Commit
•
ea3c0b1
1
Parent(s):
2e9194b
Upload 9 files
Browse files- config.json +130 -0
- optimizer.pt +3 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1351 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "D:\\PycharmProjects\\AER_ENGLISH\\wav2vec2-large-xlsr-53-english",
|
| 3 |
+
"activation_dropout": 0.05,
|
| 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": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 256,
|
| 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": true,
|
| 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": 0.05,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"finetuning_task": "wav2vec2_clf",
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.05,
|
| 58 |
+
"hidden_size": 1024,
|
| 59 |
+
"id2label": {
|
| 60 |
+
"0": "angry",
|
| 61 |
+
"1": "happy",
|
| 62 |
+
"2": "neutral",
|
| 63 |
+
"3": "sad"
|
| 64 |
+
},
|
| 65 |
+
"initializer_range": 0.02,
|
| 66 |
+
"intermediate_size": 4096,
|
| 67 |
+
"label2id": {
|
| 68 |
+
"angry": 0,
|
| 69 |
+
"happy": 1,
|
| 70 |
+
"neutral": 2,
|
| 71 |
+
"sad": 3
|
| 72 |
+
},
|
| 73 |
+
"layer_norm_eps": 1e-05,
|
| 74 |
+
"layerdrop": 0.05,
|
| 75 |
+
"mask_channel_length": 10,
|
| 76 |
+
"mask_channel_min_space": 1,
|
| 77 |
+
"mask_channel_other": 0.0,
|
| 78 |
+
"mask_channel_prob": 0.0,
|
| 79 |
+
"mask_channel_selection": "static",
|
| 80 |
+
"mask_feature_length": 10,
|
| 81 |
+
"mask_feature_min_masks": 0,
|
| 82 |
+
"mask_feature_prob": 0.0,
|
| 83 |
+
"mask_time_length": 10,
|
| 84 |
+
"mask_time_min_masks": 2,
|
| 85 |
+
"mask_time_min_space": 1,
|
| 86 |
+
"mask_time_other": 0.0,
|
| 87 |
+
"mask_time_prob": 0.05,
|
| 88 |
+
"mask_time_selection": "static",
|
| 89 |
+
"model_type": "wav2vec2",
|
| 90 |
+
"num_adapter_layers": 3,
|
| 91 |
+
"num_attention_heads": 16,
|
| 92 |
+
"num_codevector_groups": 2,
|
| 93 |
+
"num_codevectors_per_group": 320,
|
| 94 |
+
"num_conv_pos_embedding_groups": 16,
|
| 95 |
+
"num_conv_pos_embeddings": 128,
|
| 96 |
+
"num_feat_extract_layers": 7,
|
| 97 |
+
"num_hidden_layers": 24,
|
| 98 |
+
"num_negatives": 100,
|
| 99 |
+
"output_hidden_size": 1024,
|
| 100 |
+
"pad_token_id": 0,
|
| 101 |
+
"pooling_mode": "mean",
|
| 102 |
+
"problem_type": "single_label_classification",
|
| 103 |
+
"proj_codevector_dim": 256,
|
| 104 |
+
"tdnn_dilation": [
|
| 105 |
+
1,
|
| 106 |
+
2,
|
| 107 |
+
3,
|
| 108 |
+
1,
|
| 109 |
+
1
|
| 110 |
+
],
|
| 111 |
+
"tdnn_dim": [
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
512,
|
| 115 |
+
512,
|
| 116 |
+
1500
|
| 117 |
+
],
|
| 118 |
+
"tdnn_kernel": [
|
| 119 |
+
5,
|
| 120 |
+
3,
|
| 121 |
+
3,
|
| 122 |
+
1,
|
| 123 |
+
1
|
| 124 |
+
],
|
| 125 |
+
"torch_dtype": "float32",
|
| 126 |
+
"transformers_version": "4.29.2",
|
| 127 |
+
"use_weighted_layer_sum": false,
|
| 128 |
+
"vocab_size": 33,
|
| 129 |
+
"xvector_output_dim": 512
|
| 130 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:227ea10a0cc5559adf0b5919bd69c0b84f21c9f1f8c429ae6758fc96e53d1abb
|
| 3 |
+
size 2498491717
|
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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adc7cf78c831f7d654a0cf296a355c46ab1e3a1571dc63523610d1c75c8ecae3
|
| 3 |
+
size 1266117365
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d101375d77124aeda5ffb16b4a5d6858b063ce818ad9fbdb5b5ce05ba49cfd2
|
| 3 |
+
size 14639
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e8d407729cf398de31e94e18fff7f357437646319b163e49b1d38c97af5554b
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbbe56b494f428613e2af18e08ece3e17de14a2fa2e37347180bc3dcecca109d
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1351 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.94413407821229,
|
| 5 |
+
"global_step": 890,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 9.887640449438202e-05,
|
| 13 |
+
"loss": 1.3963,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"eval_accuracy": 0.33006536960601807,
|
| 19 |
+
"eval_loss": 1.3515560626983643,
|
| 20 |
+
"eval_runtime": 318.9295,
|
| 21 |
+
"eval_samples_per_second": 0.959,
|
| 22 |
+
"eval_steps_per_second": 0.241,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.22,
|
| 27 |
+
"learning_rate": 9.775280898876405e-05,
|
| 28 |
+
"loss": 1.2981,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.22,
|
| 33 |
+
"eval_accuracy": 0.30392158031463623,
|
| 34 |
+
"eval_loss": 1.2864599227905273,
|
| 35 |
+
"eval_runtime": 533.6299,
|
| 36 |
+
"eval_samples_per_second": 0.573,
|
| 37 |
+
"eval_steps_per_second": 0.144,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.34,
|
| 42 |
+
"learning_rate": 9.662921348314608e-05,
|
| 43 |
+
"loss": 1.2614,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.34,
|
| 48 |
+
"eval_accuracy": 0.6535947918891907,
|
| 49 |
+
"eval_loss": 0.9824705719947815,
|
| 50 |
+
"eval_runtime": 348.7575,
|
| 51 |
+
"eval_samples_per_second": 0.877,
|
| 52 |
+
"eval_steps_per_second": 0.221,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.45,
|
| 57 |
+
"learning_rate": 9.550561797752809e-05,
|
| 58 |
+
"loss": 0.9419,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.45,
|
| 63 |
+
"eval_accuracy": 0.49346405267715454,
|
| 64 |
+
"eval_loss": 1.0978724956512451,
|
| 65 |
+
"eval_runtime": 312.9714,
|
| 66 |
+
"eval_samples_per_second": 0.978,
|
| 67 |
+
"eval_steps_per_second": 0.246,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.56,
|
| 72 |
+
"learning_rate": 9.438202247191012e-05,
|
| 73 |
+
"loss": 0.9813,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.56,
|
| 78 |
+
"eval_accuracy": 0.5196078419685364,
|
| 79 |
