Upload 8 files
Browse files- config.json +137 -0
- model.safetensors +3 -0
- optimizer-001.pt +3 -0
- preprocessor_config.json +10 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +846 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-french",
|
| 3 |
+
"activation_dropout": 0.05,
|
| 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": 256,
|
| 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": "mean",
|
| 46 |
+
"ctc_zero_infinity": true,
|
| 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": 0.05,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.0,
|
| 56 |
+
"finetuning_task": "wav2vec2_clf",
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.05,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": "Col\u041are",
|
| 62 |
+
"1": "D\u0412go\u0426t",
|
| 63 |
+
"2": "fear",
|
| 64 |
+
"3": "happiness",
|
| 65 |
+
"4": "neutral",
|
| 66 |
+
"5": "sadness",
|
| 67 |
+
"6": "surprise"
|
| 68 |
+
},
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 4096,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"Col\u041are": 0,
|
| 73 |
+
"D\u0412go\u0426t": 1,
|
| 74 |
+
"fear": 2,
|
| 75 |
+
"happiness": 3,
|
| 76 |
+
"neutral": 4,
|
| 77 |
+
"sadness": 5,
|
| 78 |
+
"surprise": 6
|
| 79 |
+
},
|
| 80 |
+
"layer_norm_eps": 1e-05,
|
| 81 |
+
"layerdrop": 0.05,
|
| 82 |
+
"mask_channel_length": 10,
|
| 83 |
+
"mask_channel_min_space": 1,
|
| 84 |
+
"mask_channel_other": 0.0,
|
| 85 |
+
"mask_channel_prob": 0.0,
|
| 86 |
+
"mask_channel_selection": "static",
|
| 87 |
+
"mask_feature_length": 10,
|
| 88 |
+
"mask_feature_min_masks": 0,
|
| 89 |
+
"mask_feature_prob": 0.0,
|
| 90 |
+
"mask_time_length": 10,
|
| 91 |
+
"mask_time_min_masks": 2,
|
| 92 |
+
"mask_time_min_space": 1,
|
| 93 |
+
"mask_time_other": 0.0,
|
| 94 |
+
"mask_time_prob": 0.05,
|
| 95 |
+
"mask_time_selection": "static",
|
| 96 |
+
"model_type": "wav2vec2",
|
| 97 |
+
"num_adapter_layers": 3,
|
| 98 |
+
"num_attention_heads": 16,
|
| 99 |
+
"num_codevector_groups": 2,
|
| 100 |
+
"num_codevectors_per_group": 320,
|
| 101 |
+
"num_conv_pos_embedding_groups": 16,
|
| 102 |
+
"num_conv_pos_embeddings": 128,
|
| 103 |
+
"num_feat_extract_layers": 7,
|
| 104 |
+
"num_hidden_layers": 24,
|
| 105 |
+
"num_negatives": 100,
|
| 106 |
+
"output_hidden_size": 1024,
|
| 107 |
+
"pad_token_id": 0,
|
| 108 |
+
"pooling_mode": "mean",
|
| 109 |
+
"problem_type": "single_label_classification",
|
| 110 |
+
"proj_codevector_dim": 256,
|
| 111 |
+
"tdnn_dilation": [
|
| 112 |
+
1,
|
| 113 |
+
2,
|
| 114 |
+
3,
|
| 115 |
+
1,
|
| 116 |
+
1
|
| 117 |
+
],
|
| 118 |
+
"tdnn_dim": [
|
| 119 |
+
512,
|
| 120 |
+
512,
|
| 121 |
+
512,
|
| 122 |
+
512,
|
| 123 |
+
1500
|
| 124 |
+
],
|
| 125 |
+
"tdnn_kernel": [
|
| 126 |
+
5,
|
| 127 |
+
3,
|
| 128 |
+
3,
|
| 129 |
+
1,
|
| 130 |
+
1
|
| 131 |
+
],
|
| 132 |
+
"torch_dtype": "float32",
|
| 133 |
+
"transformers_version": "4.37.0.dev0",
|
| 134 |
+
"use_weighted_layer_sum": false,
|
| 135 |
+
"vocab_size": 59,
|
| 136 |
+
"xvector_output_dim": 512
|
| 137 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56612f82edc9e2079aec99cec650ebd948dc9aacf3ebd967d3eb990a64d96024
|
| 3 |
+
size 1266034804
|
optimizer-001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1b2db04267299f0c64c1b43e5d07e8ca607a3d574f51fc35f6e62a6ad9cbdf1
|
| 3 |
+
size 2498615612
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62a0b5a9c071ff5a50cb7dfccc23394dcd8f419f218cd90883692f95ec2f1e32
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99f05826c8342d8d3ab7caf2da89009e7eacabe953850ac5d3ed53997ef26d06
