Upload 7 files
Browse files- config.json +128 -0
- preprocessor_config.json +9 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +913 -0
- training_args.bin +3 -0
- vocab.json +1 -0
config.json
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "soba1911/xlsr-wav2vec2",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSpeechClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 768,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": true,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": true,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.0,
|
| 56 |
+
"finetuning_task": "wav2vec2_clf",
|
| 57 |
+
"gradient_checkpointing": false,
|
| 58 |
+
"hidden_act": "gelu",
|
| 59 |
+
"hidden_dropout": 0.1,
|
| 60 |
+
"hidden_size": 1024,
|
| 61 |
+
"id2label": {
|
| 62 |
+
"0": "bonafide",
|
| 63 |
+
"1": "spoof"
|
| 64 |
+
},
|
| 65 |
+
"initializer_range": 0.02,
|
| 66 |
+
"intermediate_size": 4096,
|
| 67 |
+
"label2id": {
|
| 68 |
+
"bonafide": 0,
|
| 69 |
+
"spoof": 1
|
| 70 |
+
},
|
| 71 |
+
"layer_norm_eps": 1e-05,
|
| 72 |
+
"layerdrop": 0.1,
|
| 73 |
+
"mask_channel_length": 10,
|
| 74 |
+
"mask_channel_min_space": 1,
|
| 75 |
+
"mask_channel_other": 0.0,
|
| 76 |
+
"mask_channel_prob": 0.0,
|
| 77 |
+
"mask_channel_selection": "static",
|
| 78 |
+
"mask_feature_length": 10,
|
| 79 |
+
"mask_feature_min_masks": 0,
|
| 80 |
+
"mask_feature_prob": 0.0,
|
| 81 |
+
"mask_time_length": 10,
|
| 82 |
+
"mask_time_min_masks": 2,
|
| 83 |
+
"mask_time_min_space": 1,
|
| 84 |
+
"mask_time_other": 0.0,
|
| 85 |
+
"mask_time_prob": 0.075,
|
| 86 |
+
"mask_time_selection": "static",
|
| 87 |
+
"model_type": "wav2vec2",
|
| 88 |
+
"num_adapter_layers": 3,
|
| 89 |
+
"num_attention_heads": 16,
|
| 90 |
+
"num_codevector_groups": 2,
|
| 91 |
+
"num_codevectors_per_group": 320,
|
| 92 |
+
"num_conv_pos_embedding_groups": 16,
|
| 93 |
+
"num_conv_pos_embeddings": 128,
|
| 94 |
+
"num_feat_extract_layers": 7,
|
| 95 |
+
"num_hidden_layers": 24,
|
| 96 |
+
"num_negatives": 100,
|
| 97 |
+
"output_hidden_size": 1024,
|
| 98 |
+
"pad_token_id": 0,
|
| 99 |
+
"pooling_mode": "mean",
|
| 100 |
+
"problem_type": "single_label_classification",
|
| 101 |
+
"proj_codevector_dim": 768,
|
| 102 |
+
"tdnn_dilation": [
|
| 103 |
+
1,
|
| 104 |
+
2,
|
| 105 |
+
3,
|
| 106 |
+
1,
|
| 107 |
+
1
|
| 108 |
+
],
|
| 109 |
+
"tdnn_dim": [
|
| 110 |
+
512,
|
| 111 |
+
512,
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
1500
|
| 115 |
+
],
|
| 116 |
+
"tdnn_kernel": [
|
| 117 |
+
5,
|
| 118 |
+
3,
|
| 119 |
+
3,
|
| 120 |
+
1,
|
| 121 |
+
1
|
| 122 |
+
],
|
| 123 |
+
"torch_dtype": "float32",
|
| 124 |
+
"transformers_version": "4.41.0.dev0",
|
| 125 |
+
"use_weighted_layer_sum": false,
|
| 126 |
+
"vocab_size": 32,
|
| 127 |
+
"xvector_output_dim": 512
|
| 128 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fe258b7acd770c26a92648df46edefefd3201139dbb23982e694e83f8060c2e
|
| 3 |
+
size 14308
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43d9476704a2b5fc8a9f2cd4f2b882e6f0387d6e8e661a51cbf47cb22502edbe
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,913 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.24509803921568626,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 550,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004456327985739751,
|
| 13 |
+
"grad_norm": 0.7227747440338135,
|
| 14 |
+
"learning_rate": 0.00019636363636363636,
|
| 15 |
+
"loss": 0.364,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004456327985739751,
|
| 20 |
+
"eval_accuracy": 0.89683598279953,
|
| 21 |
+
"eval_loss": 0.3638981878757477,
|
| 22 |
+
"eval_runtime": 537.6403,
|
| 23 |
+
"eval_samples_per_second": 8.348,
|
| 24 |
+
"eval_steps_per_second": 2.087,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.008912655971479501,
|
| 29 |
+
"grad_norm": 0.0924869254231453,
|
| 30 |
+
"learning_rate": 0.00019272727272727274,
|
| 31 |
+
"loss": 0.3247,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.008912655971479501,
|
| 36 |
+
"eval_accuracy": 0.89683598279953,
|
| 37 |
+
"eval_loss": 0.5152587890625,
|
| 38 |
+
"eval_runtime": 533.0372,
|
| 39 |
+
"eval_samples_per_second": 8.42,
|
