Add files.
Browse files- config.json +133 -0
- optimizer.pt +3 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- stats.md +10 -0
- trainer_state.json +811 -0
- training_args.bin +3 -0
- vocab.json +1 -0
config.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "classla/wav2vec2-large-slavic-parlaspeech-hr",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForSpeechClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"finetuning_task": "wav2vec2_clf",
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.0,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": "anger",
|
| 62 |
+
"1": "fear",
|
| 63 |
+
"2": "happiness",
|
| 64 |
+
"3": "neutral",
|
| 65 |
+
"4": "sadness"
|
| 66 |
+
},
|
| 67 |
+
"initializer_range": 0.02,
|
| 68 |
+
"intermediate_size": 4096,
|
| 69 |
+
"label2id": {
|
| 70 |
+
"anger": 0,
|
| 71 |
+
"fear": 1,
|
| 72 |
+
"happiness": 2,
|
| 73 |
+
"neutral": 3,
|
| 74 |
+
"sadness": 4
|
| 75 |
+
},
|
| 76 |
+
"layer_norm_eps": 1e-05,
|
| 77 |
+
"layerdrop": 0.0,
|
| 78 |
+
"mask_channel_length": 10,
|
| 79 |
+
"mask_channel_min_space": 1,
|
| 80 |
+
"mask_channel_other": 0.0,
|
| 81 |
+
"mask_channel_prob": 0.0,
|
| 82 |
+
"mask_channel_selection": "static",
|
| 83 |
+
"mask_feature_length": 10,
|
| 84 |
+
"mask_feature_min_masks": 0,
|
| 85 |
+
"mask_feature_prob": 0.0,
|
| 86 |
+
"mask_time_length": 10,
|
| 87 |
+
"mask_time_min_masks": 2,
|
| 88 |
+
"mask_time_min_space": 1,
|
| 89 |
+
"mask_time_other": 0.0,
|
| 90 |
+
"mask_time_prob": 0.05,
|
| 91 |
+
"mask_time_selection": "static",
|
| 92 |
+
"model_type": "wav2vec2",
|
| 93 |
+
"num_adapter_layers": 3,
|
| 94 |
+
"num_attention_heads": 16,
|
| 95 |
+
"num_codevector_groups": 2,
|
| 96 |
+
"num_codevectors_per_group": 320,
|
| 97 |
+
"num_conv_pos_embedding_groups": 16,
|
| 98 |
+
"num_conv_pos_embeddings": 128,
|
| 99 |
+
"num_feat_extract_layers": 7,
|
| 100 |
+
"num_hidden_layers": 24,
|
| 101 |
+
"num_negatives": 100,
|
| 102 |
+
"output_hidden_size": 1024,
|
| 103 |
+
"pad_token_id": 1,
|
| 104 |
+
"pooling_mode": "mean",
|
| 105 |
+
"problem_type": "single_label_classification",
|
| 106 |
+
"proj_codevector_dim": 768,
|
| 107 |
+
"tdnn_dilation": [
|
| 108 |
+
1,
|
| 109 |
+
2,
|
| 110 |
+
3,
|
| 111 |
+
1,
|
| 112 |
+
1
|
| 113 |
+
],
|
| 114 |
+
"tdnn_dim": [
|
| 115 |
+
512,
|
| 116 |
+
512,
|
| 117 |
+
512,
|
| 118 |
+
512,
|
| 119 |
+
1500
|
| 120 |
+
],
|
| 121 |
+
"tdnn_kernel": [
|
| 122 |
+
5,
|
| 123 |
+
3,
|
| 124 |
+
3,
|
| 125 |
+
1,
|
| 126 |
+
1
|
| 127 |
+
],
|
| 128 |
+
"torch_dtype": "float32",
|
| 129 |
+
"transformers_version": "4.19.2",
|
| 130 |
+
"use_weighted_layer_sum": false,
|
| 131 |
+
"vocab_size": 50,
|
| 132 |
+
"xvector_output_dim": 512
|
| 133 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6e6bc71f1f6162fcd8e675d807d6da0995087b0207d1c69781fbbc43b9dfd19
|
| 3 |
+
size 2498497929
|
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": 0.0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79874d308c0bbe3eaf6551bbdaafb1aeb7b86a1e090e552f1d5d5c17aabed067
|
| 3 |
+
size 1266118253
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7dbe44d49485edecb6dde49bc5d8645c0d283b90a1d59a2d64b65aaf1a34c29
|
| 3 |
+
size 14503
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7aae24ee13846e246b37bbb4d65264fc17487a20329b99f62fdb47ff22b7f733
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1992a35c74e8d0ffd01caf1992a4808f9d54c9cff8fc4295913ed1e24c934333
|
| 3 |
+
size 623
|
stats.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
| | TASK | accuracy | macroF1 | split | NUM_EPOCH |
|
| 2 |
+
|---:|:---------------------|-----------:|----------:|:--------|------------:|
|
| 3 |
+