+
"eval_loss": 0.9674614667892456,
|
| 80 |
+
"eval_runtime": 312.3793,
|
| 81 |
+
"eval_samples_per_second": 0.98,
|
| 82 |
+
"eval_steps_per_second": 0.246,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.67,
|
| 87 |
+
"learning_rate": 9.325842696629214e-05,
|
| 88 |
+
"loss": 0.7973,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.67,
|
| 93 |
+
"eval_accuracy": 0.5947712659835815,
|
| 94 |
+
"eval_loss": 1.0033761262893677,
|
| 95 |
+
"eval_runtime": 316.8558,
|
| 96 |
+
"eval_samples_per_second": 0.966,
|
| 97 |
+
"eval_steps_per_second": 0.243,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.78,
|
| 102 |
+
"learning_rate": 9.213483146067416e-05,
|
| 103 |
+
"loss": 0.9575,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.78,
|
| 108 |
+
"eval_accuracy": 0.5882353186607361,
|
| 109 |
+
"eval_loss": 0.8489904403686523,
|
| 110 |
+
"eval_runtime": 535.4904,
|
| 111 |
+
"eval_samples_per_second": 0.571,
|
| 112 |
+
"eval_steps_per_second": 0.144,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.89,
|
| 117 |
+
"learning_rate": 9.112359550561799e-05,
|
| 118 |
+
"loss": 0.8752,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.89,
|
| 123 |
+
"eval_accuracy": 0.6895424723625183,
|
| 124 |
+
"eval_loss": 0.7460987567901611,
|
| 125 |
+
"eval_runtime": 597.5484,
|
| 126 |
+
"eval_samples_per_second": 0.512,
|
| 127 |
+
"eval_steps_per_second": 0.129,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.01,
|
| 132 |
+
"learning_rate": 9e-05,
|
| 133 |
+
"loss": 0.719,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.01,
|
| 138 |
+
"eval_accuracy": 0.7973856329917908,
|
| 139 |
+
"eval_loss": 0.5500715374946594,
|
| 140 |
+
"eval_runtime": 583.2832,
|
| 141 |
+
"eval_samples_per_second": 0.525,
|
| 142 |
+
"eval_steps_per_second": 0.132,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.12,
|
| 147 |
+
"learning_rate": 8.887640449438202e-05,
|
| 148 |
+
"loss": 0.5311,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.12,
|
| 153 |
+
"eval_accuracy": 0.7973856329917908,
|
| 154 |
+
"eval_loss": 0.5389693379402161,
|
| 155 |
+
"eval_runtime": 590.4987,
|
| 156 |
+
"eval_samples_per_second": 0.518,
|
| 157 |
+
"eval_steps_per_second": 0.13,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.23,
|
| 162 |
+
"learning_rate": 8.775280898876405e-05,
|
| 163 |
+
"loss": 0.3922,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.23,
|
| 168 |
+
"eval_accuracy": 0.843137264251709,
|
| 169 |
+
"eval_loss": 0.42480573058128357,
|
| 170 |
+
"eval_runtime": 597.2704,
|
| 171 |
+
"eval_samples_per_second": 0.512,
|
| 172 |
+
"eval_steps_per_second": 0.129,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.34,
|
| 177 |
+
"learning_rate": 8.662921348314608e-05,
|
| 178 |
+
"loss": 0.3043,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.34,
|
| 183 |
+
"eval_accuracy": 0.8496732115745544,
|
| 184 |
+
"eval_loss": 0.5262107253074646,
|
| 185 |
+
"eval_runtime": 618.0607,
|
| 186 |
+
"eval_samples_per_second": 0.495,
|
| 187 |
+
"eval_steps_per_second": 0.125,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.45,
|
| 192 |
+
"learning_rate": 8.550561797752809e-05,
|
| 193 |
+
"loss": 0.7841,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.45,
|
| 198 |
+
"eval_accuracy": 0.8202614188194275,
|
| 199 |
+
"eval_loss": 0.618194580078125,
|
| 200 |
+
"eval_runtime": 480.4521,
|
| 201 |
+
"eval_samples_per_second": 0.637,
|
| 202 |
+
"eval_steps_per_second": 0.16,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.56,
|
| 207 |
+
"learning_rate": 8.438202247191012e-05,
|
| 208 |
+
"loss": 0.4881,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.56,
|
| 213 |
+
"eval_accuracy": 0.8333333134651184,
|
| 214 |
+
"eval_loss": 0.4706672728061676,
|
| 215 |
+
"eval_runtime": 546.9776,
|
| 216 |
+
"eval_samples_per_second": 0.559,
|
| 217 |
+
"eval_steps_per_second": 0.141,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.68,
|
| 222 |
+
"learning_rate": 8.325842696629214e-05,
|
| 223 |
+
"loss": 0.39,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.68,
|
| 228 |
+
"eval_accuracy": 0.8594771027565002,
|
| 229 |
+
"eval_loss": 0.4261144995689392,
|
| 230 |
+
"eval_runtime": 314.3222,
|
| 231 |
+
"eval_samples_per_second": 0.974,
|
| 232 |
+
"eval_steps_per_second": 0.245,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.79,
|
| 237 |
+
"learning_rate": 8.213483146067417e-05,
|
| 238 |
+
"loss": 0.4687,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.79,
|
| 243 |
+
"eval_accuracy": 0.7745097875595093,
|
| 244 |
+
"eval_loss": 0.7588664293289185,
|
| 245 |
+
"eval_runtime": 316.9261,
|
| 246 |
+
"eval_samples_per_second": 0.966,
|
| 247 |
+
"eval_steps_per_second": 0.243,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.9,
|
| 252 |
+
"learning_rate": 8.101123595505618e-05,
|
| 253 |
+
"loss": 0.4289,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.9,
|
| 258 |
+
"eval_accuracy": 0.843137264251709,
|
| 259 |
+
"eval_loss": 0.4307919144630432,
|
| 260 |
+
"eval_runtime": 299.2563,
|
| 261 |
+
"eval_samples_per_second": 1.023,
|
| 262 |
+
"eval_steps_per_second": 0.257,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.01,
|
| 267 |
+
"learning_rate": 7.988764044943821e-05,
|
| 268 |
+
"loss": 0.4127,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.01,
|
| 273 |
+
"eval_accuracy": 0.9117646813392639,
|
| 274 |
+
"eval_loss": 0.30210039019584656,
|
| 275 |
+
"eval_runtime": 293.1021,
|
| 276 |
+
"eval_samples_per_second": 1.044,
|
| 277 |
+
"eval_steps_per_second": 0.263,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.12,