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,846 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.882352941176471,
|
| 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": 0.11,
|
| 13 |
+
"learning_rate": 9.820788530465951e-05,
|
| 14 |
+
"loss": 2.039,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"eval_accuracy": 0.15425531566143036,
|
| 20 |
+
"eval_loss": 1.9874085187911987,
|
| 21 |
+
"eval_runtime": 18.0154,
|
| 22 |
+
"eval_samples_per_second": 10.436,
|
| 23 |
+
"eval_steps_per_second": 2.609,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.21,
|
| 28 |
+
"learning_rate": 9.6415770609319e-05,
|
| 29 |
+
"loss": 1.8674,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21,
|
| 34 |
+
"eval_accuracy": 0.18617020547389984,
|
| 35 |
+
"eval_loss": 1.915345549583435,
|
| 36 |
+
"eval_runtime": 19.3568,
|
| 37 |
+
"eval_samples_per_second": 9.712,
|
| 38 |
+
"eval_steps_per_second": 2.428,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.32,
|
| 43 |
+
"learning_rate": 9.46236559139785e-05,
|
| 44 |
+
"loss": 1.9047,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.32,
|
| 49 |
+
"eval_accuracy": 0.21808511018753052,
|
| 50 |
+
"eval_loss": 1.8614839315414429,
|
| 51 |
+
"eval_runtime": 16.987,
|
| 52 |
+
"eval_samples_per_second": 11.067,
|
| 53 |
+
"eval_steps_per_second": 2.767,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.43,
|
| 58 |
+
"learning_rate": 9.2831541218638e-05,
|
| 59 |
+
"loss": 1.8554,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.43,
|
| 64 |
+
"eval_accuracy": 0.3297872245311737,
|
| 65 |
+
"eval_loss": 1.7530335187911987,
|
| 66 |
+
"eval_runtime": 17.9287,
|
| 67 |
+
"eval_samples_per_second": 10.486,
|
| 68 |
+
"eval_steps_per_second": 2.621,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.53,
|
| 73 |
+
"learning_rate": 9.10394265232975e-05,
|
| 74 |
+
"loss": 1.7546,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.53,
|
| 79 |
+
"eval_accuracy": 0.34574466943740845,
|
| 80 |
+
"eval_loss": 1.693456768989563,
|
| 81 |
+
"eval_runtime": 17.7507,
|
| 82 |
+
"eval_samples_per_second": 10.591,
|
| 83 |
+
"eval_steps_per_second": 2.648,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.64,
|
| 88 |
+
"learning_rate": 8.924731182795699e-05,
|
| 89 |
+
"loss": 1.7583,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.64,
|
| 94 |
+
"eval_accuracy": 0.31382977962493896,
|
| 95 |
+
"eval_loss": 1.7744777202606201,
|
| 96 |
+
"eval_runtime": 17.5758,
|
| 97 |
+
"eval_samples_per_second": 10.697,
|
| 98 |
+
"eval_steps_per_second": 2.674,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.75,
|
| 103 |
+
"learning_rate": 8.74551971326165e-05,
|
| 104 |
+
"loss": 1.6846,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.75,
|
| 109 |
+
"eval_accuracy": 0.47340425848960876,
|
| 110 |
+
"eval_loss": 1.383662462234497,
|
| 111 |
+
"eval_runtime": 17.9239,
|
| 112 |
+
"eval_samples_per_second": 10.489,
|
| 113 |
+
"eval_steps_per_second": 2.622,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.86,
|
| 118 |
+
"learning_rate": 8.566308243727598e-05,
|
| 119 |
+
"loss": 1.335,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.86,
|
| 124 |
+
"eval_accuracy": 0.4095744788646698,
|
| 125 |
+
"eval_loss": 1.3189808130264282,
|
| 126 |
+
"eval_runtime": 17.9015,
|
| 127 |
+
"eval_samples_per_second": 10.502,
|
| 128 |
+
"eval_steps_per_second": 2.625,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.96,
|