| 40 |
+
"eval_steps_per_second": 2.105,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.013368983957219251,
|
| 45 |
+
"grad_norm": 0.23558691143989563,
|
| 46 |
+
"learning_rate": 0.0001890909090909091,
|
| 47 |
+
"loss": 0.4074,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.013368983957219251,
|
| 52 |
+
"eval_accuracy": 0.89683598279953,
|
| 53 |
+
"eval_loss": 0.3966202735900879,
|
| 54 |
+
"eval_runtime": 532.3437,
|
| 55 |
+
"eval_samples_per_second": 8.431,
|
| 56 |
+
"eval_steps_per_second": 2.108,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.017825311942959002,
|
| 61 |
+
"grad_norm": 0.7453870177268982,
|
| 62 |
+
"learning_rate": 0.00018545454545454545,
|
| 63 |
+
"loss": 0.2989,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.017825311942959002,
|
| 68 |
+
"eval_accuracy": 0.89683598279953,
|
| 69 |
+
"eval_loss": 0.33440741896629333,
|
| 70 |
+
"eval_runtime": 532.0041,
|
| 71 |
+
"eval_samples_per_second": 8.436,
|
| 72 |
+
"eval_steps_per_second": 2.109,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.022281639928698752,
|
| 77 |
+
"grad_norm": 6.811055660247803,
|
| 78 |
+
"learning_rate": 0.00018181818181818183,
|
| 79 |
+
"loss": 0.3399,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.022281639928698752,
|
| 84 |
+
"eval_accuracy": 0.89683598279953,
|
| 85 |
+
"eval_loss": 0.32954567670822144,
|
| 86 |
+
"eval_runtime": 536.9612,
|
| 87 |
+
"eval_samples_per_second": 8.358,
|
| 88 |
+
"eval_steps_per_second": 2.09,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.026737967914438502,
|
| 93 |
+
"grad_norm": 1.3061631917953491,
|
| 94 |
+
"learning_rate": 0.0001781818181818182,
|
| 95 |
+
"loss": 0.3437,
|
| 96 |
+
"step": 60
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.026737967914438502,
|
| 100 |
+
"eval_accuracy": 0.89683598279953,
|
| 101 |
+
"eval_loss": 0.3265528976917267,
|
| 102 |
+
"eval_runtime": 533.3224,
|
| 103 |
+
"eval_samples_per_second": 8.415,
|
| 104 |
+
"eval_steps_per_second": 2.104,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.031194295900178252,
|
| 109 |
+
"grad_norm": 1.7616266012191772,
|
| 110 |
+
"learning_rate": 0.00017454545454545454,
|
| 111 |
+
"loss": 0.3749,
|
| 112 |
+
"step": 70
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.031194295900178252,
|
| 116 |
+
"eval_accuracy": 0.89683598279953,
|
| 117 |
+
"eval_loss": 0.3122697174549103,
|
| 118 |
+
"eval_runtime": 530.7411,
|
| 119 |
+
"eval_samples_per_second": 8.456,
|
| 120 |
+
"eval_steps_per_second": 2.114,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.035650623885918005,
|
| 125 |
+
"grad_norm": 1.1275932788848877,
|
| 126 |
+
"learning_rate": 0.0001709090909090909,
|
| 127 |
+
"loss": 0.4267,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.035650623885918005,
|
| 132 |
+
"eval_accuracy": 0.89683598279953,
|
| 133 |
+
"eval_loss": 0.23432780802249908,
|
| 134 |
+
"eval_runtime": 533.9058,
|
| 135 |
+
"eval_samples_per_second": 8.406,
|
| 136 |
+
"eval_steps_per_second": 2.101,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.040106951871657755,
|
| 141 |
+
"grad_norm": 1.387789249420166,
|
| 142 |
+
"learning_rate": 0.00016727272727272728,
|
| 143 |
+
"loss": 0.4221,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.040106951871657755,
|
| 148 |
+
"eval_accuracy": 0.89683598279953,
|
| 149 |
+
"eval_loss": 0.21733854711055756,
|
| 150 |
+
"eval_runtime": 533.5436,
|
| 151 |
+
"eval_samples_per_second": 8.412,
|
| 152 |
+
"eval_steps_per_second": 2.103,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.044563279857397504,
|
| 157 |
+
"grad_norm": 9.95677375793457,
|
| 158 |
+
"learning_rate": 0.00016363636363636366,
|
| 159 |
+
"loss": 0.2292,
|
| 160 |
+
"step": 100
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.044563279857397504,
|
| 164 |
+
"eval_accuracy": 0.89683598279953,
|
| 165 |
+
"eval_loss": 0.3393175005912781,
|
| 166 |
+
"eval_runtime": 537.6972,
|
| 167 |
+
"eval_samples_per_second": 8.347,
|
| 168 |
+
"eval_steps_per_second": 2.087,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.049019607843137254,
|
| 173 |
+
"grad_norm": 1.0864927768707275,
|
| 174 |
+
"learning_rate": 0.00016,
