Commit
·
e30a64c
1
Parent(s):
ed4205a
Done last 3:42
Browse files- .ipynb_checkpoints/config-checkpoint.json +0 -131
- .ipynb_checkpoints/preprocessor_config-checkpoint.json +0 -10
- .ipynb_checkpoints/trainer_state-checkpoint.json +0 -121
- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +309 -54
- training_args.bin +1 -1
.ipynb_checkpoints/config-checkpoint.json
DELETED
|
@@ -1,131 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "jonatasgrosman/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": "fearful",
|
| 62 |
-
"2": "happy",
|
| 63 |
-
"3": "neutral"
|
| 64 |
-
},
|
| 65 |
-
"initializer_range": 0.02,
|
| 66 |
-
"intermediate_size": 4096,
|
| 67 |
-
"label2id": {
|
| 68 |
-
"angry": 0,
|
| 69 |
-
"fearful": 1,
|
| 70 |
-
"happy": 2,
|
| 71 |
-
"neutral": 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 |
-
"push_to_hub": true,
|
| 105 |
-
"tdnn_dilation": [
|
| 106 |
-
1,
|
| 107 |
-
2,
|
| 108 |
-
3,
|
| 109 |
-
1,
|
| 110 |
-
1
|
| 111 |
-
],
|
| 112 |
-
"tdnn_dim": [
|
| 113 |
-
512,
|
| 114 |
-
512,
|
| 115 |
-
512,
|
| 116 |
-
512,
|
| 117 |
-
1500
|
| 118 |
-
],
|
| 119 |
-
"tdnn_kernel": [
|
| 120 |
-
5,
|
| 121 |
-
3,
|
| 122 |
-
3,
|
| 123 |
-
1,
|
| 124 |
-
1
|
| 125 |
-
],
|
| 126 |
-
"torch_dtype": "float32",
|
| 127 |
-
"transformers_version": "4.23.0.dev0",
|
| 128 |
-
"use_weighted_layer_sum": false,
|
| 129 |
-
"vocab_size": 33,
|
| 130 |
-
"xvector_output_dim": 512
|
| 131 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/preprocessor_config-checkpoint.json
DELETED
|
@@ -1,10 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.ipynb_checkpoints/trainer_state-checkpoint.json
DELETED
|
@@ -1,121 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.9166666666666665,
|
| 5 |
-
"global_step": 70,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.42,
|
| 12 |
-
"learning_rate": 8.611111111111112e-05,
|
| 13 |
-
"loss": 1.4322,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.42,
|
| 18 |
-
"eval_accuracy": 0.3125,
|
| 19 |
-
"eval_loss": 1.3030599355697632,
|
| 20 |
-
"eval_runtime": 9.8316,
|
| 21 |
-
"eval_samples_per_second": 4.882,
|
| 22 |
-
"eval_steps_per_second": 1.221,
|
| 23 |
-
"step": 10
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.83,
|
| 27 |
-
"learning_rate": 7.222222222222222e-05,
|
| 28 |
-
"loss": 1.2975,
|
| 29 |
-
"step": 20
|
| 30 |
-
},
|
| 31 |
-
{
|
| 32 |
-
"epoch": 0.83,
|
| 33 |
-
"eval_accuracy": 0.3541666567325592,
|
| 34 |
-
"eval_loss": 1.2456461191177368,
|
| 35 |
-
"eval_runtime": 12.762,
|
| 36 |
-
"eval_samples_per_second": 3.761,
|
| 37 |
-
"eval_steps_per_second": 0.94,
|
| 38 |
-
"step": 20
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 1.25,
|
| 42 |
-
"learning_rate": 5.833333333333334e-05,
|
| 43 |
-
"loss": 1.3053,
|
| 44 |
-
"step": 30
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 1.25,
|
| 48 |
-
"eval_accuracy": 0.375,
|
| 49 |
-
"eval_loss": 1.235076904296875,
|
| 50 |
-
"eval_runtime": 9.8907,
|
| 51 |
-
"eval_samples_per_second": 4.853,
|
| 52 |
-
"eval_steps_per_second": 1.213,
|
| 53 |
-
"step": 30
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"epoch": 1.67,
|
| 57 |
-
"learning_rate": 4.4444444444444447e-05,
|
| 58 |
-
"loss": 1.2042,
|
| 59 |
-
"step": 40
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 1.67,
|
| 63 |
-
"eval_accuracy": 0.375,
|
| 64 |
-
"eval_loss": 1.1900380849838257,
|
| 65 |
-
"eval_runtime": 12.1455,
|
| 66 |
-
"eval_samples_per_second": 3.952,
|
| 67 |
-
"eval_steps_per_second": 0.988,
|
| 68 |
-
"step": 40
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 2.08,
|
| 72 |
-
"learning_rate": 3.055555555555556e-05,
|
| 73 |
-
"loss": 1.0192,
|
| 74 |
-
"step": 50
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 2.08,
|
| 78 |
-