| 133 |
+
"learning_rate": 8.387096774193549e-05,
|
| 134 |
+
"loss": 1.3937,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.96,
|
| 139 |
+
"eval_accuracy": 0.5,
|
| 140 |
+
"eval_loss": 1.2728934288024902,
|
| 141 |
+
"eval_runtime": 16.8503,
|
| 142 |
+
"eval_samples_per_second": 11.157,
|
| 143 |
+
"eval_steps_per_second": 2.789,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.07,
|
| 148 |
+
"learning_rate": 8.207885304659499e-05,
|
| 149 |
+
"loss": 1.3213,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.07,
|
| 154 |
+
"eval_accuracy": 0.5319148898124695,
|
| 155 |
+
"eval_loss": 1.348612666130066,
|
| 156 |
+
"eval_runtime": 17.9939,
|
| 157 |
+
"eval_samples_per_second": 10.448,
|
| 158 |
+
"eval_steps_per_second": 2.612,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.18,
|
| 163 |
+
"learning_rate": 8.028673835125448e-05,
|
| 164 |
+
"loss": 1.2577,
|
| 165 |
+
"step": 110
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.18,
|
| 169 |
+
"eval_accuracy": 0.43617022037506104,
|
| 170 |
+
"eval_loss": 1.4858437776565552,
|
| 171 |
+
"eval_runtime": 16.7284,
|
| 172 |
+
"eval_samples_per_second": 11.238,
|
| 173 |
+
"eval_steps_per_second": 2.81,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.28,
|
| 178 |
+
"learning_rate": 7.849462365591398e-05,
|
| 179 |
+
"loss": 1.3039,
|
| 180 |
+
"step": 120
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.28,
|
| 184 |
+
"eval_accuracy": 0.5372340679168701,
|
| 185 |
+
"eval_loss": 1.1272777318954468,
|
| 186 |
+
"eval_runtime": 18.0338,
|
| 187 |
+
"eval_samples_per_second": 10.425,
|
| 188 |
+
"eval_steps_per_second": 2.606,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.39,
|
| 193 |
+
"learning_rate": 7.670250896057349e-05,
|
| 194 |
+
"loss": 1.2018,
|
| 195 |
+
"step": 130
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.39,
|
| 199 |
+
"eval_accuracy": 0.6010638475418091,
|
| 200 |
+
"eval_loss": 1.07073974609375,
|
| 201 |
+
"eval_runtime": 18.3403,
|
| 202 |
+
"eval_samples_per_second": 10.251,
|
| 203 |
+
"eval_steps_per_second": 2.563,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.5,
|
| 208 |
+
"learning_rate": 7.491039426523297e-05,
|
| 209 |
+
"loss": 1.0523,
|
| 210 |
+
"step": 140
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.5,
|
| 214 |
+
"eval_accuracy": 0.6223404407501221,
|
| 215 |
+
"eval_loss": 0.9273392558097839,
|
| 216 |
+
"eval_runtime": 17.4553,
|
| 217 |
+
"eval_samples_per_second": 10.77,
|
| 218 |
+
"eval_steps_per_second": 2.693,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.6,
|
| 223 |
+
"learning_rate": 7.311827956989248e-05,
|
| 224 |
+
"loss": 0.8089,
|
| 225 |
+
"step": 150
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.6,
|
| 229 |
+
"eval_accuracy": 0.6436170339584351,
|
| 230 |
+
"eval_loss": 0.958331823348999,
|
| 231 |
+
"eval_runtime": 18.1909,
|
| 232 |
+
"eval_samples_per_second": 10.335,
|
| 233 |
+
"eval_steps_per_second": 2.584,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.71,
|
| 238 |
+
"learning_rate": 7.132616487455197e-05,
|
| 239 |
+
"loss": 0.86,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.71,
|
| 244 |
+
"eval_accuracy": 0.728723406791687,
|
| 245 |
+
"eval_loss": 0.7838733792304993,
|
| 246 |
+
"eval_runtime": 17.986,
|
| 247 |
+
"eval_samples_per_second": 10.453,
|
| 248 |
+
"eval_steps_per_second": 2.613,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.82,
|
| 253 |
+
"learning_rate": 6.953405017921147e-05,
|
| 254 |
+
"loss": 0.7991,
|
| 255 |