|
| 282 |
+
"learning_rate": 7.876404494382022e-05,
|
| 283 |
+
"loss": 0.3205,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.12,
|
| 288 |
+
"eval_accuracy": 0.9052287340164185,
|
| 289 |
+
"eval_loss": 0.3764496445655823,
|
| 290 |
+
"eval_runtime": 626.3698,
|
| 291 |
+
"eval_samples_per_second": 0.489,
|
| 292 |
+
"eval_steps_per_second": 0.123,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.23,
|
| 297 |
+
"learning_rate": 7.764044943820225e-05,
|
| 298 |
+
"loss": 0.302,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.23,
|
| 303 |
+
"eval_accuracy": 0.8169934749603271,
|
| 304 |
+
"eval_loss": 0.6414448618888855,
|
| 305 |
+
"eval_runtime": 406.1799,
|
| 306 |
+
"eval_samples_per_second": 0.753,
|
| 307 |
+
"eval_steps_per_second": 0.19,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.35,
|
| 312 |
+
"learning_rate": 7.651685393258428e-05,
|
| 313 |
+
"loss": 0.2767,
|
| 314 |
+
"step": 210
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.35,
|
| 318 |
+
"eval_accuracy": 0.8856208920478821,
|
| 319 |
+
"eval_loss": 0.3875592350959778,
|
| 320 |
+
"eval_runtime": 358.8222,
|
| 321 |
+
"eval_samples_per_second": 0.853,
|
| 322 |
+
"eval_steps_per_second": 0.215,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.46,
|
| 327 |
+
"learning_rate": 7.53932584269663e-05,
|
| 328 |
+
"loss": 0.4107,
|
| 329 |
+
"step": 220
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.46,
|
| 333 |
+
"eval_accuracy": 0.8104575276374817,
|
| 334 |
+
"eval_loss": 0.6241660118103027,
|
| 335 |
+
"eval_runtime": 301.8068,
|
| 336 |
+
"eval_samples_per_second": 1.014,
|
| 337 |
+
"eval_steps_per_second": 0.255,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.57,
|
| 342 |
+
"learning_rate": 7.426966292134831e-05,
|
| 343 |
+
"loss": 0.4392,
|
| 344 |
+
"step": 230
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.57,
|
| 348 |
+
"eval_accuracy": 0.9183006286621094,
|
| 349 |
+
"eval_loss": 0.2545139491558075,
|
| 350 |
+
"eval_runtime": 315.8591,
|
| 351 |
+
"eval_samples_per_second": 0.969,
|
| 352 |
+
"eval_steps_per_second": 0.244,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.68,
|
| 357 |
+
"learning_rate": 7.314606741573034e-05,
|
| 358 |
+
"loss": 0.2376,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.68,
|
| 363 |
+
"eval_accuracy": 0.8496732115745544,
|
| 364 |
+
"eval_loss": 0.49588432908058167,
|
| 365 |
+
"eval_runtime": 304.5879,
|
| 366 |
+
"eval_samples_per_second": 1.005,
|
| 367 |
+
"eval_steps_per_second": 0.253,
|
| 368 |
+
"step": 240
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.79,
|
| 372 |
+
"learning_rate": 7.202247191011237e-05,
|
| 373 |
+
"loss": 0.4715,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.79,
|
| 378 |
+
"eval_accuracy": 0.8235294222831726,
|
| 379 |
+
"eval_loss": 0.6127722859382629,
|
| 380 |
+
"eval_runtime": 296.1686,
|
| 381 |
+
"eval_samples_per_second": 1.033,
|
| 382 |
+
"eval_steps_per_second": 0.26,
|
| 383 |
+
"step": 250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.91,
|
| 387 |
+
"learning_rate": 7.089887640449438e-05,
|
| 388 |
+
"loss": 0.2753,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.91,
|
| 393 |
+
"eval_accuracy": 0.898692786693573,
|
| 394 |
+
"eval_loss": 0.33089637756347656,
|
| 395 |
+
"eval_runtime": 318.4459,
|
| 396 |
+
"eval_samples_per_second": 0.961,
|
| 397 |
+
"eval_steps_per_second": 0.242,
|
| 398 |
+
"step": 260
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.02,
|
| 402 |
+
"learning_rate": 6.97752808988764e-05,
|
| 403 |
+
"loss": 0.2919,
|
| 404 |
+
"step": 270
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.02,
|
| 408 |
+
"eval_accuracy": 0.8921568393707275,
|
| 409 |
+
"eval_loss": 0.41311776638031006,
|
| 410 |
+
"eval_runtime": 285.5443,
|
| 411 |
+
"eval_samples_per_second": 1.072,
|
| 412 |
+
"eval_steps_per_second": 0.27,
|
| 413 |
+
"step": 270
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.13,
|
| 417 |
+
"learning_rate": 6.865168539325843e-05,
|
| 418 |
+
"loss": 0.2222,
|
| 419 |
+
"step": 280
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.13,
|
| 423 |
+
"eval_accuracy": 0.898692786693573,
|
| 424 |
+
"eval_loss": 0.3918479084968567,
|
| 425 |
+
"eval_runtime": 297.6229,
|
| 426 |
+
"eval_samples_per_second": 1.028,
|
| 427 |
+
"eval_steps_per_second": 0.259,
|
| 428 |
+
"step": 280
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.24,
|
| 432 |
+
"learning_rate": 6.752808988764046e-05,
|
| 433 |
+
"loss": 0.0371,
|
| 434 |
+
"step": 290
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.24,
|
| 438 |
+
"eval_accuracy": 0.9183006286621094,
|
| 439 |
+
"eval_loss": 0.28783220052719116,
|
| 440 |
+
"eval_runtime": 293.7099,
|
| 441 |
+
"eval_samples_per_second": 1.042,
|
| 442 |
+
"eval_steps_per_second": 0.262,
|
| 443 |
+
"step": 290
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.35,
|
| 447 |
+
"learning_rate": 6.640449438202247e-05,
|
| 448 |
+
"loss": 0.0172,
|
| 449 |
+
"step": 300
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.35,
|
| 453 |
+
"eval_accuracy": 0.9215686321258545,
|
| 454 |
+
"eval_loss": 0.3087099492549896,
|
| 455 |
+
"eval_runtime": 317.6569,
|
| 456 |
+
"eval_samples_per_second": 0.963,
|
| 457 |
+
"eval_steps_per_second": 0.242,
|
| 458 |
+
"step": 300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.46,
|
| 462 |
+
"learning_rate": 6.52808988764045e-05,
|
| 463 |
+
"loss": 0.1953,
|
| 464 |
+
"step": 310
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.46,
|
| 468 |
+
"eval_accuracy": 0.9183006286621094,
|
| 469 |
+
"eval_loss": 0.29489144682884216,