| 2 | best_model_finding_1 | 0.772277 | 0.772291 | dev | 7 |
|
| 4 |
+
| 0 | best_model_finding_0 | 0.767327 | 0.763055 | dev | 7 |
|
| 5 |
+
| 4 | best_model_finding_2 | 0.752475 | 0.751493 | dev | 7 |
|
| 6 |
+
| 5 | best_model_finding_2 | 0.747573 | 0.70292 | test | 7 |
|
| 7 |
+
| 1 | best_model_finding_0 | 0.728155 | 0.690463 | test | 7 |
|
| 8 |
+
| 3 | best_model_finding_1 | 0.679612 | 0.635755 | test | 7 |
|
| 9 |
+
| 6 | best_model_finding_3 | 0.658416 | 0.652704 | dev | 7 |
|
| 10 |
+
| 7 | best_model_finding_3 | 0.582524 | 0.52383 | test | 7 |
|
trainer_state.json
ADDED
|
@@ -0,0 +1,811 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.997150997150997,
|
| 5 |
+
"global_step": 1225,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 9.918367346938776e-05,
|
| 13 |
+
"loss": 1.5894,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 9.836734693877552e-05,
|
| 19 |
+
"loss": 1.5249,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.17,
|
| 24 |
+
"learning_rate": 9.755102040816328e-05,
|
| 25 |
+
"loss": 1.4639,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.23,
|
| 30 |
+
"learning_rate": 9.673469387755102e-05,
|
| 31 |
+
"loss": 1.4989,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.28,
|
| 36 |
+
"learning_rate": 9.591836734693878e-05,
|
| 37 |
+
"loss": 1.4726,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.34,
|
| 42 |
+
"learning_rate": 9.510204081632653e-05,
|
| 43 |
+
"loss": 1.3616,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.4,
|
| 48 |
+
"learning_rate": 9.428571428571429e-05,
|
| 49 |
+
"loss": 1.4093,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.46,
|
| 54 |
+
"learning_rate": 9.346938775510204e-05,
|
| 55 |
+
"loss": 1.2487,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.51,
|
| 60 |
+
"learning_rate": 9.26530612244898e-05,
|
| 61 |
+
"loss": 1.1843,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.57,
|
| 66 |
+
"learning_rate": 9.183673469387756e-05,
|
| 67 |
+
"loss": 1.2226,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.63,
|
| 72 |
+
"learning_rate": 9.102040816326532e-05,
|
| 73 |
+
"loss": 1.1402,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.68,
|
| 78 |
+
"learning_rate": 9.020408163265308e-05,
|
| 79 |
+
"loss": 1.2654,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.74,
|
| 84 |
+
"learning_rate": 8.938775510204082e-05,
|
| 85 |
+
"loss": 1.2024,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.8,
|
| 90 |
+
"learning_rate": 8.857142857142857e-05,
|
| 91 |
+
"loss": 1.447,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.85,
|
| 96 |
+
"learning_rate": 8.775510204081632e-05,
|
| 97 |
+
"loss": 1.0705,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.91,
|
| 102 |
+
"learning_rate": 8.693877551020408e-05,
|
| 103 |
+
"loss": 0.7617,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.97,
|
| 108 |
+
"learning_rate": 8.612244897959184e-05,
|
| 109 |
+
"loss": 0.7525,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0,
|
| 114 |
+
"eval_accuracy": 0.6188119053840637,
|
| 115 |
+
"eval_loss": 1.0104970932006836,
|
| 116 |
+
"eval_runtime": 11.9979,
|
| 117 |
+
"eval_samples_per_second": 16.836,
|
| 118 |
+
"eval_steps_per_second": 8.418,
|
| 119 |
+
"step": 175
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.03,
|
| 123 |
+
"learning_rate": 8.53061224489796e-05,
|
| 124 |
+
"loss": 0.9951,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.09,
|
| 129 |
+
"learning_rate": 8.448979591836736e-05,
|
| 130 |
+
"loss": 0.8361,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.14,
|
| 135 |
+
"learning_rate": 8.367346938775511e-05,
|
| 136 |
+
"loss": 0.5858,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.2,
|
| 141 |
+