+
"step": 170
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.82,
|
| 259 |
+
"eval_accuracy": 0.7393617033958435,
|
| 260 |
+
"eval_loss": 0.7742288708686829,
|
| 261 |
+
"eval_runtime": 17.5516,
|
| 262 |
+
"eval_samples_per_second": 10.711,
|
| 263 |
+
"eval_steps_per_second": 2.678,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.93,
|
| 268 |
+
"learning_rate": 6.774193548387096e-05,
|
| 269 |
+
"loss": 0.6772,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.93,
|
| 274 |
+
"eval_accuracy": 0.728723406791687,
|
| 275 |
+
"eval_loss": 0.7831820845603943,
|
| 276 |
+
"eval_runtime": 17.1247,
|
| 277 |
+
"eval_samples_per_second": 10.978,
|
| 278 |
+
"eval_steps_per_second": 2.745,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.03,
|
| 283 |
+
"learning_rate": 6.594982078853047e-05,
|
| 284 |
+
"loss": 0.5716,
|
| 285 |
+
"step": 190
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.03,
|
| 289 |
+
"eval_accuracy": 0.6808510422706604,
|
| 290 |
+
"eval_loss": 0.8607780933380127,
|
| 291 |
+
"eval_runtime": 17.9663,
|
| 292 |
+
"eval_samples_per_second": 10.464,
|
| 293 |
+
"eval_steps_per_second": 2.616,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.14,
|
| 298 |
+
"learning_rate": 6.415770609318996e-05,
|
| 299 |
+
"loss": 0.7228,
|
| 300 |
+
"step": 200
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.14,
|
| 304 |
+
"eval_accuracy": 0.7127659320831299,
|
| 305 |
+
"eval_loss": 0.9357430338859558,
|
| 306 |
+
"eval_runtime": 16.801,
|
| 307 |
+
"eval_samples_per_second": 11.19,
|
| 308 |
+
"eval_steps_per_second": 2.797,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.25,
|
| 313 |
+
"learning_rate": 6.236559139784946e-05,
|
| 314 |
+
"loss": 0.5451,
|
| 315 |
+
"step": 210
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.25,
|
| 319 |
+
"eval_accuracy": 0.6489361524581909,
|
| 320 |
+
"eval_loss": 1.018636703491211,
|
| 321 |
+
"eval_runtime": 17.1948,
|
| 322 |
+
"eval_samples_per_second": 10.934,
|
| 323 |
+
"eval_steps_per_second": 2.733,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.35,
|
| 328 |
+
"learning_rate": 6.057347670250897e-05,
|
| 329 |
+
"loss": 0.6429,
|
| 330 |
+
"step": 220
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.35,
|
| 334 |
+
"eval_accuracy": 0.6968085169792175,
|
| 335 |
+
"eval_loss": 0.917243242263794,
|
| 336 |
+
"eval_runtime": 17.5045,
|
| 337 |
+
"eval_samples_per_second": 10.74,
|
| 338 |
+
"eval_steps_per_second": 2.685,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.46,
|
| 343 |
+
"learning_rate": 5.878136200716846e-05,
|
| 344 |
+
"loss": 0.8224,
|
| 345 |
+
"step": 230
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.46,
|
| 349 |
+
"eval_accuracy": 0.6329787373542786,
|
| 350 |
+
"eval_loss": 1.0460094213485718,
|
| 351 |
+
"eval_runtime": 16.9483,
|
| 352 |
+
"eval_samples_per_second": 11.093,
|
| 353 |
+
"eval_steps_per_second": 2.773,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.57,
|
| 358 |
+
"learning_rate": 5.6989247311827965e-05,
|
| 359 |
+
"loss": 0.6061,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.57,
|
| 364 |
+
"eval_accuracy": 0.7446808218955994,
|
| 365 |
+
"eval_loss": 0.8167480230331421,
|
| 366 |
+
"eval_runtime": 16.9079,
|
| 367 |
+
"eval_samples_per_second": 11.119,
|
| 368 |
+
"eval_steps_per_second": 2.78,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.67,
|
| 373 |
+
"learning_rate": 5.519713261648746e-05,
|
| 374 |
+
"loss": 0.3594,
|
| 375 |
+
"step": 250