|
| 470 |
+
"eval_runtime": 293.4224,
|
| 471 |
+
"eval_samples_per_second": 1.043,
|
| 472 |
+
"eval_steps_per_second": 0.262,
|
| 473 |
+
"step": 310
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.58,
|
| 477 |
+
"learning_rate": 6.415730337078652e-05,
|
| 478 |
+
"loss": 0.2093,
|
| 479 |
+
"step": 320
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.58,
|
| 483 |
+
"eval_accuracy": 0.8921568393707275,
|
| 484 |
+
"eval_loss": 0.38903045654296875,
|
| 485 |
+
"eval_runtime": 313.0985,
|
| 486 |
+
"eval_samples_per_second": 0.977,
|
| 487 |
+
"eval_steps_per_second": 0.246,
|
| 488 |
+
"step": 320
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.69,
|
| 492 |
+
"learning_rate": 6.303370786516854e-05,
|
| 493 |
+
"loss": 0.1393,
|
| 494 |
+
"step": 330
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.69,
|
| 498 |
+
"eval_accuracy": 0.898692786693573,
|
| 499 |
+
"eval_loss": 0.34058284759521484,
|
| 500 |
+
"eval_runtime": 316.0484,
|
| 501 |
+
"eval_samples_per_second": 0.968,
|
| 502 |
+
"eval_steps_per_second": 0.244,
|
| 503 |
+
"step": 330
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.8,
|
| 507 |
+
"learning_rate": 6.191011235955056e-05,
|
| 508 |
+
"loss": 0.0532,
|
| 509 |
+
"step": 340
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 3.8,
|
| 513 |
+
"eval_accuracy": 0.9313725233078003,
|
| 514 |
+
"eval_loss": 0.38309353590011597,
|
| 515 |
+
"eval_runtime": 315.0427,
|
| 516 |
+
"eval_samples_per_second": 0.971,
|
| 517 |
+
"eval_steps_per_second": 0.244,
|
| 518 |
+
"step": 340
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.91,
|
| 522 |
+
"learning_rate": 6.078651685393258e-05,
|
| 523 |
+
"loss": 0.2061,
|
| 524 |
+
"step": 350
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.91,
|
| 528 |
+
"eval_accuracy": 0.8954248428344727,
|
| 529 |
+
"eval_loss": 0.43487662076950073,
|
| 530 |
+
"eval_runtime": 308.5388,
|
| 531 |
+
"eval_samples_per_second": 0.992,
|
| 532 |
+
"eval_steps_per_second": 0.25,
|
| 533 |
+
"step": 350
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.02,
|
| 537 |
+
"learning_rate": 5.96629213483146e-05,
|
| 538 |
+
"loss": 0.1755,
|
| 539 |
+
"step": 360
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.02,
|
| 543 |
+
"eval_accuracy": 0.8954248428344727,
|
| 544 |
+
"eval_loss": 0.4112664461135864,
|
| 545 |
+
"eval_runtime": 314.6158,
|
| 546 |
+
"eval_samples_per_second": 0.973,
|
| 547 |
+
"eval_steps_per_second": 0.245,
|
| 548 |
+
"step": 360
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.13,
|
| 552 |
+
"learning_rate": 5.853932584269663e-05,
|
| 553 |
+
"loss": 0.0155,
|
| 554 |
+
"step": 370
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.13,
|
| 558 |
+
"eval_accuracy": 0.9084967374801636,
|
| 559 |
+
"eval_loss": 0.34788793325424194,
|
| 560 |
+
"eval_runtime": 317.1579,
|
| 561 |
+
"eval_samples_per_second": 0.965,
|
| 562 |
+
"eval_steps_per_second": 0.243,
|
| 563 |
+
"step": 370
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 4.25,
|
| 567 |
+
"learning_rate": 5.7415730337078654e-05,
|
| 568 |
+
"loss": 0.1389,
|
| 569 |
+
"step": 380
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.25,
|
| 573 |
+
"eval_accuracy": 0.9248365759849548,
|
| 574 |
+
"eval_loss": 0.28591012954711914,
|
| 575 |
+
"eval_runtime": 323.1301,
|
| 576 |
+
"eval_samples_per_second": 0.947,
|
| 577 |
+
"eval_steps_per_second": 0.238,
|
| 578 |
+
"step": 380
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.36,
|
| 582 |
+
"learning_rate": 5.6292134831460676e-05,
|
| 583 |
+
"loss": 0.1102,
|
| 584 |
+
"step": 390
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.36,
|
| 588 |
+
"eval_accuracy": 0.9183006286621094,
|
| 589 |
+
"eval_loss": 0.2804703712463379,
|
| 590 |
+
"eval_runtime": 308.9869,
|
| 591 |
+
"eval_samples_per_second": 0.99,
|
| 592 |
+
"eval_steps_per_second": 0.249,
|
| 593 |
+
"step": 390
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.47,
|
| 597 |
+
"learning_rate": 5.516853932584269e-05,
|
| 598 |
+
"loss": 0.0447,
|
| 599 |
+
"step": 400
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 4.47,
|
| 603 |
+
"eval_accuracy": 0.9281045794487,
|
| 604 |
+
"eval_loss": 0.28759482502937317,
|
| 605 |
+
"eval_runtime": 325.9228,
|
| 606 |
+
"eval_samples_per_second": 0.939,
|
| 607 |
+
"eval_steps_per_second": 0.236,
|
| 608 |
+
"step": 400
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 4.58,
|
| 612 |
+
"learning_rate": 5.4044943820224726e-05,
|
| 613 |
+
"loss": 0.3047,
|
| 614 |
+
"step": 410
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 4.58,
|
| 618 |
+
"eval_accuracy": 0.9281045794487,
|
| 619 |
+
"eval_loss": 0.28950873017311096,
|
| 620 |
+
"eval_runtime": 302.1849,
|
| 621 |
+
"eval_samples_per_second": 1.013,
|
| 622 |
+
"eval_steps_per_second": 0.255,
|
| 623 |
+
"step": 410
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 4.69,
|
| 627 |
+
"learning_rate": 5.292134831460674e-05,
|
| 628 |
+
"loss": 0.2309,
|
| 629 |
+
"step": 420
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 4.69,
|
| 633 |
+
"eval_accuracy": 0.9313725233078003,
|
| 634 |
+
"eval_loss": 0.20166385173797607,
|
| 635 |
+
"eval_runtime": 313.1316,
|
| 636 |
+
"eval_samples_per_second": 0.977,
|
| 637 |
+
"eval_steps_per_second": 0.246,
|
| 638 |
+
"step": 420
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.8,
|
| 642 |
+
"learning_rate": 5.179775280898876e-05,
|
| 643 |
+
"loss": 0.2097,
|
| 644 |
+
"step": 430
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.8,
|
| 648 |
+
"eval_accuracy": 0.8692810535430908,
|
| 649 |
+