"learning_rate": 8.285714285714287e-05,
|
| 142 |
+
"loss": 0.5791,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.26,
|
| 147 |
+
"learning_rate": 8.204081632653062e-05,
|
| 148 |
+
"loss": 0.8001,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.31,
|
| 153 |
+
"learning_rate": 8.122448979591836e-05,
|
| 154 |
+
"loss": 0.7776,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.37,
|
| 159 |
+
"learning_rate": 8.040816326530612e-05,
|
| 160 |
+
"loss": 0.8223,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.43,
|
| 165 |
+
"learning_rate": 7.959183673469388e-05,
|
| 166 |
+
"loss": 0.621,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.48,
|
| 171 |
+
"learning_rate": 7.885714285714286e-05,
|
| 172 |
+
"loss": 0.7097,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.54,
|
| 177 |
+
"learning_rate": 7.804081632653062e-05,
|
| 178 |
+
"loss": 0.5678,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.6,
|
| 183 |
+
"learning_rate": 7.722448979591837e-05,
|
| 184 |
+
"loss": 0.4465,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.66,
|
| 189 |
+
"learning_rate": 7.640816326530612e-05,
|
| 190 |
+
"loss": 0.957,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.71,
|
| 195 |
+
"learning_rate": 7.559183673469388e-05,
|
| 196 |
+
"loss": 0.645,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.77,
|
| 201 |
+
"learning_rate": 7.477551020408163e-05,
|
| 202 |
+
"loss": 1.3314,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.83,
|
| 207 |
+
"learning_rate": 7.395918367346939e-05,
|
| 208 |
+
"loss": 0.5702,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.88,
|
| 213 |
+
"learning_rate": 7.314285714285715e-05,
|
| 214 |
+
"loss": 0.7456,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.94,
|
| 219 |
+
"learning_rate": 7.232653061224491e-05,
|
| 220 |
+
"loss": 0.3972,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.0,
|
| 225 |
+
"learning_rate": 7.151020408163265e-05,
|
| 226 |
+
"loss": 0.5402,
|
| 227 |
+
"step": 350
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.0,
|
| 231 |
+
"eval_accuracy": 0.7574257254600525,
|
| 232 |
+
"eval_loss": 0.7105001211166382,
|
| 233 |
+
"eval_runtime": 11.6399,
|
| 234 |
+
"eval_samples_per_second": 17.354,
|
| 235 |
+
"eval_steps_per_second": 8.677,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.06,
|
| 240 |
+
"learning_rate": 7.069387755102041e-05,
|
| 241 |
+
"loss": 0.4779,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.11,
|
| 246 |
+
"learning_rate": 6.987755102040817e-05,
|
| 247 |
+
"loss": 0.4267,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.17,
|
| 252 |
+
"learning_rate": 6.906122448979592e-05,
|
| 253 |
+
"loss": 0.2531,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.23,
|
| 258 |
+
"learning_rate": 6.824489795918367e-05,
|
| 259 |
+
"loss": 0.2189,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.28,
|
| 264 |
+
"learning_rate": 6.742857142857143e-05,
|
| 265 |
+
"loss": 0.2174,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.34,
|
| 270 |
+
"learning_rate": 6.661224489795919e-05,
|
| 271 |
+
"loss": 0.466,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.4,
|
| 276 |
+
"learning_rate": 6.579591836734695e-05,
|
| 277 |
+
"loss": 0.2604,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.46,
|
| 282 |
+
"learning_rate": 6.497959183673469e-05,
|
| 283 |
+
"loss": 0.3566,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.51,
|
| 288 |
+
"learning_rate": 6.424489795918368e-05,
|
| 289 |
+
"loss": 0.5317,
|
| 290 |
+
"step": 440
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.57,
|
| 294 |
+
"learning_rate": 6.342857142857143e-05,
|
| 295 |
+
"loss": 0.124,
|
| 296 |
+
"step": 450