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.67,
|
| 379 |
+
"eval_accuracy": 0.7234042286872864,
|
| 380 |
+
"eval_loss": 0.8162137866020203,
|
| 381 |
+
"eval_runtime": 16.7777,
|
| 382 |
+
"eval_samples_per_second": 11.205,
|
| 383 |
+
"eval_steps_per_second": 2.801,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.78,
|
| 388 |
+
"learning_rate": 5.340501792114696e-05,
|
| 389 |
+
"loss": 0.4122,
|
| 390 |
+
"step": 260
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.78,
|
| 394 |
+
"eval_accuracy": 0.7819148898124695,
|
| 395 |
+
"eval_loss": 0.7674133777618408,
|
| 396 |
+
"eval_runtime": 16.8556,
|
| 397 |
+
"eval_samples_per_second": 11.154,
|
| 398 |
+
"eval_steps_per_second": 2.788,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.89,
|
| 403 |
+
"learning_rate": 5.161290322580645e-05,
|
| 404 |
+
"loss": 0.2874,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.89,
|
| 409 |
+
"eval_accuracy": 0.7978723645210266,
|
| 410 |
+
"eval_loss": 0.6874329447746277,
|
| 411 |
+
"eval_runtime": 18.1768,
|
| 412 |
+
"eval_samples_per_second": 10.343,
|
| 413 |
+
"eval_steps_per_second": 2.586,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.99,
|
| 418 |
+
"learning_rate": 4.982078853046595e-05,
|
| 419 |
+
"loss": 0.4881,
|
| 420 |
+
"step": 280
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.99,
|
| 424 |
+
"eval_accuracy": 0.7553191781044006,
|
| 425 |
+
"eval_loss": 0.7479570508003235,
|
| 426 |
+
"eval_runtime": 17.7772,
|
| 427 |
+
"eval_samples_per_second": 10.575,
|
| 428 |
+
"eval_steps_per_second": 2.644,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.1,
|
| 433 |
+
"learning_rate": 4.802867383512545e-05,
|
| 434 |
+
"loss": 0.5232,
|
| 435 |
+
"step": 290
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.1,
|
| 439 |
+
"eval_accuracy": 0.7659574747085571,
|
| 440 |
+
"eval_loss": 0.7912107706069946,
|
| 441 |
+
"eval_runtime": 17.9423,
|
| 442 |
+
"eval_samples_per_second": 10.478,
|
| 443 |
+
"eval_steps_per_second": 2.62,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.21,
|
| 448 |
+
"learning_rate": 4.6236559139784944e-05,
|
| 449 |
+
"loss": 0.1914,
|
| 450 |
+
"step": 300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.21,
|
| 454 |
+
"eval_accuracy": 0.7978723645210266,
|
| 455 |
+
"eval_loss": 0.7023528218269348,
|
| 456 |
+
"eval_runtime": 18.317,
|
| 457 |
+
"eval_samples_per_second": 10.264,
|
| 458 |
+
"eval_steps_per_second": 2.566,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 3.32,
|
| 463 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 464 |
+
"loss": 0.2573,
|
| 465 |
+
"step": 310
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.32,
|
| 469 |
+
"eval_accuracy": 0.7659574747085571,
|
| 470 |
+
"eval_loss": 0.7678730487823486,
|
| 471 |
+
"eval_runtime": 16.9343,
|
| 472 |
+
"eval_samples_per_second": 11.102,
|
| 473 |
+
"eval_steps_per_second": 2.775,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 3.42,
|
| 478 |
+
"learning_rate": 4.265232974910394e-05,
|
| 479 |
+
"loss": 0.1959,
|
| 480 |
+
"step": 320
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 3.42,
|
| 484 |
+
"eval_accuracy": 0.7819148898124695,
|
| 485 |
+
"eval_loss": 0.7615554332733154,
|
| 486 |
+
"eval_runtime": 17.2171,
|
| 487 |
+
"eval_samples_per_second": 10.919,
|
| 488 |
+
"eval_steps_per_second": 2.73,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.53,
|
| 493 |
+
"learning_rate": 4.0860215053763444e-05,
|
| 494 |
+
"loss": 0.2317,
|
| 495 |
+
"step": 330