"eval_accuracy": 0.5416666865348816,
|
| 79 |
-
"eval_loss": 1.006090760231018,
|
| 80 |
-
"eval_runtime": 9.9246,
|
| 81 |
-
"eval_samples_per_second": 4.836,
|
| 82 |
-
"eval_steps_per_second": 1.209,
|
| 83 |
-
"step": 50
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 2.5,
|
| 87 |
-
"learning_rate": 1.6666666666666667e-05,
|
| 88 |
-
"loss": 0.8874,
|
| 89 |
-
"step": 60
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 2.5,
|
| 93 |
-
"eval_accuracy": 0.625,
|
| 94 |
-
"eval_loss": 0.8699900507926941,
|
| 95 |
-
"eval_runtime": 11.1183,
|
| 96 |
-
"eval_samples_per_second": 4.317,
|
| 97 |
-
"eval_steps_per_second": 1.079,
|
| 98 |
-
"step": 60
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 2.92,
|
| 102 |
-
"learning_rate": 2.777777777777778e-06,
|
| 103 |
-
"loss": 0.855,
|
| 104 |
-
"step": 70
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 2.92,
|
| 108 |
-
"eval_accuracy": 0.5833333134651184,
|
| 109 |
-
"eval_loss": 0.9461669921875,
|
| 110 |
-
"eval_runtime": 9.9807,
|
| 111 |
-
"eval_samples_per_second": 4.809,
|
| 112 |
-
"eval_steps_per_second": 1.202,
|
| 113 |
-
"step": 70
|
| 114 |
-
}
|
| 115 |
-
],
|
| 116 |
-
"max_steps": 72,
|
| 117 |
-
"num_train_epochs": 3,
|
| 118 |
-
"total_flos": 2.022508856471088e+17,
|
| 119 |
-
"trial_name": null,
|
| 120 |
-
"trial_params": null
|
| 121 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:175aca2d22d4e0ffe707aa0203de63cde30621cf49a4e7a9ded1eabcd757b3ae
|
| 3 |
+
size 2498489737
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1266114157
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5eb5fcea715082561dc34412edd0b99d2474089f52a1ff834f8183f80b52062
|
| 3 |
size 1266114157
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e9db4f8fb9adcedf9b8f43bc1c1355687d2a0381ee8c01e6f555f0a82cb5dc
|
| 3 |
size 14503
|
scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fccda41cf05d0c2582a5ae864ddced240b945973cac170056ad38621f56c053
|
| 3 |
size 559
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f178de8fd426d107cb3181bc3de3565897ca73a1fcc762375a87651bd94651ae
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,121 +1,376 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.42,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 1.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.42,
|
| 18 |
-
"eval_accuracy": 0.
|
| 19 |
-
"eval_loss":
|
| 20 |
-
"eval_runtime":
|
| 21 |
-
"eval_samples_per_second": 4.
|
| 22 |
-
"eval_steps_per_second": 1.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.83,
|
| 27 |
-
"learning_rate": 7.
|
| 28 |
-
"loss":
|
| 29 |
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 0.83,
|
| 33 |
-
"eval_accuracy": 0.
|
| 34 |
-
"eval_loss":
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second":
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 1.25,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.25,
|
| 48 |
-
"eval_accuracy": 0.
|
| 49 |
-
"eval_loss":
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second": 4.
|
| 52 |
-
"eval_steps_per_second": 1.
|
| 53 |
"step": 30
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 1.67,
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss":
|
| 59 |
"step": 40
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 1.67,
|
| 63 |
-
"eval_accuracy": 0.
|
| 64 |
-
"eval_loss": 1.
|
| 65 |
-
"eval_runtime":
|
| 66 |
-
"eval_samples_per_second":
|
| 67 |
-
"eval_steps_per_second":
|
| 68 |
"step": 40
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 2.08,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss":
|
| 74 |
"step": 50
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 2.08,
|
| 78 |
-
"eval_accuracy": 0.
|
| 79 |
-
"eval_loss":
|
| 80 |
-
"eval_runtime":
|
| 81 |
-
"eval_samples_per_second": 4.