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.63,
|
| 300 |
+
"learning_rate": 6.261224489795919e-05,
|
| 301 |
+
"loss": 0.3307,
|
| 302 |
+
"step": 460
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.68,
|
| 306 |
+
"learning_rate": 6.179591836734693e-05,
|
| 307 |
+
"loss": 0.2536,
|
| 308 |
+
"step": 470
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.74,
|
| 312 |
+
"learning_rate": 6.09795918367347e-05,
|
| 313 |
+
"loss": 0.4331,
|
| 314 |
+
"step": 480
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.8,
|
| 318 |
+
"learning_rate": 6.016326530612245e-05,
|
| 319 |
+
"loss": 0.3736,
|
| 320 |
+
"step": 490
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.85,
|
| 324 |
+
"learning_rate": 5.934693877551021e-05,
|
| 325 |
+
"loss": 0.3034,
|
| 326 |
+
"step": 500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.91,
|
| 330 |
+
"learning_rate": 5.8530612244897965e-05,
|
| 331 |
+
"loss": 0.5411,
|
| 332 |
+
"step": 510
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.97,
|
| 336 |
+
"learning_rate": 5.771428571428572e-05,
|
| 337 |
+
"loss": 0.6408,
|
| 338 |
+
"step": 520
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.0,
|
| 342 |
+
"eval_accuracy": 0.7227723002433777,
|
| 343 |
+
"eval_loss": 1.0339319705963135,
|
| 344 |
+
"eval_runtime": 11.8395,
|
| 345 |
+
"eval_samples_per_second": 17.062,
|
| 346 |
+
"eval_steps_per_second": 8.531,
|
| 347 |
+
"step": 525
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.03,
|
| 351 |
+
"learning_rate": 5.6897959183673475e-05,
|
| 352 |
+
"loss": 0.1283,
|
| 353 |
+
"step": 530
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.09,
|
| 357 |
+
"learning_rate": 5.608163265306122e-05,
|
| 358 |
+
"loss": 0.2879,
|
| 359 |
+
"step": 540
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.14,
|
| 363 |
+
"learning_rate": 5.526530612244898e-05,
|
| 364 |
+
"loss": 0.0459,
|
| 365 |
+
"step": 550
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.2,
|
| 369 |
+
"learning_rate": 5.4448979591836736e-05,
|
| 370 |
+
"loss": 0.4081,
|
| 371 |
+
"step": 560
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.26,
|
| 375 |
+
"learning_rate": 5.3632653061224494e-05,
|
| 376 |
+
"loss": 0.0723,
|
| 377 |
+
"step": 570
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.31,
|
| 381 |
+
"learning_rate": 5.2816326530612245e-05,
|
| 382 |
+
"loss": 0.3279,
|
| 383 |
+
"step": 580
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.37,
|
| 387 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 388 |
+
"loss": 0.1205,
|
| 389 |
+
"step": 590
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.43,
|
| 393 |
+
"learning_rate": 5.118367346938776e-05,
|
| 394 |
+
"loss": 0.1483,
|
| 395 |
+
"step": 600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.48,
|
| 399 |
+
"learning_rate": 5.036734693877552e-05,
|
| 400 |
+
"loss": 0.1873,
|
| 401 |
+
"step": 610
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.54,
|
| 405 |
+
"learning_rate": 4.9551020408163265e-05,
|
| 406 |
+
"loss": 0.2136,
|
| 407 |
+
"step": 620
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.6,
|
| 411 |
+
"learning_rate": 4.873469387755102e-05,
|
| 412 |
+
"loss": 0.2166,
|
| 413 |
+
"step": 630
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.66,
|
| 417 |
+
"learning_rate": 4.7918367346938774e-05,
|
| 418 |
+
"loss": 0.1963,
|
| 419 |
+
"step": 640
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.71,
|
| 423 |
+
"learning_rate": 4.710204081632653e-05,
|
| 424 |
+
"loss": 0.0301,
|
| 425 |
+
"step": 650
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.77,
|
| 429 |
+
"learning_rate": 4.628571428571429e-05,
|
| 430 |
+
"loss": 0.1655,
|
| 431 |