"eval_loss": 0.4348565936088562,
|
| 650 |
+
"eval_runtime": 328.5983,
|
| 651 |
+
"eval_samples_per_second": 0.931,
|
| 652 |
+
"eval_steps_per_second": 0.234,
|
| 653 |
+
"step": 430
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.92,
|
| 657 |
+
"learning_rate": 5.0674157303370785e-05,
|
| 658 |
+
"loss": 0.0094,
|
| 659 |
+
"step": 440
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 4.92,
|
| 663 |
+
"eval_accuracy": 0.898692786693573,
|
| 664 |
+
"eval_loss": 0.3308834135532379,
|
| 665 |
+
"eval_runtime": 261.8274,
|
| 666 |
+
"eval_samples_per_second": 1.169,
|
| 667 |
+
"eval_steps_per_second": 0.294,
|
| 668 |
+
"step": 440
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 5.03,
|
| 672 |
+
"learning_rate": 4.955056179775281e-05,
|
| 673 |
+
"loss": 0.0068,
|
| 674 |
+
"step": 450
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 5.03,
|
| 678 |
+
"eval_accuracy": 0.9379084706306458,
|
| 679 |
+
"eval_loss": 0.22690723836421967,
|
| 680 |
+
"eval_runtime": 321.9057,
|
| 681 |
+
"eval_samples_per_second": 0.951,
|
| 682 |
+
"eval_steps_per_second": 0.239,
|
| 683 |
+
"step": 450
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 5.14,
|
| 687 |
+
"learning_rate": 4.8426966292134836e-05,
|
| 688 |
+
"loss": 0.0428,
|
| 689 |
+
"step": 460
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 5.14,
|
| 693 |
+
"eval_accuracy": 0.9313725233078003,
|
| 694 |
+
"eval_loss": 0.24997933208942413,
|
| 695 |
+
"eval_runtime": 306.0175,
|
| 696 |
+
"eval_samples_per_second": 1.0,
|
| 697 |
+
"eval_steps_per_second": 0.252,
|
| 698 |
+
"step": 460
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 5.25,
|
| 702 |
+
"learning_rate": 4.730337078651685e-05,
|
| 703 |
+
"loss": 0.0555,
|
| 704 |
+
"step": 470
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 5.25,
|
| 708 |
+
"eval_accuracy": 0.8888888955116272,
|
| 709 |
+
"eval_loss": 0.4563826024532318,
|
| 710 |
+
"eval_runtime": 304.3479,
|
| 711 |
+
"eval_samples_per_second": 1.005,
|
| 712 |
+
"eval_steps_per_second": 0.253,
|
| 713 |
+
"step": 470
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 5.36,
|
| 717 |
+
"learning_rate": 4.617977528089888e-05,
|
| 718 |
+
"loss": 0.0928,
|
| 719 |
+
"step": 480
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 5.36,
|
| 723 |
+
"eval_accuracy": 0.915032684803009,
|
| 724 |
+
"eval_loss": 0.3516130745410919,
|
| 725 |
+
"eval_runtime": 320.668,
|
| 726 |
+
"eval_samples_per_second": 0.954,
|
| 727 |
+
"eval_steps_per_second": 0.24,
|
| 728 |
+
"step": 480
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 5.47,
|
| 732 |
+
"learning_rate": 4.50561797752809e-05,
|
| 733 |
+
"loss": 0.1947,
|
| 734 |
+
"step": 490
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 5.47,
|
| 738 |
+
"eval_accuracy": 0.9379084706306458,
|
| 739 |
+
"eval_loss": 0.24630288779735565,
|
| 740 |
+
"eval_runtime": 305.3109,
|
| 741 |
+
"eval_samples_per_second": 1.002,
|
| 742 |
+
"eval_steps_per_second": 0.252,
|
| 743 |
+
"step": 490
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 5.59,
|
| 747 |
+
"learning_rate": 4.393258426966292e-05,
|
| 748 |
+
"loss": 0.0934,
|
| 749 |
+
"step": 500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 5.59,
|
| 753 |
+
"eval_accuracy": 0.9477124214172363,
|
| 754 |
+
"eval_loss": 0.18016140162944794,
|
| 755 |
+
"eval_runtime": 308.018,
|
| 756 |
+
"eval_samples_per_second": 0.993,
|
| 757 |
+
"eval_steps_per_second": 0.25,
|
| 758 |
+
"step": 500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 5.7,
|
| 762 |
+
"learning_rate": 4.2808988764044945e-05,
|
| 763 |
+
"loss": 0.0035,
|
| 764 |
+
"step": 510
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 5.7,
|
| 768 |
+
"eval_accuracy": 0.9411764740943909,
|
| 769 |
+
"eval_loss": 0.22933033108711243,
|
| 770 |
+
"eval_runtime": 316.2253,
|
| 771 |
+
"eval_samples_per_second": 0.968,
|
| 772 |
+
"eval_steps_per_second": 0.243,
|
| 773 |
+
"step": 510
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 5.81,
|
| 777 |
+
"learning_rate": 4.168539325842697e-05,
|
| 778 |
+
"loss": 0.0038,
|
| 779 |
+
"step": 520
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 5.81,
|
| 783 |
+
"eval_accuracy": 0.9215686321258545,
|
| 784 |
+
"eval_loss": 0.2865773141384125,
|
| 785 |
+
"eval_runtime": 306.9042,
|
| 786 |
+
"eval_samples_per_second": 0.997,
|
| 787 |
+
"eval_steps_per_second": 0.251,
|
| 788 |
+
"step": 520
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 5.92,
|
| 792 |
+
"learning_rate": 4.056179775280899e-05,
|
| 793 |
+
"loss": 0.0027,
|
| 794 |
+
"step": 530
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 5.92,
|
| 798 |
+
"eval_accuracy": 0.915032684803009,
|
| 799 |
+
"eval_loss": 0.3221026659011841,
|
| 800 |
+
"eval_runtime": 308.5611,
|
| 801 |
+
"eval_samples_per_second": 0.992,
|
| 802 |
+
"eval_steps_per_second": 0.25,
|
| 803 |
+
"step": 530
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 6.03,
|
| 807 |
+
"learning_rate": 3.943820224719101e-05,
|
| 808 |
+
"loss": 0.0586,
|
| 809 |
+
"step": 540
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 6.03,
|
| 813 |
+
"eval_accuracy": 0.9215686321258545,
|
| 814 |
+
"eval_loss": 0.2714509665966034,
|
| 815 |
+
"eval_runtime": 307.936,
|
| 816 |
+
"eval_samples_per_second": 0.994,
|
| 817 |
+
"eval_steps_per_second": 0.25,
|
| 818 |
+
"step": 540
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 6.15,
|
| 822 |
+
"learning_rate": 3.831460674157303e-05,
|
| 823 |
+
"loss": 0.003,
|
| 824 |
+
"step": 550
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 6.15,
|
| 828 |
+
"eval_accuracy": 0.9117646813392639,
