Upload 6 files
Browse files- all_results.json +9 -0
- config.json +94 -0
- preprocessor_config.json +9 -0
- train_results.json +9 -0
- trainer_state.json +325 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.769435596456942e+16,
|
| 4 |
+
"train_loss": 0.14601652294397355,
|
| 5 |
+
"train_runtime": 502.1897,
|
| 6 |
+
"train_samples": 800,
|
| 7 |
+
"train_samples_per_second": 1.593,
|
| 8 |
+
"train_steps_per_second": 0.398
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "m3hrdadfi/hubert-base-persian-speech-emotion-recognition",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSpeechClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_dropout": 0.0,
|
| 45 |
+
"feat_extract_norm": "group",
|
| 46 |
+
"feat_proj_dropout": 0.1,
|
| 47 |
+
"feat_proj_layer_norm": true,
|
| 48 |
+
"final_dropout": 0.1,
|
| 49 |
+
"finetuning_task": "wav2vec2_clf",
|
| 50 |
+
"gradient_checkpointing": false,
|
| 51 |
+
"hidden_act": "gelu",
|
| 52 |
+
"hidden_dropout": 0.1,
|
| 53 |
+
"hidden_dropout_prob": 0.1,
|
| 54 |
+
"hidden_size": 768,
|
| 55 |
+
"id2label": {
|
| 56 |
+
"0": "angry",
|
| 57 |
+
"1": "fearful",
|
| 58 |
+
"2": "happy",
|
| 59 |
+
"3": "neutral",
|
| 60 |
+
"4": "sad",
|
| 61 |
+
"5": "surprised"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"angry": 0,
|
| 67 |
+
"fearful": 1,
|
| 68 |
+
"happy": 2,
|
| 69 |
+
"neutral": 3,
|
| 70 |
+
"sad": 4,
|
| 71 |
+
"surprised": 5
|
| 72 |
+
},
|
| 73 |
+
"layer_norm_eps": 1e-05,
|
| 74 |
+
"layerdrop": 0.1,
|
| 75 |
+
"mask_feature_length": 10,
|
| 76 |
+
"mask_feature_min_masks": 0,
|
| 77 |
+
"mask_feature_prob": 0.0,
|
| 78 |
+
"mask_time_length": 10,
|
| 79 |
+
"mask_time_min_masks": 2,
|
| 80 |
+
"mask_time_prob": 0.05,
|
| 81 |
+
"model_type": "hubert",
|
| 82 |
+
"num_attention_heads": 12,
|
| 83 |
+
"num_conv_pos_embedding_groups": 16,
|
| 84 |
+
"num_conv_pos_embeddings": 128,
|
| 85 |
+
"num_feat_extract_layers": 7,
|
| 86 |
+
"num_hidden_layers": 12,
|
| 87 |
+
"pad_token_id": 0,
|
| 88 |
+
"pooling_mode": "mean",
|
| 89 |
+
"problem_type": "single_label_classification",
|
| 90 |
+
"torch_dtype": "float32",
|
| 91 |
+
"transformers_version": "4.29.2",
|
| 92 |
+
"use_weighted_layer_sum": false,
|
| 93 |
+
"vocab_size": 32
|
| 94 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.769435596456942e+16,
|
| 4 |
+
"train_loss": 0.14601652294397355,
|
| 5 |
+
"train_runtime": 502.1897,
|
| 6 |
+
"train_samples": 800,
|
| 7 |
+
"train_samples_per_second": 1.593,
|
| 8 |
+
"train_steps_per_second": 0.398
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 9.55e-06,
|
| 13 |
+
"loss": 0.1171,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_accuracy": 0.9800000190734863,
|
| 19 |
+
"eval_loss": 0.1231689453125,
|
| 20 |
+
"eval_runtime": 25.5746,
|
| 21 |
+
"eval_samples_per_second": 7.82,
|
| 22 |
+
"eval_steps_per_second": 1.955,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1,
|
| 27 |
+
"learning_rate": 9.100000000000001e-06,
|
| 28 |
+
"loss": 0.2892,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.1,
|
| 33 |
+
"eval_accuracy": 0.9800000190734863,
|
| 34 |
+
"eval_loss": 0.1242372915148735,
|
| 35 |
+
"eval_runtime": 11.4531,
|
| 36 |
+
"eval_samples_per_second": 17.463,
|
| 37 |
+
"eval_steps_per_second": 4.366,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 8.65e-06,
|
| 43 |
+
"loss": 0.1402,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"eval_accuracy": 0.9800000190734863,
|
| 49 |
+
"eval_loss": 0.12265077233314514,
|
| 50 |
+
"eval_runtime": 11.5293,
|
| 51 |
+
"eval_samples_per_second": 17.347,
|
| 52 |
+
"eval_steps_per_second": 4.337,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.2,
|
| 57 |
+
"learning_rate": 8.15e-06,
|
| 58 |
+