|
| 82 |
-
"eval_steps_per_second": 1.
|
| 83 |
"step": 50
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 2.5,
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 60
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 2.5,
|
| 93 |
-
"eval_accuracy": 0.
|
| 94 |
-
"eval_loss": 0.
|
| 95 |
-
"eval_runtime": 11.
|
| 96 |
-
"eval_samples_per_second": 4.
|
| 97 |
-
"eval_steps_per_second": 1.
|
| 98 |
"step": 60
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 2.92,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 70
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.92,
|
| 108 |
-
"eval_accuracy": 0.
|
| 109 |
-
"eval_loss": 0.
|
| 110 |
-
"eval_runtime":
|
| 111 |
-
"eval_samples_per_second": 4.
|
| 112 |
-
"eval_steps_per_second": 1.
|
| 113 |
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 114 |
}
|
| 115 |
],
|
| 116 |
-
"max_steps":
|
| 117 |
-
"num_train_epochs":
|
| 118 |
-
"total_flos":
|
| 119 |
"trial_name": null,
|
| 120 |
"trial_params": null
|
| 121 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 240,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.42,
|
| 12 |
+
"learning_rate": 7.500000000000001e-05,
|
| 13 |
+
"loss": 1.2218,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.42,
|
| 18 |
+
"eval_accuracy": 0.6041666865348816,
|
| 19 |
+
"eval_loss": 0.9863560795783997,
|
| 20 |
+
"eval_runtime": 10.1253,
|
| 21 |
+
"eval_samples_per_second": 4.741,
|
| 22 |
+
"eval_steps_per_second": 1.185,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.83,
|
| 27 |
+
"learning_rate": 7.083333333333334e-05,
|
| 28 |
+
"loss": 0.9652,
|
| 29 |
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 0.83,
|
| 33 |
+
"eval_accuracy": 0.5833333134651184,
|
| 34 |
+
"eval_loss": 0.8854789733886719,
|
| 35 |
+
"eval_runtime": 11.1802,
|
| 36 |
+
"eval_samples_per_second": 4.293,
|
| 37 |
+
"eval_steps_per_second": 1.073,
|
| 38 |
"step": 20
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 1.25,
|
| 42 |
+
"learning_rate": 6.666666666666667e-05,
|
| 43 |
+
"loss": 0.9764,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.25,
|
| 48 |
+
"eval_accuracy": 0.6666666865348816,
|
| 49 |
+
"eval_loss": 0.8104388117790222,
|
| 50 |
+
"eval_runtime": 10.0746,
|
| 51 |
+
"eval_samples_per_second": 4.764,
|
| 52 |
+
"eval_steps_per_second": 1.191,
|
| 53 |
"step": 30
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 1.67,
|
| 57 |
+
"learning_rate": 6.25e-05,
|
| 58 |
+
"loss": 0.5574,
|
| 59 |
"step": 40
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 1.67,
|
| 63 |
+
"eval_accuracy": 0.625,
|
| 64 |
+
"eval_loss": 1.0489534139633179,
|
| 65 |
+
"eval_runtime": 11.7457,
|
| 66 |
+
"eval_samples_per_second": 4.087,
|
| 67 |
+
"eval_steps_per_second": 1.022,
|
| 68 |
"step": 40
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 2.08,
|
| 72 |
+
"learning_rate": 5.833333333333334e-05,
|
| 73 |
+
"loss": 0.778,
|
| 74 |
"step": 50
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 2.08,
|
| 78 |
+
"eval_accuracy": 0.6458333134651184,
|
| 79 |
+
"eval_loss": 0.8387454152107239,
|
| 80 |
+
"eval_runtime": 10.2158,
|
| 81 |
+
"eval_samples_per_second": 4.699,
|
| 82 |
+
"eval_steps_per_second": 1.175,
|
| 83 |
"step": 50
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 2.5,
|
| 87 |
+
"learning_rate": 5.4166666666666664e-05,
|
| 88 |
+
"loss": 0.4129,
|
| 89 |
"step": 60
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 2.5,
|
| 93 |
+
"eval_accuracy": 0.7083333134651184,
|
| 94 |
+
"eval_loss": 0.7567564845085144,
|
| 95 |
+
"eval_runtime": 11.1124,
|
| 96 |
+
"eval_samples_per_second": 4.319,
|
| 97 |
+
"eval_steps_per_second": 1.08,
|
| 98 |
"step": 60
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 2.92,
|
| 102 |
+
"learning_rate": 5e-05,
|
| 103 |
+
"loss": 0.4054,
|
| 104 |
"step": 70