|
| 175 |
+
"loss": 0.4339,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.049019607843137254,
|
| 180 |
+
"eval_accuracy": 0.89683598279953,
|
| 181 |
+
"eval_loss": 0.28164002299308777,
|
| 182 |
+
"eval_runtime": 531.492,
|
| 183 |
+
"eval_samples_per_second": 8.444,
|
| 184 |
+
"eval_steps_per_second": 2.111,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.053475935828877004,
|
| 189 |
+
"grad_norm": 1.7070204019546509,
|
| 190 |
+
"learning_rate": 0.00015636363636363637,
|
| 191 |
+
"loss": 0.4143,
|
| 192 |
+
"step": 120
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.053475935828877004,
|
| 196 |
+
"eval_accuracy": 0.8963903784751892,
|
| 197 |
+
"eval_loss": 0.20752401649951935,
|
| 198 |
+
"eval_runtime": 538.1828,
|
| 199 |
+
"eval_samples_per_second": 8.339,
|
| 200 |
+
"eval_steps_per_second": 2.085,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.057932263814616754,
|
| 205 |
+
"grad_norm": 0.08961692452430725,
|
| 206 |
+
"learning_rate": 0.00015272727272727275,
|
| 207 |
+
"loss": 0.2757,
|
| 208 |
+
"step": 130
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.057932263814616754,
|
| 212 |
+
"eval_accuracy": 0.89683598279953,
|
| 213 |
+
"eval_loss": 0.1715579330921173,
|
| 214 |
+
"eval_runtime": 534.1189,
|
| 215 |
+
"eval_samples_per_second": 8.403,
|
| 216 |
+
"eval_steps_per_second": 2.101,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.062388591800356503,
|
| 221 |
+
"grad_norm": 1.3324838876724243,
|
| 222 |
+
"learning_rate": 0.0001490909090909091,
|
| 223 |
+
"loss": 0.1588,
|
| 224 |
+
"step": 140
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.062388591800356503,
|
| 228 |
+
"eval_accuracy": 0.89683598279953,
|
| 229 |
+
"eval_loss": 0.149879589676857,
|
| 230 |
+
"eval_runtime": 530.7418,
|
| 231 |
+
"eval_samples_per_second": 8.456,
|
| 232 |
+
"eval_steps_per_second": 2.114,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.06684491978609626,
|
| 237 |
+
"grad_norm": 2.0198991298675537,
|
| 238 |
+
"learning_rate": 0.00014545454545454546,
|
| 239 |
+
"loss": 0.4453,
|
| 240 |
+
"step": 150
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.06684491978609626,
|
| 244 |
+
"eval_accuracy": 0.89683598279953,
|
| 245 |
+
"eval_loss": 0.2379792034626007,
|
| 246 |
+
"eval_runtime": 530.3365,
|
| 247 |
+
"eval_samples_per_second": 8.463,
|
| 248 |
+
"eval_steps_per_second": 2.116,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.07130124777183601,
|
| 253 |
+
"grad_norm": 0.3087630867958069,
|
| 254 |
+
"learning_rate": 0.00014181818181818184,
|
| 255 |
+
"loss": 0.2505,
|
| 256 |
+
"step": 160
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.07130124777183601,
|
| 260 |
+
"eval_accuracy": 0.89683598279953,
|
| 261 |
+
"eval_loss": 0.3300795257091522,
|
| 262 |
+
"eval_runtime": 529.0534,
|
| 263 |
+
"eval_samples_per_second": 8.483,
|
| 264 |
+
"eval_steps_per_second": 2.121,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.07575757575757576,
|
| 269 |
+
"grad_norm": 2.6436047554016113,
|
| 270 |
+
"learning_rate": 0.0001381818181818182,
|
| 271 |
+
"loss": 0.2654,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.07575757575757576,
|
| 276 |
+
"eval_accuracy": 0.89683598279953,
|
| 277 |
+
"eval_loss": 0.22237823903560638,
|
| 278 |
+
"eval_runtime": 536.9554,
|
| 279 |
+
"eval_samples_per_second": 8.358,
|
| 280 |
+
"eval_steps_per_second": 2.09,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.08021390374331551,
|
| 285 |
+
"grad_norm": 0.9066676497459412,
|
| 286 |
+
"learning_rate": 0.00013454545454545455,
|
| 287 |
+
"loss": 0.3018,
|
| 288 |
+
"step": 180
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.08021390374331551,
|
| 292 |
+
"eval_accuracy": 0.89683598279953,
|
| 293 |
+
"eval_loss": 0.2531951069831848,
|
| 294 |
+
"eval_runtime": 532.2386,
|
| 295 |
+
"eval_samples_per_second": 8.432,
|
| 296 |
+
"eval_steps_per_second": 2.108,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.08467023172905526,
|
| 301 |
+
"grad_norm": 0.10262551158666611,
|
| 302 |
+
"learning_rate": 0.00013090909090909093,
|
| 303 |
+
"loss": 0.2325,
|
| 304 |
+
"step": 190