+
"step": 660
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.83,
|
| 435 |
+
"learning_rate": 4.546938775510204e-05,
|
| 436 |
+
"loss": 0.0028,
|
| 437 |
+
"step": 670
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.88,
|
| 441 |
+
"learning_rate": 4.46530612244898e-05,
|
| 442 |
+
"loss": 0.0482,
|
| 443 |
+
"step": 680
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.94,
|
| 447 |
+
"learning_rate": 4.383673469387755e-05,
|
| 448 |
+
"loss": 0.1093,
|
| 449 |
+
"step": 690
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.0,
|
| 453 |
+
"learning_rate": 4.302040816326531e-05,
|
| 454 |
+
"loss": 0.0784,
|
| 455 |
+
"step": 700
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.0,
|
| 459 |
+
"eval_accuracy": 0.7277227640151978,
|
| 460 |
+
"eval_loss": 1.246588945388794,
|
| 461 |
+
"eval_runtime": 11.9773,
|
| 462 |
+
"eval_samples_per_second": 16.865,
|
| 463 |
+
"eval_steps_per_second": 8.433,
|
| 464 |
+
"step": 700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.06,
|
| 468 |
+
"learning_rate": 4.220408163265306e-05,
|
| 469 |
+
"loss": 0.0031,
|
| 470 |
+
"step": 710
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.11,
|
| 474 |
+
"learning_rate": 4.138775510204082e-05,
|
| 475 |
+
"loss": 0.023,
|
| 476 |
+
"step": 720
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.17,
|
| 480 |
+
"learning_rate": 4.057142857142857e-05,
|
| 481 |
+
"loss": 0.0178,
|
| 482 |
+
"step": 730
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.23,
|
| 486 |
+
"learning_rate": 3.9836734693877556e-05,
|
| 487 |
+
"loss": 0.141,
|
| 488 |
+
"step": 740
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.28,
|
| 492 |
+
"learning_rate": 3.902040816326531e-05,
|
| 493 |
+
"loss": 0.0021,
|
| 494 |
+
"step": 750
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.34,
|
| 498 |
+
"learning_rate": 3.820408163265306e-05,
|
| 499 |
+
"loss": 0.0996,
|
| 500 |
+
"step": 760
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.4,
|
| 504 |
+
"learning_rate": 3.738775510204082e-05,
|
| 505 |
+
"loss": 0.0155,
|
| 506 |
+
"step": 770
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 4.46,
|
| 510 |
+
"learning_rate": 3.6571428571428576e-05,
|
| 511 |
+
"loss": 0.0638,
|
| 512 |
+
"step": 780
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.51,
|
| 516 |
+
"learning_rate": 3.575510204081633e-05,
|
| 517 |
+
"loss": 0.035,
|
| 518 |
+
"step": 790
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.57,
|
| 522 |
+
"learning_rate": 3.4938775510204085e-05,
|
| 523 |
+
"loss": 0.0019,
|
| 524 |
+
"step": 800
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.63,
|
| 528 |
+
"learning_rate": 3.412244897959184e-05,
|
| 529 |
+
"loss": 0.0018,
|
| 530 |
+
"step": 810
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.68,
|
| 534 |
+
"learning_rate": 3.3306122448979595e-05,
|
| 535 |
+
"loss": 0.0014,
|
| 536 |
+
"step": 820
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.74,
|
| 540 |
+
"learning_rate": 3.2489795918367346e-05,
|
| 541 |
+
"loss": 0.0046,
|
| 542 |
+
"step": 830
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.8,
|
| 546 |
+
"learning_rate": 3.1673469387755105e-05,
|
| 547 |
+
"loss": 0.0044,
|
| 548 |
+
"step": 840
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.85,
|
| 552 |
+
"learning_rate": 3.0857142857142856e-05,
|
| 553 |
+
"loss": 0.0207,
|
| 554 |
+
"step": 850
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.91,
|
| 558 |
+
"learning_rate": 3.0040816326530614e-05,
|
| 559 |
+
"loss": 0.0029,
|
| 560 |
+
"step": 860
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.97,
|
| 564 |
+
"learning_rate": 2.922448979591837e-05,
|
| 565 |
+
"loss": 0.0385,