|
| 829 |
+
"eval_loss": 0.2935124635696411,
|
| 830 |
+
"eval_runtime": 322.5288,
|
| 831 |
+
"eval_samples_per_second": 0.949,
|
| 832 |
+
"eval_steps_per_second": 0.239,
|
| 833 |
+
"step": 550
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 6.26,
|
| 837 |
+
"learning_rate": 3.719101123595506e-05,
|
| 838 |
+
"loss": 0.0748,
|
| 839 |
+
"step": 560
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 6.26,
|
| 843 |
+
"eval_accuracy": 0.9379084706306458,
|
| 844 |
+
"eval_loss": 0.2554876506328583,
|
| 845 |
+
"eval_runtime": 310.2055,
|
| 846 |
+
"eval_samples_per_second": 0.986,
|
| 847 |
+
"eval_steps_per_second": 0.248,
|
| 848 |
+
"step": 560
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 6.37,
|
| 852 |
+
"learning_rate": 3.6179775280898874e-05,
|
| 853 |
+
"loss": 0.0273,
|
| 854 |
+
"step": 570
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 6.37,
|
| 858 |
+
"eval_accuracy": 0.9477124214172363,
|
| 859 |
+
"eval_loss": 0.26076748967170715,
|
| 860 |
+
"eval_runtime": 309.3501,
|
| 861 |
+
"eval_samples_per_second": 0.989,
|
| 862 |
+
"eval_steps_per_second": 0.249,
|
| 863 |
+
"step": 570
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 6.48,
|
| 867 |
+
"learning_rate": 3.50561797752809e-05,
|
| 868 |
+
"loss": 0.0021,
|
| 869 |
+
"step": 580
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 6.48,
|
| 873 |
+
"eval_accuracy": 0.9542483687400818,
|
| 874 |
+
"eval_loss": 0.2612459659576416,
|
| 875 |
+
"eval_runtime": 317.8944,
|
| 876 |
+
"eval_samples_per_second": 0.963,
|
| 877 |
+
"eval_steps_per_second": 0.242,
|
| 878 |
+
"step": 580
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 6.59,
|
| 882 |
+
"learning_rate": 3.393258426966292e-05,
|
| 883 |
+
"loss": 0.0042,
|
| 884 |
+
"step": 590
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 6.59,
|
| 888 |
+
"eval_accuracy": 0.9575163125991821,
|
| 889 |
+
"eval_loss": 0.24474120140075684,
|
| 890 |
+
"eval_runtime": 308.9228,
|
| 891 |
+
"eval_samples_per_second": 0.991,
|
| 892 |
+
"eval_steps_per_second": 0.249,
|
| 893 |
+
"step": 590
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 6.7,
|
| 897 |
+
"learning_rate": 3.2808988764044946e-05,
|
| 898 |
+
"loss": 0.0274,
|
| 899 |
+
"step": 600
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 6.7,
|
| 903 |
+
"eval_accuracy": 0.9542483687400818,
|
| 904 |
+
"eval_loss": 0.23039507865905762,
|
| 905 |
+
"eval_runtime": 311.9509,
|
| 906 |
+
"eval_samples_per_second": 0.981,
|
| 907 |
+
"eval_steps_per_second": 0.247,
|
| 908 |
+
"step": 600
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 6.82,
|
| 912 |
+
"learning_rate": 3.168539325842697e-05,
|
| 913 |
+
"loss": 0.0037,
|
| 914 |
+
"step": 610
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 6.82,
|
| 918 |
+
"eval_accuracy": 0.9542483687400818,
|
| 919 |
+
"eval_loss": 0.22053539752960205,
|
| 920 |
+
"eval_runtime": 315.7913,
|
| 921 |
+
"eval_samples_per_second": 0.969,
|
| 922 |
+
"eval_steps_per_second": 0.244,
|
| 923 |
+
"step": 610
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 6.93,
|
| 927 |
+
"learning_rate": 3.056179775280899e-05,
|
| 928 |
+
"loss": 0.0059,
|
| 929 |
+
"step": 620
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 6.93,
|
| 933 |
+
"eval_accuracy": 0.9379084706306458,
|
| 934 |
+
"eval_loss": 0.26862725615501404,
|
| 935 |
+
"eval_runtime": 321.9798,
|
| 936 |
+
"eval_samples_per_second": 0.95,
|
| 937 |
+
"eval_steps_per_second": 0.239,
|
| 938 |
+
"step": 620
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 7.04,
|
| 942 |
+
"learning_rate": 2.9438202247191012e-05,
|
| 943 |
+
"loss": 0.002,
|
| 944 |
+
"step": 630
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 7.04,
|
| 948 |
+
"eval_accuracy": 0.9379084706306458,
|
| 949 |
+
"eval_loss": 0.29074591398239136,
|
| 950 |
+
"eval_runtime": 311.6792,
|
| 951 |
+
"eval_samples_per_second": 0.982,
|
| 952 |
+
"eval_steps_per_second": 0.247,
|
| 953 |
+
"step": 630
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 7.15,
|
| 957 |
+
"learning_rate": 2.8314606741573037e-05,
|
| 958 |
+
"loss": 0.0214,
|
| 959 |
+
"step": 640
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 7.15,
|
| 963 |
+
"eval_accuracy": 0.9509803652763367,
|
| 964 |
+
"eval_loss": 0.217881441116333,
|
| 965 |
+
"eval_runtime": 312.0489,
|
| 966 |
+
"eval_samples_per_second": 0.981,
|
| 967 |
+
"eval_steps_per_second": 0.247,
|
| 968 |
+
"step": 640
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 7.26,
|
| 972 |
+
"learning_rate": 2.7191011235955055e-05,
|
| 973 |
+
"loss": 0.0011,
|
| 974 |
+
"step": 650
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 7.26,
|
| 978 |
+
"eval_accuracy": 0.9444444179534912,
|
| 979 |
+
"eval_loss": 0.24239015579223633,
|
| 980 |
+
"eval_runtime": 320.4623,
|
| 981 |
+
"eval_samples_per_second": 0.955,
|
| 982 |
+
"eval_steps_per_second": 0.24,
|
| 983 |
+
"step": 650
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 7.37,
|
| 987 |
+
"learning_rate": 2.606741573033708e-05,
|
| 988 |
+
"loss": 0.1222,
|
| 989 |
+
"step": 660
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 7.37,
|
| 993 |
+
"eval_accuracy": 0.9607843160629272,
|
| 994 |
+
"eval_loss": 0.22233766317367554,
|
| 995 |
+
"eval_runtime": 316.2672,
|
| 996 |
+
"eval_samples_per_second": 0.968,
|
| 997 |
+
"eval_steps_per_second": 0.243,
|
| 998 |
+
"step": 660
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 7.49,
|
| 1002 |
+
"learning_rate": 2.4943820224719103e-05,
|
| 1003 |
+
"loss": 0.0308,
|
| 1004 |
+
"step": 670
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 7.49,