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.92,
|
| 108 |
+
"eval_accuracy": 0.75,
|
| 109 |
+
"eval_loss": 0.7560882568359375,
|
| 110 |
+
"eval_runtime": 10.3666,
|
| 111 |
+
"eval_samples_per_second": 4.63,
|
| 112 |
+
"eval_steps_per_second": 1.158,
|
| 113 |
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.33,
|
| 117 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 118 |
+
"loss": 0.3773,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.33,
|
| 123 |
+
"eval_accuracy": 0.8125,
|
| 124 |
+
"eval_loss": 0.6256787180900574,
|
| 125 |
+
"eval_runtime": 11.7432,
|
| 126 |
+
"eval_samples_per_second": 4.087,
|
| 127 |
+
"eval_steps_per_second": 1.022,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.75,
|
| 132 |
+
"learning_rate": 4.166666666666667e-05,
|
| 133 |
+
"loss": 0.1139,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.75,
|
| 138 |
+
"eval_accuracy": 0.875,
|
| 139 |
+
"eval_loss": 0.44811201095581055,
|
| 140 |
+
"eval_runtime": 10.2271,
|
| 141 |
+
"eval_samples_per_second": 4.693,
|
| 142 |
+
"eval_steps_per_second": 1.173,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.17,
|
| 147 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 148 |
+
"loss": 0.1395,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.17,
|
| 153 |
+
"eval_accuracy": 0.7708333134651184,
|
| 154 |
+
"eval_loss": 0.7507086396217346,
|
| 155 |
+
"eval_runtime": 11.1455,
|
| 156 |
+
"eval_samples_per_second": 4.307,
|
| 157 |
+
"eval_steps_per_second": 1.077,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.58,
|
| 162 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 163 |
+
"loss": 0.0564,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.58,
|
| 168 |
+
"eval_accuracy": 0.7916666865348816,
|
| 169 |
+
"eval_loss": 0.7551252841949463,
|
| 170 |
+
"eval_runtime": 10.0567,
|
| 171 |
+
"eval_samples_per_second": 4.773,
|
| 172 |
+
"eval_steps_per_second": 1.193,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 5.0,
|
| 177 |
+
"learning_rate": 2.916666666666667e-05,
|
| 178 |
+
"loss": 0.0767,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 5.0,
|
| 183 |
+
"eval_accuracy": 0.7916666865348816,
|
| 184 |
+
"eval_loss": 0.7378367781639099,
|
| 185 |
+
"eval_runtime": 11.5811,
|
| 186 |
+
"eval_samples_per_second": 4.145,
|
| 187 |
+
"eval_steps_per_second": 1.036,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.42,
|
| 192 |
+
"learning_rate": 2.5e-05,
|
| 193 |
+
"loss": 0.0464,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.42,
|
| 198 |
+
"eval_accuracy": 0.7291666865348816,
|
| 199 |
+
"eval_loss": 1.1143478155136108,
|
| 200 |
+
"eval_runtime": 10.0199,
|
| 201 |
+
"eval_samples_per_second": 4.79,
|
| 202 |
+
"eval_steps_per_second": 1.198,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.83,
|
| 207 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 208 |
+
"loss": 0.0996,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.83,
|
| 213 |
+
"eval_accuracy": 0.8333333134651184,
|
| 214 |
+
"eval_loss": 0.6909031867980957,
|
| 215 |
+
"eval_runtime": 11.7023,
|
| 216 |
+
"eval_samples_per_second": 4.102,
|
| 217 |
+
"eval_steps_per_second": 1.025,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.25,
|
| 222 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 223 |
+
"loss": 0.0166,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.25,
|
| 228 |
+
"eval_accuracy": 0.8333333134651184,
|
| 229 |
+
"eval_loss": 0.6695077419281006,
|
| 230 |
+
"eval_runtime": 9.8609,
|
| 231 |
+
"eval_samples_per_second": 4.868,
|
| 232 |
+
"eval_steps_per_second": 1.217,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.67,
|
| 237 |
+
"learning_rate": 1.25e-05,
|
| 238 |
+
"loss": 0.0547,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.67,
|
| 243 |
+
"eval_accuracy": 0.75,
|
| 244 |
+
