime": 102.1993,
|
| 406 |
+
"eval_samples_per_second": 96.958,
|
| 407 |
+
"eval_steps_per_second": 3.033,
|
| 408 |
+
"step": 21000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 7.893792608539648,
|
| 412 |
+
"grad_norm": 21.03769302368164,
|
| 413 |
+
"learning_rate": 1.1258845808830857e-06,
|
| 414 |
+
"loss": 0.2048,
|
| 415 |
+
"step": 22000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 7.893792608539648,
|
| 419 |
+
"eval_accuracy": 0.8614390957715209,
|
| 420 |
+
"eval_f1": 0.8651674359226161,
|
| 421 |
+
"eval_loss": 0.2696681320667267,
|
| 422 |
+
"eval_precision": 0.8515368258264063,
|
| 423 |
+
"eval_recall": 0.8792415169660679,
|
| 424 |
+
"eval_runtime": 101.9575,
|
| 425 |
+
"eval_samples_per_second": 97.188,
|
| 426 |
+
"eval_steps_per_second": 3.04,
|
| 427 |
+
"step": 22000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 8.25260136347327,
|
| 431 |
+
"grad_norm": 20.60344886779785,
|
| 432 |
+
"learning_rate": 1.0760490381740256e-06,
|
| 433 |
+
"loss": 0.1981,
|
| 434 |
+
"step": 23000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.25260136347327,
|
| 438 |
+
"eval_accuracy": 0.86154001412857,
|
| 439 |
+
"eval_f1": 0.8633466135458168,
|
| 440 |
+
"eval_loss": 0.2807515561580658,
|
| 441 |
+
"eval_precision": 0.8616302186878728,
|
| 442 |
+
"eval_recall": 0.8650698602794411,
|
| 443 |
+
"eval_runtime": 102.0894,
|
| 444 |
+
"eval_samples_per_second": 97.062,
|
| 445 |
+
"eval_steps_per_second": 3.037,
|
| 446 |
+
"step": 23000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.611410118406889,
|
| 450 |
+
"grad_norm": 28.312131881713867,
|
| 451 |
+
"learning_rate": 1.0262134954649656e-06,
|
| 452 |
+
"loss": 0.1984,
|
| 453 |
+
"step": 24000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 8.611410118406889,
|
| 457 |
+
"eval_accuracy": 0.86154001412857,
|
| 458 |
+
"eval_f1": 0.861442132902444,
|
| 459 |
+
"eval_loss": 0.2837580144405365,
|
| 460 |
+
"eval_precision": 0.8718315617334423,
|
| 461 |
+
"eval_recall": 0.8512974051896207,
|
| 462 |
+
"eval_runtime": 102.0456,
|
| 463 |
+
"eval_samples_per_second": 97.104,
|
| 464 |
+
"eval_steps_per_second": 3.038,
|
| 465 |
+
"step": 24000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 8.97021887334051,
|
| 469 |
+
"grad_norm": 19.9366512298584,
|
| 470 |
+
"learning_rate": 9.763779527559055e-07,
|
| 471 |
+
"loss": 0.1921,
|
| 472 |
+
"step": 25000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 8.97021887334051,
|
| 476 |
+
"eval_accuracy": 0.8596225653446362,
|
| 477 |
+
"eval_f1": 0.8671061431164613,
|
| 478 |
+
"eval_loss": 0.2752152383327484,
|
| 479 |
+
"eval_precision": 0.8315924500641378,
|
| 480 |
+
"eval_recall": 0.9057884231536926,
|
| 481 |
+
"eval_runtime": 101.9498,
|
| 482 |
+
"eval_samples_per_second": 97.195,
|
| 483 |
+
"eval_steps_per_second": 3.041,
|
| 484 |
+
"step": 25000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 9.32902762827413,
|
| 488 |
+
"grad_norm": 32.3852653503418,
|
| 489 |
+
"learning_rate": 9.265424100468454e-07,
|
| 490 |
+
"loss": 0.1874,
|
| 491 |
+
"step": 26000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.32902762827413,
|
| 495 |
+
"eval_accuracy": 0.8653749116964375,
|
| 496 |
+
"eval_f1": 0.8631794871794872,
|
| 497 |
+
"eval_loss": 0.30365535616874695,
|
| 498 |
+
"eval_precision": 0.8877637130801688,
|
| 499 |
+
"eval_recall": 0.8399201596806387,
|
| 500 |
+
"eval_runtime": 101.9607,
|
| 501 |
+
"eval_samples_per_second": 97.185,
|
| 502 |
+
"eval_steps_per_second": 3.04,
|
| 503 |
+