"loss": 0.0031,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2,
|
| 63 |
+
"eval_accuracy": 0.9800000190734863,
|
| 64 |
+
"eval_loss": 0.11888507753610611,
|
| 65 |
+
"eval_runtime": 10.4745,
|
| 66 |
+
"eval_samples_per_second": 19.094,
|
| 67 |
+
"eval_steps_per_second": 4.774,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.25,
|
| 72 |
+
"learning_rate": 7.650000000000001e-06,
|
| 73 |
+
"loss": 0.0396,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.25,
|
| 78 |
+
"eval_accuracy": 0.9800000190734863,
|
| 79 |
+
"eval_loss": 0.114516980946064,
|
| 80 |
+
"eval_runtime": 12.1068,
|
| 81 |
+
"eval_samples_per_second": 16.52,
|
| 82 |
+
"eval_steps_per_second": 4.13,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.3,
|
| 87 |
+
"learning_rate": 7.15e-06,
|
| 88 |
+
"loss": 0.002,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.3,
|
| 93 |
+
"eval_accuracy": 0.9850000143051147,
|
| 94 |
+
"eval_loss": 0.0992085188627243,
|
| 95 |
+
"eval_runtime": 14.5419,
|
| 96 |
+
"eval_samples_per_second": 13.753,
|
| 97 |
+
"eval_steps_per_second": 3.438,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.35,
|
| 102 |
+
"learning_rate": 6.650000000000001e-06,
|
| 103 |
+
"loss": 0.0017,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.35,
|
| 108 |
+
"eval_accuracy": 0.9850000143051147,
|
| 109 |
+
"eval_loss": 0.0962493047118187,
|
| 110 |
+
"eval_runtime": 11.2088,
|
| 111 |
+
"eval_samples_per_second": 17.843,
|
| 112 |
+
"eval_steps_per_second": 4.461,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.4,
|
| 117 |
+
"learning_rate": 6.15e-06,
|
| 118 |
+
"loss": 0.2019,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.4,
|
| 123 |
+
"eval_accuracy": 0.9850000143051147,
|
| 124 |
+
"eval_loss": 0.09745711088180542,
|
| 125 |
+
"eval_runtime": 11.6004,
|
| 126 |
+
"eval_samples_per_second": 17.241,
|
| 127 |
+
"eval_steps_per_second": 4.31,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45,
|
| 132 |
+
"learning_rate": 5.65e-06,
|
| 133 |
+
"loss": 0.3375,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.45,
|
| 138 |
+
"eval_accuracy": 0.9850000143051147,
|
| 139 |
+
"eval_loss": 0.10359522700309753,
|
| 140 |
+
"eval_runtime": 11.2369,
|
| 141 |
+
"eval_samples_per_second": 17.798,
|
| 142 |
+
"eval_steps_per_second": 4.45,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5,
|
| 147 |
+
"learning_rate": 5.150000000000001e-06,
|
| 148 |
+
"loss": 0.1627,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5,
|
| 153 |
+
"eval_accuracy": 0.9850000143051147,
|
| 154 |
+
"eval_loss": 0.10511761903762817,
|
| 155 |
+
"eval_runtime": 16.5862,
|
| 156 |
+
"eval_samples_per_second": 12.058,
|
| 157 |
+
"eval_steps_per_second": 3.015,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.55,
|
| 162 |
+
"learning_rate": 4.65e-06,
|
| 163 |
+
"loss": 0.0135,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.55,
|
| 168 |
+
"eval_accuracy": 0.9800000190734863,
|
| 169 |
+
"eval_loss": 0.10832720994949341,
|
| 170 |
+
"eval_runtime": 12.361,
|
| 171 |
+
"eval_samples_per_second": 16.18,
|
| 172 |
+
"eval_steps_per_second": 4.045,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.6,
|
| 177 |
+
"learning_rate": 4.15e-06,
|
| 178 |
+
"loss": 0.3365,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.6,
|
| 183 |
+
"eval_accuracy": 0.9800000190734863,
|
| 184 |
+
"eval_loss": 0.10196716338396072,
|
| 185 |
+
"eval_runtime": 11.3569,
|
| 186 |
+
"eval_samples_per_second": 17.61,
|
| 187 |
+
"eval_steps_per_second": 4.403,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.65,
|
| 192 |
+
"learning_rate": 3.65e-06,
|
| 193 |
+
"loss": 0.0401,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.65,
|
| 198 |
+
"eval_accuracy": 0.9850000143051147,