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.53,
|
| 499 |
+
"eval_accuracy": 0.8191489577293396,
|
| 500 |
+
"eval_loss": 0.6963978409767151,
|
| 501 |
+
"eval_runtime": 18.8086,
|
| 502 |
+
"eval_samples_per_second": 9.995,
|
| 503 |
+
"eval_steps_per_second": 2.499,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.64,
|
| 508 |
+
"learning_rate": 3.906810035842295e-05,
|
| 509 |
+
"loss": 0.2674,
|
| 510 |
+
"step": 340
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.64,
|
| 514 |
+
"eval_accuracy": 0.813829779624939,
|
| 515 |
+
"eval_loss": 0.6807590126991272,
|
| 516 |
+
"eval_runtime": 18.085,
|
| 517 |
+
"eval_samples_per_second": 10.395,
|
| 518 |
+
"eval_steps_per_second": 2.599,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.74,
|
| 523 |
+
"learning_rate": 3.727598566308244e-05,
|
| 524 |
+
"loss": 0.1163,
|
| 525 |
+
"step": 350
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.74,
|
| 529 |
+
"eval_accuracy": 0.8297872543334961,
|
| 530 |
+
"eval_loss": 0.6285024881362915,
|
| 531 |
+
"eval_runtime": 18.2735,
|
| 532 |
+
"eval_samples_per_second": 10.288,
|
| 533 |
+
"eval_steps_per_second": 2.572,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.85,
|
| 538 |
+
"learning_rate": 3.548387096774194e-05,
|
| 539 |
+
"loss": 0.1601,
|
| 540 |
+
"step": 360
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.85,
|
| 544 |
+
"eval_accuracy": 0.813829779624939,
|
| 545 |
+
"eval_loss": 0.68441241979599,
|
| 546 |
+
"eval_runtime": 18.2649,
|
| 547 |
+
"eval_samples_per_second": 10.293,
|
| 548 |
+
"eval_steps_per_second": 2.573,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.96,
|
| 553 |
+
"learning_rate": 3.369175627240144e-05,
|
| 554 |
+
"loss": 0.2855,
|
| 555 |
+
"step": 370
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.96,
|
| 559 |
+
"eval_accuracy": 0.792553186416626,
|
| 560 |
+
"eval_loss": 0.7759273052215576,
|
| 561 |
+
"eval_runtime": 16.9436,
|
| 562 |
+
"eval_samples_per_second": 11.096,
|
| 563 |
+
"eval_steps_per_second": 2.774,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 4.06,
|
| 568 |
+
"learning_rate": 3.1899641577060935e-05,
|
| 569 |
+
"loss": 0.2195,
|
| 570 |
+
"step": 380
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.06,
|
| 574 |
+
"eval_accuracy": 0.835106372833252,
|
| 575 |
+
"eval_loss": 0.6165522336959839,
|
| 576 |
+
"eval_runtime": 16.8992,
|
| 577 |
+
"eval_samples_per_second": 11.125,
|
| 578 |
+
"eval_steps_per_second": 2.781,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 4.17,
|
| 583 |
+
"learning_rate": 3.010752688172043e-05,
|
| 584 |
+
"loss": 0.2313,
|
| 585 |
+
"step": 390
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 4.17,
|
| 589 |
+
"eval_accuracy": 0.8457446694374084,
|
| 590 |
+
"eval_loss": 0.5867934823036194,
|
| 591 |
+
"eval_runtime": 16.9793,
|
| 592 |
+
"eval_samples_per_second": 11.072,
|
| 593 |
+
"eval_steps_per_second": 2.768,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 4.28,
|
| 598 |
+
"learning_rate": 2.831541218637993e-05,
|
| 599 |
+
"loss": 0.0568,
|
| 600 |
+
"step": 400
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 4.28,
|
| 604 |
+
"eval_accuracy": 0.8510638475418091,
|
| 605 |
+
"eval_loss": 0.5872617959976196,
|
| 606 |
+
"eval_runtime": 17.0099,
|
| 607 |
+
"eval_samples_per_second": 11.052,
|
| 608 |
+
"eval_steps_per_second": 2.763,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 4.39,
|
| 613 |
+
"learning_rate": 2.652329749103943e-05,
|
| 614 |
+
"loss": 0.1141,
|
| 615 |
+
"step": 410