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.08467023172905526,
|
| 308 |
+
"eval_accuracy": 0.89683598279953,
|
| 309 |
+
"eval_loss": 0.22432851791381836,
|
| 310 |
+
"eval_runtime": 531.5973,
|
| 311 |
+
"eval_samples_per_second": 8.442,
|
| 312 |
+
"eval_steps_per_second": 2.111,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.08912655971479501,
|
| 317 |
+
"grad_norm": 0.20511843264102936,
|
| 318 |
+
"learning_rate": 0.00012727272727272728,
|
| 319 |
+
"loss": 0.2641,
|
| 320 |
+
"step": 200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.08912655971479501,
|
| 324 |
+
"eval_accuracy": 0.89683598279953,
|
| 325 |
+
"eval_loss": 0.14137917757034302,
|
| 326 |
+
"eval_runtime": 528.9957,
|
| 327 |
+
"eval_samples_per_second": 8.484,
|
| 328 |
+
"eval_steps_per_second": 2.121,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.09358288770053476,
|
| 333 |
+
"grad_norm": 0.9824792742729187,
|
| 334 |
+
"learning_rate": 0.00012363636363636364,
|
| 335 |
+
"loss": 0.1497,
|
| 336 |
+
"step": 210
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.09358288770053476,
|
| 340 |
+
"eval_accuracy": 0.89683598279953,
|
| 341 |
+
"eval_loss": 0.12781496345996857,
|
| 342 |
+
"eval_runtime": 532.3045,
|
| 343 |
+
"eval_samples_per_second": 8.431,
|
| 344 |
+
"eval_steps_per_second": 2.108,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.09803921568627451,
|
| 349 |
+
"grad_norm": 0.29042425751686096,
|
| 350 |
+
"learning_rate": 0.00012,
|
| 351 |
+
"loss": 0.1536,
|
| 352 |
+
"step": 220
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.09803921568627451,
|
| 356 |
+
"eval_accuracy": 0.9380570650100708,
|
| 357 |
+
"eval_loss": 0.14640431106090546,
|
| 358 |
+
"eval_runtime": 535.3538,
|
| 359 |
+
"eval_samples_per_second": 8.383,
|
| 360 |
+
"eval_steps_per_second": 2.096,
|
| 361 |
+
"step": 220
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.10249554367201426,
|
| 365 |
+
"grad_norm": 0.5411375761032104,
|
| 366 |
+
"learning_rate": 0.00011636363636363636,
|
| 367 |
+
"loss": 0.1801,
|
| 368 |
+
"step": 230
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.10249554367201426,
|
| 372 |
+
"eval_accuracy": 0.9358288645744324,
|
| 373 |
+
"eval_loss": 0.1414562165737152,
|
| 374 |
+
"eval_runtime": 533.0939,
|
| 375 |
+
"eval_samples_per_second": 8.419,
|
| 376 |
+
"eval_steps_per_second": 2.105,
|
| 377 |
+
"step": 230
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.10695187165775401,
|
| 381 |
+
"grad_norm": 5.630716323852539,
|
| 382 |
+
"learning_rate": 0.00011272727272727272,
|
| 383 |
+
"loss": 0.1344,
|
| 384 |
+
"step": 240
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.10695187165775401,
|
| 388 |
+
"eval_accuracy": 0.9844028353691101,
|
| 389 |
+
"eval_loss": 0.08324988931417465,
|
| 390 |
+
"eval_runtime": 536.1639,
|
| 391 |
+
"eval_samples_per_second": 8.371,
|
| 392 |
+
"eval_steps_per_second": 2.093,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.11140819964349376,
|
| 397 |
+
"grad_norm": 0.27143993973731995,
|
| 398 |
+
"learning_rate": 0.00010909090909090909,
|
| 399 |
+
"loss": 0.1722,
|
| 400 |
+
"step": 250
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.11140819964349376,
|
| 404 |
+
"eval_accuracy": 0.9861853718757629,
|
| 405 |
+
"eval_loss": 0.060878392308950424,
|
| 406 |
+
"eval_runtime": 533.7467,
|
| 407 |
+
"eval_samples_per_second": 8.408,
|
| 408 |
+
"eval_steps_per_second": 2.102,
|
| 409 |
+
"step": 250
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.11586452762923351,
|
| 413 |
+
"grad_norm": 0.6671731472015381,
|
| 414 |
+
"learning_rate": 0.00010545454545454545,
|
| 415 |
+
"loss": 0.0684,
|
| 416 |
+
"step": 260
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.11586452762923351,
|
| 420 |
+
"eval_accuracy": 0.8997326493263245,
|
| 421 |
+
"eval_loss": 0.19059808552265167,
|
| 422 |
+
"eval_runtime": 537.3352,
|
| 423 |
+
"eval_samples_per_second": 8.352,
|
| 424 |
+
"eval_steps_per_second": 2.088,
|
| 425 |
+
"step": 260
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.12032085561497326,
|
| 429 |
+
"grad_norm": 0.007157750893384218,
|
| 430 |
+
"learning_rate": 0.00010181818181818181,
|
| 431 |
+