|
| 199 |
+
"eval_loss": 0.0968363955616951,
|
| 200 |
+
"eval_runtime": 11.6857,
|
| 201 |
+
"eval_samples_per_second": 17.115,
|
| 202 |
+
"eval_steps_per_second": 4.279,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.7,
|
| 207 |
+
"learning_rate": 3.1500000000000003e-06,
|
| 208 |
+
"loss": 0.5678,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.7,
|
| 213 |
+
"eval_accuracy": 0.9850000143051147,
|
| 214 |
+
"eval_loss": 0.09780912101268768,
|
| 215 |
+
"eval_runtime": 11.6042,
|
| 216 |
+
"eval_samples_per_second": 17.235,
|
| 217 |
+
"eval_steps_per_second": 4.309,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.75,
|
| 222 |
+
"learning_rate": 2.6500000000000005e-06,
|
| 223 |
+
"loss": 0.2519,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.75,
|
| 228 |
+
"eval_accuracy": 0.9800000190734863,
|
| 229 |
+
"eval_loss": 0.10378458350896835,
|
| 230 |
+
"eval_runtime": 11.6217,
|
| 231 |
+
"eval_samples_per_second": 17.209,
|
| 232 |
+
"eval_steps_per_second": 4.302,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8,
|
| 237 |
+
"learning_rate": 2.15e-06,
|
| 238 |
+
"loss": 0.0373,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.8,
|
| 243 |
+
"eval_accuracy": 0.9800000190734863,
|
| 244 |
+
"eval_loss": 0.11212433129549026,
|
| 245 |
+
"eval_runtime": 11.5639,
|
| 246 |
+
"eval_samples_per_second": 17.295,
|
| 247 |
+
"eval_steps_per_second": 4.324,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.85,
|
| 252 |
+
"learning_rate": 1.6500000000000003e-06,
|
| 253 |
+
"loss": 0.2023,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.85,
|
| 258 |
+
"eval_accuracy": 0.9800000190734863,
|
| 259 |
+
"eval_loss": 0.1162676215171814,
|
| 260 |
+
"eval_runtime": 10.3566,
|
| 261 |
+
"eval_samples_per_second": 19.311,
|
| 262 |
+
"eval_steps_per_second": 4.828,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.9,
|
| 267 |
+
"learning_rate": 1.1500000000000002e-06,
|
| 268 |
+
"loss": 0.0061,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.9,
|
| 273 |
+
"eval_accuracy": 0.9800000190734863,
|
| 274 |
+
"eval_loss": 0.11709693819284439,
|
| 275 |
+
"eval_runtime": 10.4736,
|
| 276 |
+
"eval_samples_per_second": 19.096,
|
| 277 |
+
"eval_steps_per_second": 4.774,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.95,
|
| 282 |
+
"learning_rate": 6.5e-07,
|
| 283 |
+
"loss": 0.0844,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.95,
|
| 288 |
+
"eval_accuracy": 0.9800000190734863,
|
| 289 |
+
"eval_loss": 0.115566685795784,
|
| 290 |
+
"eval_runtime": 11.1708,
|
| 291 |
+
"eval_samples_per_second": 17.904,
|
| 292 |
+
"eval_steps_per_second": 4.476,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.0,
|
| 297 |
+
"learning_rate": 1.5000000000000002e-07,
|
| 298 |
+
"loss": 0.0854,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.0,
|
| 303 |
+
"eval_accuracy": 0.9800000190734863,
|
| 304 |
+
"eval_loss": 0.1153903380036354,
|
| 305 |
+
"eval_runtime": 11.4553,
|
| 306 |
+
"eval_samples_per_second": 17.459,
|
| 307 |
+
"eval_steps_per_second": 4.365,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.0,
|
| 312 |
+
"step": 200,
|
| 313 |
+
"total_flos": 5.769435596456942e+16,
|
| 314 |
+
"train_loss": 0.14601652294397355,
|
| 315 |
+
"train_runtime": 502.1897,
|
| 316 |
+
"train_samples_per_second": 1.593,
|
| 317 |
+
"train_steps_per_second": 0.398
|
| 318 |
+
}
|
| 319 |
+
],
|
| 320 |
+
"max_steps": 200,
|
| 321 |
+
"num_train_epochs": 1,
|
| 322 |
+
"total_flos": 5.769435596456942e+16,
|
| 323 |
+
"trial_name": null,
|
| 324 |
+
"trial_params": null
|
| 325 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f98a815af6756007f49aaac7fd445a84022514155186c9412cdd5d3fa0f25362
|
| 3 |
+
size 3963
|