|
| 566 |
+
"step": 870
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 5.0,
|
| 570 |
+
"eval_accuracy": 0.7623762488365173,
|
| 571 |
+
"eval_loss": 1.2059693336486816,
|
| 572 |
+
"eval_runtime": 11.6571,
|
| 573 |
+
"eval_samples_per_second": 17.328,
|
| 574 |
+
"eval_steps_per_second": 8.664,
|
| 575 |
+
"step": 875
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.03,
|
| 579 |
+
"learning_rate": 2.8408163265306127e-05,
|
| 580 |
+
"loss": 0.0605,
|
| 581 |
+
"step": 880
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 5.09,
|
| 585 |
+
"learning_rate": 2.7591836734693875e-05,
|
| 586 |
+
"loss": 0.0011,
|
| 587 |
+
"step": 890
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 5.14,
|
| 591 |
+
"learning_rate": 2.6775510204081634e-05,
|
| 592 |
+
"loss": 0.0037,
|
| 593 |
+
"step": 900
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.2,
|
| 597 |
+
"learning_rate": 2.595918367346939e-05,
|
| 598 |
+
"loss": 0.0011,
|
| 599 |
+
"step": 910
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 5.26,
|
| 603 |
+
"learning_rate": 2.5142857142857147e-05,
|
| 604 |
+
"loss": 0.0036,
|
| 605 |
+
"step": 920
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.31,
|
| 609 |
+
"learning_rate": 2.4326530612244898e-05,
|
| 610 |
+
"loss": 0.0015,
|
| 611 |
+
"step": 930
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.37,
|
| 615 |
+
"learning_rate": 2.3510204081632653e-05,
|
| 616 |
+
"loss": 0.0039,
|
| 617 |
+
"step": 940
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.43,
|
| 621 |
+
"learning_rate": 2.269387755102041e-05,
|
| 622 |
+
"loss": 0.0019,
|
| 623 |
+
"step": 950
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 5.48,
|
| 627 |
+
"learning_rate": 2.1877551020408162e-05,
|
| 628 |
+
"loss": 0.0011,
|
| 629 |
+
"step": 960
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 5.54,
|
| 633 |
+
"learning_rate": 2.106122448979592e-05,
|
| 634 |
+
"loss": 0.0031,
|
| 635 |
+
"step": 970
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 5.6,
|
| 639 |
+
"learning_rate": 2.0244897959183676e-05,
|
| 640 |
+
"loss": 0.0012,
|
| 641 |
+
"step": 980
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 5.66,
|
| 645 |
+
"learning_rate": 1.942857142857143e-05,
|
| 646 |
+
"loss": 0.0009,
|
| 647 |
+
"step": 990
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 5.71,
|
| 651 |
+
"learning_rate": 1.8612244897959185e-05,
|
| 652 |
+
"loss": 0.0031,
|
| 653 |
+
"step": 1000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 5.77,
|
| 657 |
+
"learning_rate": 1.779591836734694e-05,
|
| 658 |
+
"loss": 0.001,
|
| 659 |
+
"step": 1010
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 5.83,
|
| 663 |
+
"learning_rate": 1.6979591836734695e-05,
|
| 664 |
+
"loss": 0.0011,
|
| 665 |
+
"step": 1020
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 5.88,
|
| 669 |
+
"learning_rate": 1.616326530612245e-05,
|
| 670 |
+
"loss": 0.0011,
|
| 671 |
+
"step": 1030
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 5.94,
|
| 675 |
+
"learning_rate": 1.5346938775510204e-05,
|
| 676 |
+
"loss": 0.0008,
|
| 677 |
+
"step": 1040
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 6.0,
|
| 681 |
+
"learning_rate": 1.453061224489796e-05,
|
| 682 |
+
"loss": 0.0066,
|
| 683 |
+
"step": 1050
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 6.0,
|
| 687 |
+
"eval_accuracy": 0.7425742745399475,
|
| 688 |
+
"eval_loss": 1.2782899141311646,
|
| 689 |
+
"eval_runtime": 11.4463,
|
| 690 |
+
"eval_samples_per_second": 17.648,
|
| 691 |
+
"eval_steps_per_second": 8.824,
|
| 692 |
+
"step": 1050
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.06,
|
| 696 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 697 |