"loss": 0.2185,
|
| 432 |
+
"step": 270
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.12032085561497326,
|
| 436 |
+
"eval_accuracy": 0.9703654050827026,
|
| 437 |
+
"eval_loss": 0.07430911809206009,
|
| 438 |
+
"eval_runtime": 534.3595,
|
| 439 |
+
"eval_samples_per_second": 8.399,
|
| 440 |
+
"eval_steps_per_second": 2.1,
|
| 441 |
+
"step": 270
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.12477718360071301,
|
| 445 |
+
"grad_norm": 0.10907144099473953,
|
| 446 |
+
"learning_rate": 9.818181818181818e-05,
|
| 447 |
+
"loss": 0.0562,
|
| 448 |
+
"step": 280
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.12477718360071301,
|
| 452 |
+
"eval_accuracy": 0.9839572310447693,
|
| 453 |
+
"eval_loss": 0.046000149101018906,
|
| 454 |
+
"eval_runtime": 532.5534,
|
| 455 |
+
"eval_samples_per_second": 8.427,
|
| 456 |
+
"eval_steps_per_second": 2.107,
|
| 457 |
+
"step": 280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.12923351158645277,
|
| 461 |
+
"grad_norm": 0.004431632813066244,
|
| 462 |
+
"learning_rate": 9.454545454545455e-05,
|
| 463 |
+
"loss": 0.007,
|
| 464 |
+
"step": 290
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.12923351158645277,
|
| 468 |
+
"eval_accuracy": 0.9895276427268982,
|
| 469 |
+
"eval_loss": 0.03365661948919296,
|
| 470 |
+
"eval_runtime": 539.0883,
|
| 471 |
+
"eval_samples_per_second": 8.325,
|
| 472 |
+
"eval_steps_per_second": 2.081,
|
| 473 |
+
"step": 290
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.13368983957219252,
|
| 477 |
+
"grad_norm": 0.14239944517612457,
|
| 478 |
+
"learning_rate": 9.090909090909092e-05,
|
| 479 |
+
"loss": 0.1054,
|
| 480 |
+
"step": 300
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.13368983957219252,
|
| 484 |
+
"eval_accuracy": 0.9890819787979126,
|
| 485 |
+
"eval_loss": 0.03497695177793503,
|
| 486 |
+
"eval_runtime": 530.7114,
|
| 487 |
+
"eval_samples_per_second": 8.457,
|
| 488 |
+
"eval_steps_per_second": 2.114,
|
| 489 |
+
"step": 300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.13814616755793227,
|
| 493 |
+
"grad_norm": 0.19534932076931,
|
| 494 |
+
"learning_rate": 8.727272727272727e-05,
|
| 495 |
+
"loss": 0.0074,
|
| 496 |
+
"step": 310
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.13814616755793227,
|
| 500 |
+
"eval_accuracy": 0.9815062284469604,
|
| 501 |
+
"eval_loss": 0.055771518498659134,
|
| 502 |
+
"eval_runtime": 540.1438,
|
| 503 |
+
"eval_samples_per_second": 8.309,
|
| 504 |
+
"eval_steps_per_second": 2.077,
|
| 505 |
+
"step": 310
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.14260249554367202,
|
| 509 |
+
"grad_norm": 0.14106573164463043,
|
| 510 |
+
"learning_rate": 8.363636363636364e-05,
|
| 511 |
+
"loss": 0.0069,
|
| 512 |
+
"step": 320
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.14260249554367202,
|
| 516 |
+
"eval_accuracy": 0.9752673506736755,
|
| 517 |
+
"eval_loss": 0.07411307096481323,
|
| 518 |
+
"eval_runtime": 530.0836,
|
| 519 |
+
"eval_samples_per_second": 8.467,
|
| 520 |
+
"eval_steps_per_second": 2.117,
|
| 521 |
+
"step": 320
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.14705882352941177,
|
| 525 |
+
"grad_norm": 0.04756563529372215,
|
| 526 |
+
"learning_rate": 8e-05,
|
| 527 |
+
"loss": 0.0881,
|
| 528 |
+
"step": 330
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.14705882352941177,
|
| 532 |
+
"eval_accuracy": 0.9884135723114014,
|
| 533 |
+
"eval_loss": 0.03824571892619133,
|
| 534 |
+
"eval_runtime": 529.2936,
|
| 535 |
+
"eval_samples_per_second": 8.479,
|
| 536 |
+
"eval_steps_per_second": 2.12,
|
| 537 |
+
"step": 330
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.15151515151515152,
|
| 541 |
+
"grad_norm": 0.008182384073734283,
|
| 542 |
+
"learning_rate": 7.636363636363637e-05,
|
| 543 |
+
"loss": 0.047,
|
| 544 |
+
"step": 340
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.15151515151515152,
|
| 548 |
+
"eval_accuracy": 0.9779411554336548,
|
| 549 |
+
"eval_loss": 0.07092902809381485,
|
| 550 |
+
"eval_runtime": 530.9951,
|
| 551 |
+
"eval_samples_per_second": 8.452,
|
| 552 |
+
"eval_steps_per_second": 2.113,
|
| 553 |
+
"step": 340