|
| 1008 |
+
"eval_accuracy": 0.9542483687400818,
|
| 1009 |
+
"eval_loss": 0.23289808630943298,
|
| 1010 |
+
"eval_runtime": 314.263,
|
| 1011 |
+
"eval_samples_per_second": 0.974,
|
| 1012 |
+
"eval_steps_per_second": 0.245,
|
| 1013 |
+
"step": 670
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 7.6,
|
| 1017 |
+
"learning_rate": 2.3820224719101125e-05,
|
| 1018 |
+
"loss": 0.0047,
|
| 1019 |
+
"step": 680
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 7.6,
|
| 1023 |
+
"eval_accuracy": 0.9444444179534912,
|
| 1024 |
+
"eval_loss": 0.2540358901023865,
|
| 1025 |
+
"eval_runtime": 314.1415,
|
| 1026 |
+
"eval_samples_per_second": 0.974,
|
| 1027 |
+
"eval_steps_per_second": 0.245,
|
| 1028 |
+
"step": 680
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 7.71,
|
| 1032 |
+
"learning_rate": 2.2696629213483146e-05,
|
| 1033 |
+
"loss": 0.0033,
|
| 1034 |
+
"step": 690
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 7.71,
|
| 1038 |
+
"eval_accuracy": 0.9379084706306458,
|
| 1039 |
+
"eval_loss": 0.26486942172050476,
|
| 1040 |
+
"eval_runtime": 313.7641,
|
| 1041 |
+
"eval_samples_per_second": 0.975,
|
| 1042 |
+
"eval_steps_per_second": 0.245,
|
| 1043 |
+
"step": 690
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 7.82,
|
| 1047 |
+
"learning_rate": 2.157303370786517e-05,
|
| 1048 |
+
"loss": 0.0799,
|
| 1049 |
+
"step": 700
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 7.82,
|
| 1053 |
+
"eval_accuracy": 0.9346405267715454,
|
| 1054 |
+
"eval_loss": 0.2804279029369354,
|
| 1055 |
+
"eval_runtime": 305.6654,
|
| 1056 |
+
"eval_samples_per_second": 1.001,
|
| 1057 |
+
"eval_steps_per_second": 0.252,
|
| 1058 |
+
"step": 700
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 7.93,
|
| 1062 |
+
"learning_rate": 2.0449438202247194e-05,
|
| 1063 |
+
"loss": 0.0223,
|
| 1064 |
+
"step": 710
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 7.93,
|
| 1068 |
+
"eval_accuracy": 0.9346405267715454,
|
| 1069 |
+
"eval_loss": 0.2961590886116028,
|
| 1070 |
+
"eval_runtime": 33.833,
|
| 1071 |
+
"eval_samples_per_second": 9.044,
|
| 1072 |
+
"eval_steps_per_second": 2.276,
|
| 1073 |
+
"step": 710
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 8.04,
|
| 1077 |
+
"learning_rate": 1.9325842696629215e-05,
|
| 1078 |
+
"loss": 0.0065,
|
| 1079 |
+
"step": 720
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 8.04,
|
| 1083 |
+
"eval_accuracy": 0.9313725233078003,
|
| 1084 |
+
"eval_loss": 0.3002856373786926,
|
| 1085 |
+
"eval_runtime": 28.9416,
|
| 1086 |
+
"eval_samples_per_second": 10.573,
|
| 1087 |
+
"eval_steps_per_second": 2.661,
|
| 1088 |
+
"step": 720
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 8.16,
|
| 1092 |
+
"learning_rate": 1.8202247191011237e-05,
|
| 1093 |
+
"loss": 0.0032,
|
| 1094 |
+
"step": 730
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 8.16,
|
| 1098 |
+
"eval_accuracy": 0.9215686321258545,
|
| 1099 |
+
"eval_loss": 0.33132508397102356,
|
| 1100 |
+
"eval_runtime": 28.9077,
|
| 1101 |
+
"eval_samples_per_second": 10.585,
|
| 1102 |
+
"eval_steps_per_second": 2.664,
|
| 1103 |
+
"step": 730
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 8.27,
|
| 1107 |
+
"learning_rate": 1.707865168539326e-05,
|
| 1108 |
+
"loss": 0.0012,
|
| 1109 |
+
"step": 740
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 8.27,
|
| 1113 |
+
"eval_accuracy": 0.9117646813392639,
|
| 1114 |
+
"eval_loss": 0.3802509605884552,
|
| 1115 |
+
"eval_runtime": 28.4035,
|
| 1116 |
+
"eval_samples_per_second": 10.773,
|
| 1117 |
+
"eval_steps_per_second": 2.711,
|
| 1118 |
+
"step": 740
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 8.38,
|
| 1122 |
+
"learning_rate": 1.595505617977528e-05,
|
| 1123 |
+
"loss": 0.0022,
|
| 1124 |
+
"step": 750
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 8.38,
|
| 1128 |
+
"eval_accuracy": 0.9183006286621094,
|
| 1129 |
+
"eval_loss": 0.3360930383205414,
|
| 1130 |
+
"eval_runtime": 28.4227,
|
| 1131 |
+
"eval_samples_per_second": 10.766,
|
| 1132 |
+
"eval_steps_per_second": 2.709,
|
| 1133 |
+
"step": 750
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 8.49,
|
| 1137 |
+
"learning_rate": 1.4831460674157305e-05,
|
| 1138 |
+
"loss": 0.0012,
|
| 1139 |
+
"step": 760
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 8.49,
|
| 1143 |
+
"eval_accuracy": 0.9346405267715454,
|
| 1144 |
+
"eval_loss": 0.29600241780281067,
|
| 1145 |
+
"eval_runtime": 300.6077,
|
| 1146 |
+
"eval_samples_per_second": 1.018,
|
| 1147 |
+
"eval_steps_per_second": 0.256,
|
| 1148 |
+
"step": 760
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 8.6,
|
| 1152 |
+
"learning_rate": 1.3707865168539327e-05,
|
| 1153 |
+
"loss": 0.0011,
|
| 1154 |
+
"step": 770
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 8.6,
|
| 1158 |
+
"eval_accuracy": 0.9346405267715454,
|
| 1159 |
+
"eval_loss": 0.2943996489048004,
|
| 1160 |
+
"eval_runtime": 312.1252,
|
| 1161 |
+
"eval_samples_per_second": 0.98,
|
| 1162 |
+
"eval_steps_per_second": 0.247,
|
| 1163 |
+
"step": 770
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 8.72,
|
| 1167 |
+
"learning_rate": 1.258426966292135e-05,
|
| 1168 |
+
"loss": 0.0039,
|
| 1169 |
+
"step": 780
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 8.72,
|
| 1173 |
+
"eval_accuracy": 0.9346405267715454,
|
| 1174 |
+
"eval_loss": 0.29687556624412537,
|
| 1175 |
+
"eval_runtime": 310.6326,
|
| 1176 |
+
"eval_samples_per_second": 0.985,
|
| 1177 |
+
"eval_steps_per_second": 0.248,
|
| 1178 |
+
"step": 780
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 8.83,