+
"loss": 0.005,
|
| 698 |
+
"step": 1060
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 6.11,
|
| 702 |
+
"learning_rate": 1.2897959183673469e-05,
|
| 703 |
+
"loss": 0.0007,
|
| 704 |
+
"step": 1070
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.17,
|
| 708 |
+
"learning_rate": 1.2081632653061225e-05,
|
| 709 |
+
"loss": 0.0011,
|
| 710 |
+
"step": 1080
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 6.23,
|
| 714 |
+
"learning_rate": 1.126530612244898e-05,
|
| 715 |
+
"loss": 0.0176,
|
| 716 |
+
"step": 1090
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 6.28,
|
| 720 |
+
"learning_rate": 1.0448979591836735e-05,
|
| 721 |
+
"loss": 0.001,
|
| 722 |
+
"step": 1100
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 6.34,
|
| 726 |
+
"learning_rate": 9.63265306122449e-06,
|
| 727 |
+
"loss": 0.0008,
|
| 728 |
+
"step": 1110
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 6.4,
|
| 732 |
+
"learning_rate": 8.816326530612245e-06,
|
| 733 |
+
"loss": 0.0008,
|
| 734 |
+
"step": 1120
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 6.46,
|
| 738 |
+
"learning_rate": 8.000000000000001e-06,
|
| 739 |
+
"loss": 0.0007,
|
| 740 |
+
"step": 1130
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 6.51,
|
| 744 |
+
"learning_rate": 7.183673469387755e-06,
|
| 745 |
+
"loss": 0.0031,
|
| 746 |
+
"step": 1140
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 6.57,
|
| 750 |
+
"learning_rate": 6.36734693877551e-06,
|
| 751 |
+
"loss": 0.0175,
|
| 752 |
+
"step": 1150
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 6.63,
|
| 756 |
+
"learning_rate": 5.551020408163266e-06,
|
| 757 |
+
"loss": 0.0044,
|
| 758 |
+
"step": 1160
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 6.68,
|
| 762 |
+
"learning_rate": 4.734693877551021e-06,
|
| 763 |
+
"loss": 0.0008,
|
| 764 |
+
"step": 1170
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 6.74,
|
| 768 |
+
"learning_rate": 3.9183673469387755e-06,
|
| 769 |
+
"loss": 0.0009,
|
| 770 |
+
"step": 1180
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 6.8,
|
| 774 |
+
"learning_rate": 3.1020408163265307e-06,
|
| 775 |
+
"loss": 0.0016,
|
| 776 |
+
"step": 1190
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 6.85,
|
| 780 |
+
"learning_rate": 2.285714285714286e-06,
|
| 781 |
+
"loss": 0.0008,
|
| 782 |
+
"step": 1200
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 6.91,
|
| 786 |
+
"learning_rate": 1.4693877551020408e-06,
|
| 787 |
+
"loss": 0.0007,
|
| 788 |
+
"step": 1210
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 6.97,
|
| 792 |
+
"learning_rate": 6.53061224489796e-07,
|
| 793 |
+
"loss": 0.0102,
|
| 794 |
+
"step": 1220
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 7.0,
|
| 798 |
+
"eval_accuracy": 0.7524752616882324,
|
| 799 |
+
"eval_loss": 1.2731852531433105,
|
| 800 |
+
"eval_runtime": 11.7439,
|
| 801 |
+
"eval_samples_per_second": 17.2,
|
| 802 |
+
"eval_steps_per_second": 8.6,
|
| 803 |
+
"step": 1225
|
| 804 |
+
}
|
| 805 |
+
],
|
| 806 |
+
"max_steps": 1225,
|
| 807 |
+
"num_train_epochs": 7,
|
| 808 |
+
"total_flos": 8.443178680144968e+17,
|
| 809 |
+
"trial_name": null,
|
| 810 |
+
"trial_params": null
|
| 811 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9c8694a1a02a17556ba46646dfbd3242298541f0f80d2d3f27a5ec007a118dc
|
| 3 |
+
size 3311
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{ "|": 0, "?": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "\u00e4": 28, "\u00fc": 29, "\u0107": 30, "\u010d": 31, "\u0111": 32, "\u0161": 33, "\u017e": 34, "[UNK]": 35, "[PAD]": 36, " ": 37, "1": 38, "2": 39, "3": 40, "4": 41, "5": 42, "6": 43, "7": 44, "8": 45, "9": 46, "0": 47}
|