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.15597147950089127,
|
| 557 |
+
"grad_norm": 6.055085182189941,
|
| 558 |
+
"learning_rate": 7.272727272727273e-05,
|
| 559 |
+
"loss": 0.1135,
|
| 560 |
+
"step": 350
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.15597147950089127,
|
| 564 |
+
"eval_accuracy": 0.9935383200645447,
|
| 565 |
+
"eval_loss": 0.02391628548502922,
|
| 566 |
+
"eval_runtime": 531.8853,
|
| 567 |
+
"eval_samples_per_second": 8.438,
|
| 568 |
+
"eval_steps_per_second": 2.109,
|
| 569 |
+
"step": 350
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.16042780748663102,
|
| 573 |
+
"grad_norm": 2.0424458980560303,
|
| 574 |
+
"learning_rate": 6.90909090909091e-05,
|
| 575 |
+
"loss": 0.1708,
|
| 576 |
+
"step": 360
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.16042780748663102,
|
| 580 |
+
"eval_accuracy": 0.9844028353691101,
|
| 581 |
+
"eval_loss": 0.0482899434864521,
|
| 582 |
+
"eval_runtime": 538.9554,
|
| 583 |
+
"eval_samples_per_second": 8.327,
|
| 584 |
+
"eval_steps_per_second": 2.082,
|
| 585 |
+
"step": 360
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.16488413547237077,
|
| 589 |
+
"grad_norm": 0.008309995755553246,
|
| 590 |
+
"learning_rate": 6.545454545454546e-05,
|
| 591 |
+
"loss": 0.0053,
|
| 592 |
+
"step": 370
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.16488413547237077,
|
| 596 |
+
"eval_accuracy": 0.9977718591690063,
|
| 597 |
+
"eval_loss": 0.011557623744010925,
|
| 598 |
+
"eval_runtime": 536.7458,
|
| 599 |
+
"eval_samples_per_second": 8.361,
|
| 600 |
+
"eval_steps_per_second": 2.09,
|
| 601 |
+
"step": 370
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.16934046345811052,
|
| 605 |
+
"grad_norm": 0.0617559477686882,
|
| 606 |
+
"learning_rate": 6.181818181818182e-05,
|
| 607 |
+
"loss": 0.0257,
|
| 608 |
+
"step": 380
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.16934046345811052,
|
| 612 |
+
"eval_accuracy": 0.9979946613311768,
|
| 613 |
+
"eval_loss": 0.011457420885562897,
|
| 614 |
+
"eval_runtime": 538.0907,
|
| 615 |
+
"eval_samples_per_second": 8.341,
|
| 616 |
+
"eval_steps_per_second": 2.085,
|
| 617 |
+
"step": 380
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.17379679144385027,
|
| 621 |
+
"grad_norm": 0.1585519164800644,
|
| 622 |
+
"learning_rate": 5.818181818181818e-05,
|
| 623 |
+
"loss": 0.0978,
|
| 624 |
+
"step": 390
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.17379679144385027,
|
| 628 |
+
"eval_accuracy": 0.9986631274223328,
|
| 629 |
+
"eval_loss": 0.009089282713830471,
|
| 630 |
+
"eval_runtime": 539.9652,
|
| 631 |
+
"eval_samples_per_second": 8.312,
|
| 632 |
+
"eval_steps_per_second": 2.078,
|
| 633 |
+
"step": 390
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.17825311942959002,
|
| 637 |
+
"grad_norm": 0.13566212356090546,
|
| 638 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 639 |
+
"loss": 0.0467,
|
| 640 |
+
"step": 400
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.17825311942959002,
|
| 644 |
+
"eval_accuracy": 0.9982174634933472,
|
| 645 |
+
"eval_loss": 0.011012092232704163,
|
| 646 |
+
"eval_runtime": 539.0037,
|
| 647 |
+
"eval_samples_per_second": 8.326,
|
| 648 |
+
"eval_steps_per_second": 2.082,
|
| 649 |
+
"step": 400
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.18270944741532977,
|
| 653 |
+
"grad_norm": 0.054975979030132294,
|
| 654 |
+
"learning_rate": 5.090909090909091e-05,
|
| 655 |
+
"loss": 0.0266,
|
| 656 |
+
"step": 410
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.18270944741532977,
|
| 660 |
+
"eval_accuracy": 0.9988859295845032,
|
| 661 |
+
"eval_loss": 0.008680622093379498,
|
| 662 |
+
"eval_runtime": 536.4536,
|
| 663 |
+
"eval_samples_per_second": 8.366,
|
| 664 |
+
"eval_steps_per_second": 2.092,
|
| 665 |
+
"step": 410
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.18716577540106952,
|
| 669 |
+
"grad_norm": 9.600521087646484,
|
| 670 |
+
"learning_rate": 4.7272727272727275e-05,
|
| 671 |
+
"loss": 0.0118,
|
| 672 |
+
"step": 420
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.18716577540106952,
|
| 676 |
+
"eval_accuracy": 0.9988859295845032,
|
| 677 |
+
"eval_loss": 0.008196841925382614,
|