|
| 1182 |
+
"learning_rate": 1.146067415730337e-05,
|
| 1183 |
+
"loss": 0.0011,
|
| 1184 |
+
"step": 790
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 8.83,
|
| 1188 |
+
"eval_accuracy": 0.9281045794487,
|
| 1189 |
+
"eval_loss": 0.32291698455810547,
|
| 1190 |
+
"eval_runtime": 312.3321,
|
| 1191 |
+
"eval_samples_per_second": 0.98,
|
| 1192 |
+
"eval_steps_per_second": 0.247,
|
| 1193 |
+
"step": 790
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 8.94,
|
| 1197 |
+
"learning_rate": 1.0337078651685394e-05,
|
| 1198 |
+
"loss": 0.0011,
|
| 1199 |
+
"step": 800
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 8.94,
|
| 1203 |
+
"eval_accuracy": 0.9281045794487,
|
| 1204 |
+
"eval_loss": 0.3310171067714691,
|
| 1205 |
+
"eval_runtime": 309.2689,
|
| 1206 |
+
"eval_samples_per_second": 0.989,
|
| 1207 |
+
"eval_steps_per_second": 0.249,
|
| 1208 |
+
"step": 800
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 9.05,
|
| 1212 |
+
"learning_rate": 9.213483146067416e-06,
|
| 1213 |
+
"loss": 0.0023,
|
| 1214 |
+
"step": 810
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 9.05,
|
| 1218 |
+
"eval_accuracy": 0.9346405267715454,
|
| 1219 |
+
"eval_loss": 0.3102934658527374,
|
| 1220 |
+
"eval_runtime": 308.188,
|
| 1221 |
+
"eval_samples_per_second": 0.993,
|
| 1222 |
+
"eval_steps_per_second": 0.25,
|
| 1223 |
+
"step": 810
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 9.16,
|
| 1227 |
+
"learning_rate": 8.089887640449438e-06,
|
| 1228 |
+
"loss": 0.0011,
|
| 1229 |
+
"step": 820
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 9.16,
|
| 1233 |
+
"eval_accuracy": 0.9444444179534912,
|
| 1234 |
+
"eval_loss": 0.29238083958625793,
|
| 1235 |
+
"eval_runtime": 323.8949,
|
| 1236 |
+
"eval_samples_per_second": 0.945,
|
| 1237 |
+
"eval_steps_per_second": 0.238,
|
| 1238 |
+
"step": 820
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 9.27,
|
| 1242 |
+
"learning_rate": 6.96629213483146e-06,
|
| 1243 |
+
"loss": 0.0015,
|
| 1244 |
+
"step": 830
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 9.27,
|
| 1248 |
+
"eval_accuracy": 0.9509803652763367,
|
| 1249 |
+
"eval_loss": 0.282598614692688,
|
| 1250 |
+
"eval_runtime": 298.2173,
|
| 1251 |
+
"eval_samples_per_second": 1.026,
|
| 1252 |
+
"eval_steps_per_second": 0.258,
|
| 1253 |
+
"step": 830
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 9.39,
|
| 1257 |
+
"learning_rate": 5.842696629213484e-06,
|
| 1258 |
+
"loss": 0.0015,
|
| 1259 |
+
"step": 840
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 9.39,
|
| 1263 |
+
"eval_accuracy": 0.9477124214172363,
|
| 1264 |
+
"eval_loss": 0.2785097658634186,
|
| 1265 |
+
"eval_runtime": 310.1298,
|
| 1266 |
+
"eval_samples_per_second": 0.987,
|
| 1267 |
+
"eval_steps_per_second": 0.248,
|
| 1268 |
+
"step": 840
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 9.5,
|
| 1272 |
+
"learning_rate": 4.719101123595506e-06,
|
| 1273 |
+
"loss": 0.0011,
|
| 1274 |
+
"step": 850
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 9.5,
|
| 1278 |
+
"eval_accuracy": 0.9477124214172363,
|
| 1279 |
+
"eval_loss": 0.2726196050643921,
|
| 1280 |
+
"eval_runtime": 315.4917,
|
| 1281 |
+
"eval_samples_per_second": 0.97,
|
| 1282 |
+
"eval_steps_per_second": 0.244,
|
| 1283 |
+
"step": 850
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 9.61,
|
| 1287 |
+
"learning_rate": 3.5955056179775286e-06,
|
| 1288 |
+
"loss": 0.0297,
|
| 1289 |
+
"step": 860
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 9.61,
|
| 1293 |
+
"eval_accuracy": 0.9509803652763367,
|
| 1294 |
+
"eval_loss": 0.26638907194137573,
|
| 1295 |
+
"eval_runtime": 299.8251,
|
| 1296 |
+
"eval_samples_per_second": 1.021,
|
| 1297 |
+
"eval_steps_per_second": 0.257,
|
| 1298 |
+
"step": 860
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 9.72,
|
| 1302 |
+
"learning_rate": 2.4719101123595505e-06,
|
| 1303 |
+
"loss": 0.0045,
|
| 1304 |
+
"step": 870
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 9.72,
|
| 1308 |
+
"eval_accuracy": 0.9509803652763367,
|
| 1309 |
+
"eval_loss": 0.26572802662849426,
|
| 1310 |
+
"eval_runtime": 300.0469,
|
| 1311 |
+
"eval_samples_per_second": 1.02,
|
| 1312 |
+
"eval_steps_per_second": 0.257,
|
| 1313 |
+
"step": 870
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 9.83,
|
| 1317 |
+
"learning_rate": 1.3483146067415732e-06,
|
| 1318 |
+
"loss": 0.0016,
|
| 1319 |
+
"step": 880
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 9.83,
|
| 1323 |
+
"eval_accuracy": 0.9477124214172363,
|
| 1324 |
+
"eval_loss": 0.2656039297580719,
|
| 1325 |
+
"eval_runtime": 305.8484,
|
| 1326 |
+
"eval_samples_per_second": 1.0,
|
| 1327 |
+
"eval_steps_per_second": 0.252,
|
| 1328 |
+
"step": 880
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 9.94,
|
| 1332 |
+
"learning_rate": 2.2471910112359554e-07,
|
| 1333 |
+
"loss": 0.0008,
|
| 1334 |
+
"step": 890
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 9.94,
|
| 1338 |
+
"eval_accuracy": 0.9477124214172363,
|
| 1339 |
+
"eval_loss": 0.26553988456726074,
|
| 1340 |
+
"eval_runtime": 335.2081,
|
| 1341 |
+
"eval_samples_per_second": 0.913,
|
| 1342 |
+
"eval_steps_per_second": 0.23,
|
| 1343 |
+
"step": 890
|
| 1344 |
+
}
|
| 1345 |
+
],
|
| 1346 |
+
"max_steps": 890,
|
| 1347 |
+
"num_train_epochs": 10,
|
| 1348 |
+
"total_flos": 1.51047400011648e+18,
|
| 1349 |
+
"trial_name": null,
|
| 1350 |
+
"trial_params": null
|
| 1351 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f71df8ecc6bb75ee5b159921480032d2ca70c2621fe6853ca66f21cd55230014
|
| 3 |
+
size 3963
|