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.39,
|
| 619 |
+
"eval_accuracy": 0.8563829660415649,
|
| 620 |
+
"eval_loss": 0.5599851012229919,
|
| 621 |
+
"eval_runtime": 17.0,
|
| 622 |
+
"eval_samples_per_second": 11.059,
|
| 623 |
+
"eval_steps_per_second": 2.765,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.49,
|
| 628 |
+
"learning_rate": 2.4731182795698928e-05,
|
| 629 |
+
"loss": 0.1607,
|
| 630 |
+
"step": 420
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 4.49,
|
| 634 |
+
"eval_accuracy": 0.8297872543334961,
|
| 635 |
+
"eval_loss": 0.6353866457939148,
|
| 636 |
+
"eval_runtime": 17.4021,
|
| 637 |
+
"eval_samples_per_second": 10.803,
|
| 638 |
+
"eval_steps_per_second": 2.701,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.6,
|
| 643 |
+
"learning_rate": 2.2939068100358423e-05,
|
| 644 |
+
"loss": 0.0994,
|
| 645 |
+
"step": 430
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.6,
|
| 649 |
+
"eval_accuracy": 0.8670212626457214,
|
| 650 |
+
"eval_loss": 0.5707226991653442,
|
| 651 |
+
"eval_runtime": 19.3599,
|
| 652 |
+
"eval_samples_per_second": 9.711,
|
| 653 |
+
"eval_steps_per_second": 2.428,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.71,
|
| 658 |
+
"learning_rate": 2.1146953405017922e-05,
|
| 659 |
+
"loss": 0.125,
|
| 660 |
+
"step": 440
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.71,
|
| 664 |
+
"eval_accuracy": 0.8510638475418091,
|
| 665 |
+
"eval_loss": 0.6016649007797241,
|
| 666 |
+
"eval_runtime": 18.1587,
|
| 667 |
+
"eval_samples_per_second": 10.353,
|
| 668 |
+
"eval_steps_per_second": 2.588,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 4.81,
|
| 673 |
+
"learning_rate": 1.935483870967742e-05,
|
| 674 |
+
"loss": 0.1598,
|
| 675 |
+
"step": 450
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.81,
|
| 679 |
+
"eval_accuracy": 0.8670212626457214,
|
| 680 |
+
"eval_loss": 0.5569073557853699,
|
| 681 |
+
"eval_runtime": 17.221,
|
| 682 |
+
"eval_samples_per_second": 10.917,
|
| 683 |
+
"eval_steps_per_second": 2.729,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.92,
|
| 688 |
+
"learning_rate": 1.7562724014336916e-05,
|
| 689 |
+
"loss": 0.1274,
|
| 690 |
+
"step": 460
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 4.92,
|
| 694 |
+
"eval_accuracy": 0.8670212626457214,
|
| 695 |
+
"eval_loss": 0.5385098457336426,
|
| 696 |
+
"eval_runtime": 17.4593,
|
| 697 |
+
"eval_samples_per_second": 10.768,
|
| 698 |
+
"eval_steps_per_second": 2.692,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 5.03,
|
| 703 |
+
"learning_rate": 1.5770609318996415e-05,
|
| 704 |
+
"loss": 0.131,
|
| 705 |
+
"step": 470
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 5.03,
|
| 709 |
+
"eval_accuracy": 0.8563829660415649,
|
| 710 |
+
"eval_loss": 0.5594031810760498,
|
| 711 |
+
"eval_runtime": 17.5202,
|
| 712 |
+
"eval_samples_per_second": 10.73,
|
| 713 |
+
"eval_steps_per_second": 2.683,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 5.13,
|
| 718 |
+
"learning_rate": 1.3978494623655914e-05,
|
| 719 |
+
"loss": 0.0754,
|
| 720 |
+
"step": 480
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 5.13,
|
| 724 |
+
"eval_accuracy": 0.8563829660415649,
|
| 725 |
+
"eval_loss": 0.5571564435958862,
|
| 726 |
+
"eval_runtime": 18.3965,
|
| 727 |
+
"eval_samples_per_second": 10.219,
|
| 728 |
+
"eval_steps_per_second": 2.555,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 5.24,
|
| 733 |
+
"learning_rate": 1.2186379928315413e-05,
|
| 734 |
+
"loss": 0.0298,