| 678 |
+
"eval_runtime": 529.3899,
|
| 679 |
+
"eval_samples_per_second": 8.478,
|
| 680 |
+
"eval_steps_per_second": 2.119,
|
| 681 |
+
"step": 420
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.19162210338680927,
|
| 685 |
+
"grad_norm": 0.00836893916130066,
|
| 686 |
+
"learning_rate": 4.3636363636363636e-05,
|
| 687 |
+
"loss": 0.0689,
|
| 688 |
+
"step": 430
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.19162210338680927,
|
| 692 |
+
"eval_accuracy": 0.9984402656555176,
|
| 693 |
+
"eval_loss": 0.009529507718980312,
|
| 694 |
+
"eval_runtime": 537.9471,
|
| 695 |
+
"eval_samples_per_second": 8.343,
|
| 696 |
+
"eval_steps_per_second": 2.086,
|
| 697 |
+
"step": 430
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.19607843137254902,
|
| 701 |
+
"grad_norm": 0.05235498398542404,
|
| 702 |
+
"learning_rate": 4e-05,
|
| 703 |
+
"loss": 0.0785,
|
| 704 |
+
"step": 440
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.19607843137254902,
|
| 708 |
+
"eval_accuracy": 0.9975489974021912,
|
| 709 |
+
"eval_loss": 0.01092607993632555,
|
| 710 |
+
"eval_runtime": 533.7576,
|
| 711 |
+
"eval_samples_per_second": 8.408,
|
| 712 |
+
"eval_steps_per_second": 2.102,
|
| 713 |
+
"step": 440
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.20053475935828877,
|
| 717 |
+
"grad_norm": 7.876805782318115,
|
| 718 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 719 |
+
"loss": 0.0749,
|
| 720 |
+
"step": 450
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.20053475935828877,
|
| 724 |
+
"eval_accuracy": 0.9971033930778503,
|
| 725 |
+
"eval_loss": 0.013591339811682701,
|
| 726 |
+
"eval_runtime": 532.153,
|
| 727 |
+
"eval_samples_per_second": 8.434,
|
| 728 |
+
"eval_steps_per_second": 2.108,
|
| 729 |
+
"step": 450
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.20499108734402852,
|
| 733 |
+
"grad_norm": 0.055418092757463455,
|
| 734 |
+
"learning_rate": 3.272727272727273e-05,
|
| 735 |
+
"loss": 0.0038,
|
| 736 |
+
"step": 460
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.20499108734402852,
|
| 740 |
+
"eval_accuracy": 0.9930927157402039,
|
| 741 |
+
"eval_loss": 0.025715434923768044,
|
| 742 |
+
"eval_runtime": 531.9415,
|
| 743 |
+
"eval_samples_per_second": 8.437,
|
| 744 |
+
"eval_steps_per_second": 2.109,
|
| 745 |
+
"step": 460
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.20944741532976827,
|
| 749 |
+
"grad_norm": 26.78069305419922,
|
| 750 |
+
"learning_rate": 2.909090909090909e-05,
|
| 751 |
+
"loss": 0.1342,
|
| 752 |
+
"step": 470
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.20944741532976827,
|
| 756 |
+
"eval_accuracy": 0.987522304058075,
|
| 757 |
+
"eval_loss": 0.040662843734025955,
|
| 758 |
+
"eval_runtime": 530.1651,
|
| 759 |
+
"eval_samples_per_second": 8.465,
|
| 760 |
+
"eval_steps_per_second": 2.116,
|
| 761 |
+
"step": 470
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.21390374331550802,
|
| 765 |
+
"grad_norm": 13.968317031860352,
|
| 766 |
+
"learning_rate": 2.5454545454545454e-05,
|
| 767 |
+
"loss": 0.1816,
|
| 768 |
+
"step": 480
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.21390374331550802,
|
| 772 |
+
"eval_accuracy": 0.9803921580314636,
|
| 773 |
+
"eval_loss": 0.06171296164393425,
|
| 774 |
+
"eval_runtime": 536.4017,
|
| 775 |
+
"eval_samples_per_second": 8.367,
|
| 776 |
+
"eval_steps_per_second": 2.092,
|
| 777 |
+
"step": 480
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.21836007130124777,
|
| 781 |
+
"grad_norm": 0.009305565617978573,
|
| 782 |
+
"learning_rate": 2.1818181818181818e-05,
|
| 783 |
+
"loss": 0.0735,
|
| 784 |
+
"step": 490
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.21836007130124777,
|
| 788 |
+
"eval_accuracy": 0.9734848737716675,
|
| 789 |
+
"eval_loss": 0.08175662159919739,
|
| 790 |
+
"eval_runtime": 530.5285,
|
| 791 |
+
"eval_samples_per_second": 8.459,
|
| 792 |
+
"eval_steps_per_second": 2.115,
|
| 793 |
+
"step": 490
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.22281639928698752,
|
| 797 |
+
"grad_norm": 0.00870052631944418,
|
| 798 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 799 |
+
"loss": 0.0535,
|
| 800 |
+