"eval_loss": 0.9423481822013855,
|
| 245 |
+
"eval_runtime": 11.5884,
|
| 246 |
+
"eval_samples_per_second": 4.142,
|
| 247 |
+
"eval_steps_per_second": 1.036,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.08,
|
| 252 |
+
"learning_rate": 8.333333333333334e-06,
|
| 253 |
+
"loss": 0.1214,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.08,
|
| 258 |
+
"eval_accuracy": 0.7916666865348816,
|
| 259 |
+
"eval_loss": 0.7280401587486267,
|
| 260 |
+
"eval_runtime": 10.0684,
|
| 261 |
+
"eval_samples_per_second": 4.767,
|
| 262 |
+
"eval_steps_per_second": 1.192,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 7.5,
|
| 267 |
+
"learning_rate": 4.166666666666667e-06,
|
| 268 |
+
"loss": 0.0096,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.5,
|
| 273 |
+
"eval_accuracy": 0.7916666865348816,
|
| 274 |
+
"eval_loss": 0.6912185549736023,
|
| 275 |
+
"eval_runtime": 11.3942,
|
| 276 |
+
"eval_samples_per_second": 4.213,
|
| 277 |
+
"eval_steps_per_second": 1.053,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 7.92,
|
| 282 |
+
"learning_rate": 0.0,
|
| 283 |
+
"loss": 0.0611,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 7.92,
|
| 288 |
+
"eval_accuracy": 0.7916666865348816,
|
| 289 |
+
"eval_loss": 0.6880165934562683,
|
| 290 |
+
"eval_runtime": 10.0683,
|
| 291 |
+
"eval_samples_per_second": 4.767,
|
| 292 |
+
"eval_steps_per_second": 1.192,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 8.33,
|
| 297 |
+
"learning_rate": 0.0,
|
| 298 |
+
"loss": 0.0254,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 8.33,
|
| 303 |
+
"eval_accuracy": 0.7916666865348816,
|
| 304 |
+
"eval_loss": 0.6880165934562683,
|
| 305 |
+
"eval_runtime": 12.1412,
|
| 306 |
+
"eval_samples_per_second": 3.953,
|
| 307 |
+
"eval_steps_per_second": 0.988,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.75,
|
| 312 |
+
"learning_rate": 0.0,
|
| 313 |
+
"loss": 0.0073,
|
| 314 |
+
"step": 210
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 8.75,
|
| 318 |
+
"eval_accuracy": 0.7916666865348816,
|
| 319 |
+
"eval_loss": 0.6880165934562683,
|
| 320 |
+
"eval_runtime": 9.9345,
|
| 321 |
+
"eval_samples_per_second": 4.832,
|
| 322 |
+
"eval_steps_per_second": 1.208,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 9.17,
|
| 327 |
+
"learning_rate": 0.0,
|
| 328 |
+
"loss": 0.0153,
|
| 329 |
+
"step": 220
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 9.17,
|
| 333 |
+
"eval_accuracy": 0.7916666865348816,
|
| 334 |
+
"eval_loss": 0.6880165934562683,
|
| 335 |
+
"eval_runtime": 10.0673,
|
| 336 |
+
"eval_samples_per_second": 4.768,
|
| 337 |
+
"eval_steps_per_second": 1.192,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.58,
|
| 342 |
+
"learning_rate": 0.0,
|
| 343 |
+
"loss": 0.0093,
|
| 344 |
+
"step": 230
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 9.58,
|
| 348 |
+
"eval_accuracy": 0.7916666865348816,
|
| 349 |
+
"eval_loss": 0.6880165934562683,
|
| 350 |
+
"eval_runtime": 9.9352,
|
| 351 |
+
"eval_samples_per_second": 4.831,
|
| 352 |
+
"eval_steps_per_second": 1.208,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 10.0,
|
| 357 |
+
"learning_rate": 0.0,
|
| 358 |
+
"loss": 0.0575,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 10.0,
|
| 363 |
+
"eval_accuracy": 0.7916666865348816,
|
| 364 |
+
"eval_loss": 0.6880165934562683,
|
| 365 |
+
"eval_runtime": 10.1458,
|
| 366 |
+
"eval_samples_per_second": 4.731,
|
| 367 |
+
"eval_steps_per_second": 1.183,
|
| 368 |
+
"step": 240
|
| 369 |
}
|
| 370 |
],
|
| 371 |
+
"max_steps": 240,
|
| 372 |
+
"num_train_epochs": 10,
|
| 373 |
+
"total_flos": 6.925070959567395e+17,
|
| 374 |
"trial_name": null,
|
| 375 |
"trial_params": null
|
| 376 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b12271e563c64702e42089024d71119a9e970eda69d0d4cc86be8336fccf95f6
|
| 3 |
size 3439
|