"step": 26000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.68783638320775,
|
| 507 |
+
"grad_norm": 24.581174850463867,
|
| 508 |
+
"learning_rate": 8.767068673377853e-07,
|
| 509 |
+
"loss": 0.1864,
|
| 510 |
+
"step": 27000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 9.68783638320775,
|
| 514 |
+
"eval_accuracy": 0.860228075486931,
|
| 515 |
+
"eval_f1": 0.859405136534362,
|
| 516 |
+
"eval_loss": 0.30304282903671265,
|
| 517 |
+
"eval_precision": 0.8744061144391655,
|
| 518 |
+
"eval_recall": 0.8449101796407186,
|
| 519 |
+
"eval_runtime": 101.9816,
|
| 520 |
+
"eval_samples_per_second": 97.165,
|
| 521 |
+
"eval_steps_per_second": 3.04,
|
| 522 |
+
"step": 27000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 10.04664513814137,
|
| 526 |
+
"grad_norm": 81.2057113647461,
|
| 527 |
+
"learning_rate": 8.268713246287253e-07,
|
| 528 |
+
"loss": 0.182,
|
| 529 |
+
"step": 28000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 10.04664513814137,
|
| 533 |
+
"eval_accuracy": 0.8641638914118478,
|
| 534 |
+
"eval_f1": 0.8636271529888551,
|
| 535 |
+
"eval_loss": 0.30453670024871826,
|
| 536 |
+
"eval_precision": 0.8769547325102881,
|
| 537 |
+
"eval_recall": 0.8506986027944112,
|
| 538 |
+
"eval_runtime": 101.9771,
|
| 539 |
+
"eval_samples_per_second": 97.169,
|
| 540 |
+
"eval_steps_per_second": 3.04,
|
| 541 |
+
"step": 28000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 10.405453893074991,
|
| 545 |
+
"grad_norm": 9.566941261291504,
|
| 546 |
+
"learning_rate": 7.770357819196651e-07,
|
| 547 |
+
"loss": 0.1731,
|
| 548 |
+
"step": 29000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 10.405453893074991,
|
| 552 |
+
"eval_accuracy": 0.8622464426279141,
|
| 553 |
+
"eval_f1": 0.8650785806068992,
|
| 554 |
+
"eval_loss": 0.3294801712036133,
|
| 555 |
+
"eval_precision": 0.8568631290385745,
|
| 556 |
+
"eval_recall": 0.8734530938123752,
|
| 557 |
+
"eval_runtime": 102.0872,
|
| 558 |
+
"eval_samples_per_second": 97.064,
|
| 559 |
+
"eval_steps_per_second": 3.037,
|
| 560 |
+
"step": 29000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 10.76426264800861,
|
| 564 |
+
"grad_norm": 47.86115646362305,
|
| 565 |
+
"learning_rate": 7.272002392106049e-07,
|
| 566 |
+
"loss": 0.1785,
|
| 567 |
+
"step": 30000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 10.76426264800861,
|
| 571 |
+
"eval_accuracy": 0.8683015440508629,
|
| 572 |
+
"eval_f1": 0.8774532819983097,
|
| 573 |
+
"eval_loss": 0.2851540446281433,
|
| 574 |
+
"eval_precision": 0.8285156942720341,
|
| 575 |
+
"eval_recall": 0.9325349301397206,
|
| 576 |
+
"eval_runtime": 101.9096,
|
| 577 |
+
"eval_samples_per_second": 97.233,
|
| 578 |
+
"eval_steps_per_second": 3.042,
|
| 579 |
+
"step": 30000
|
| 580 |
+
}
|
| 581 |
+
],
|
| 582 |
+
"logging_steps": 1000,
|
| 583 |
+
"max_steps": 44592,
|
| 584 |
+
"num_input_tokens_seen": 0,
|
| 585 |
+
"num_train_epochs": 16,
|
| 586 |
+
"save_steps": 1000,
|
| 587 |
+
"stateful_callbacks": {
|
| 588 |
+
"TrainerControl": {
|
| 589 |
+
"args": {
|
| 590 |
+
"should_epoch_stop": false,
|
| 591 |
+
"should_evaluate": false,
|
| 592 |
+
"should_log": false,
|
| 593 |
+
"should_save": true,
|
| 594 |
+
"should_training_stop": false
|
| 595 |
+
},
|
| 596 |
+
"attributes": {}
|
| 597 |
+
}
|
| 598 |
+
},
|
| 599 |
+
"total_flos": 7.694222788593573e+17,
|
| 600 |
+
"train_batch_size": 32,
|
| 601 |
+
"trial_name": null,
|
| 602 |
+
"trial_params": null
|
| 603 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a684cbebfb0bf65441eb9be784da28aac0372be258ac130d836a6554b72db9b9
|
| 3 |
+
size 5112
|