|
| 735 |
+
"step": 490
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 5.24,
|
| 739 |
+
"eval_accuracy": 0.8776595592498779,
|
| 740 |
+
"eval_loss": 0.5584980845451355,
|
| 741 |
+
"eval_runtime": 18.2497,
|
| 742 |
+
"eval_samples_per_second": 10.302,
|
| 743 |
+
"eval_steps_per_second": 2.575,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 5.35,
|
| 748 |
+
"learning_rate": 1.039426523297491e-05,
|
| 749 |
+
"loss": 0.012,
|
| 750 |
+
"step": 500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 5.35,
|
| 754 |
+
"eval_accuracy": 0.8723404407501221,
|
| 755 |
+
"eval_loss": 0.5599969625473022,
|
| 756 |
+
"eval_runtime": 17.3404,
|
| 757 |
+
"eval_samples_per_second": 10.842,
|
| 758 |
+
"eval_steps_per_second": 2.71,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 5.45,
|
| 763 |
+
"learning_rate": 8.602150537634409e-06,
|
| 764 |
+
"loss": 0.178,
|
| 765 |
+
"step": 510
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 5.45,
|
| 769 |
+
"eval_accuracy": 0.8723404407501221,
|
| 770 |
+
"eval_loss": 0.5632631778717041,
|
| 771 |
+
"eval_runtime": 17.983,
|
| 772 |
+
"eval_samples_per_second": 10.454,
|
| 773 |
+
"eval_steps_per_second": 2.614,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 5.56,
|
| 778 |
+
"learning_rate": 6.810035842293908e-06,
|
| 779 |
+
"loss": 0.0365,
|
| 780 |
+
"step": 520
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 5.56,
|
| 784 |
+
"eval_accuracy": 0.8670212626457214,
|
| 785 |
+
"eval_loss": 0.5653506517410278,
|
| 786 |
+
"eval_runtime": 18.484,
|
| 787 |
+
"eval_samples_per_second": 10.171,
|
| 788 |
+
"eval_steps_per_second": 2.543,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 5.67,
|
| 793 |
+
"learning_rate": 5.017921146953405e-06,
|
| 794 |
+
"loss": 0.0958,
|
| 795 |
+
"step": 530
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 5.67,
|
| 799 |
+
"eval_accuracy": 0.8723404407501221,
|
| 800 |
+
"eval_loss": 0.5490068197250366,
|
| 801 |
+
"eval_runtime": 16.8627,
|
| 802 |
+
"eval_samples_per_second": 11.149,
|
| 803 |
+
"eval_steps_per_second": 2.787,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 5.78,
|
| 808 |
+
"learning_rate": 3.225806451612903e-06,
|
| 809 |
+
"loss": 0.0525,
|
| 810 |
+
"step": 540
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 5.78,
|
| 814 |
+
"eval_accuracy": 0.8776595592498779,
|
| 815 |
+
"eval_loss": 0.542866051197052,
|
| 816 |
+
"eval_runtime": 18.0905,
|
| 817 |
+
"eval_samples_per_second": 10.392,
|
| 818 |
+
"eval_steps_per_second": 2.598,
|
| 819 |
+
"step": 540
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 5.88,
|
| 823 |
+
"learning_rate": 1.4336917562724014e-06,
|
| 824 |
+
"loss": 0.0144,
|
| 825 |
+
"step": 550
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 5.88,
|
| 829 |
+
"eval_accuracy": 0.8829787373542786,
|
| 830 |
+
"eval_loss": 0.5416831970214844,
|
| 831 |
+
"eval_runtime": 17.9022,
|
| 832 |
+
"eval_samples_per_second": 10.502,
|
| 833 |
+
"eval_steps_per_second": 2.625,
|
| 834 |
+
"step": 550
|
| 835 |
+
}
|
| 836 |
+
],
|
| 837 |
+
"logging_steps": 10,
|
| 838 |
+
"max_steps": 558,
|
| 839 |
+
"num_input_tokens_seen": 0,
|
| 840 |
+
"num_train_epochs": 6,
|
| 841 |
+
"save_steps": 10,
|
| 842 |
+
"total_flos": 7.083294890110614e+17,
|
| 843 |
+
"train_batch_size": 4,
|
| 844 |
+
"trial_name": null,
|
| 845 |
+
"trial_params": null
|
| 846 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98824b1aaba20a74df0687b35b3553c552d61da07f86be35e54bb41ea3990819
|
| 3 |
+
size 4728
|