"step": 500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.22281639928698752,
|
| 804 |
+
"eval_accuracy": 0.9748217463493347,
|
| 805 |
+
"eval_loss": 0.07746395468711853,
|
| 806 |
+
"eval_runtime": 534.4791,
|
| 807 |
+
"eval_samples_per_second": 8.397,
|
| 808 |
+
"eval_steps_per_second": 2.099,
|
| 809 |
+
"step": 500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.22727272727272727,
|
| 813 |
+
"grad_norm": 0.05970863625407219,
|
| 814 |
+
"learning_rate": 1.4545454545454545e-05,
|
| 815 |
+
"loss": 0.0088,
|
| 816 |
+
"step": 510
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.22727272727272727,
|
| 820 |
+
"eval_accuracy": 0.9846256971359253,
|
| 821 |
+
"eval_loss": 0.04695257917046547,
|
| 822 |
+
"eval_runtime": 532.8984,
|
| 823 |
+
"eval_samples_per_second": 8.422,
|
| 824 |
+
"eval_steps_per_second": 2.105,
|
| 825 |
+
"step": 510
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.23172905525846701,
|
| 829 |
+
"grad_norm": 11.049286842346191,
|
| 830 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 831 |
+
"loss": 0.0836,
|
| 832 |
+
"step": 520
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.23172905525846701,
|
| 836 |
+
"eval_accuracy": 0.9897504448890686,
|
| 837 |
+
"eval_loss": 0.03497246652841568,
|
| 838 |
+
"eval_runtime": 534.5562,
|
| 839 |
+
"eval_samples_per_second": 8.396,
|
| 840 |
+
"eval_steps_per_second": 2.099,
|
| 841 |
+
"step": 520
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.23618538324420676,
|
| 845 |
+
"grad_norm": 0.18157783150672913,
|
| 846 |
+
"learning_rate": 7.272727272727272e-06,
|
| 847 |
+
"loss": 0.0086,
|
| 848 |
+
"step": 530
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.23618538324420676,
|
| 852 |
+
"eval_accuracy": 0.9888591766357422,
|
| 853 |
+
"eval_loss": 0.03722322732210159,
|
| 854 |
+
"eval_runtime": 532.0239,
|
| 855 |
+
"eval_samples_per_second": 8.436,
|
| 856 |
+
"eval_steps_per_second": 2.109,
|
| 857 |
+
"step": 530
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.24064171122994651,
|
| 861 |
+
"grad_norm": 0.35108181834220886,
|
| 862 |
+
"learning_rate": 3.636363636363636e-06,
|
| 863 |
+
"loss": 0.0046,
|
| 864 |
+
"step": 540
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.24064171122994651,
|
| 868 |
+
"eval_accuracy": 0.9888591766357422,
|
| 869 |
+
"eval_loss": 0.0368054136633873,
|
| 870 |
+
"eval_runtime": 531.8153,
|
| 871 |
+
"eval_samples_per_second": 8.439,
|
| 872 |
+
"eval_steps_per_second": 2.11,
|
| 873 |
+
"step": 540
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.24509803921568626,
|
| 877 |
+
"grad_norm": 0.008579758927226067,
|
| 878 |
+
"learning_rate": 0.0,
|
| 879 |
+
"loss": 0.042,
|
| 880 |
+
"step": 550
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.24509803921568626,
|
| 884 |
+
"eval_accuracy": 0.9890819787979126,
|
| 885 |
+
"eval_loss": 0.03674088791012764,
|
| 886 |
+
"eval_runtime": 537.7421,
|
| 887 |
+
"eval_samples_per_second": 8.346,
|
| 888 |
+
"eval_steps_per_second": 2.087,
|
| 889 |
+
"step": 550
|
| 890 |
+
}
|
| 891 |
+
],
|
| 892 |
+
"logging_steps": 10,
|
| 893 |
+
"max_steps": 550,
|
| 894 |
+
"num_input_tokens_seen": 0,
|
| 895 |
+
"num_train_epochs": 1,
|
| 896 |
+
"save_steps": 10,
|
| 897 |
+
"stateful_callbacks": {
|
| 898 |
+
"TrainerControl": {
|
| 899 |
+
"args": {
|
| 900 |
+
"should_epoch_stop": false,
|
| 901 |
+
"should_evaluate": false,
|
| 902 |
+
"should_log": false,
|
| 903 |
+
"should_save": true,
|
| 904 |
+
"should_training_stop": true
|
| 905 |
+
},
|
| 906 |
+
"attributes": {}
|
| 907 |
+
}
|
| 908 |
+
},
|
| 909 |
+
"total_flos": 6.326400520422712e+17,
|
| 910 |
+
"train_batch_size": 4,
|
| 911 |
+
"trial_name": null,
|
| 912 |
+
"trial_params": null
|
| 913 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc20e3106e3deeaae77b52e921ca2de540a5648c5f467aef56a1c48a8706b46b
|
| 3 |
+
size 5112
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "'": 5, "-": 6, "a": 7, "b": 8, "c": 9, "d": 10, "e": 11, "f": 12, "g": 13, "h": 14, "i": 15, "j": 16, "k": 17, "l": 18, "m": 19, "n": 20, "o": 21, "p": 22, "q": 23, "r": 24, "s": 25, "t": 26, "u": 27, "v": 28, "w": 29, "x": 30, "y": 31, "z": 32}
|