Upload 9 files
Browse files- checkpoint-2000/config.json +42 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/preprocessor_config.json +0 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +532 -0
- checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Yilin98/whisper-small-hi",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": [
|
| 10 |
+
220,
|
| 11 |
+
50257
|
| 12 |
+
],
|
| 13 |
+
"bos_token_id": 50257,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 12,
|
| 22 |
+
"encoder_ffn_dim": 3072,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 12,
|
| 25 |
+
"eos_token_id": 50257,
|
| 26 |
+
"forced_decoder_ids": null,
|
| 27 |
+
"init_std": 0.02,
|
| 28 |
+
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 448,
|
| 30 |
+
"max_source_positions": 1500,
|
| 31 |
+
"max_target_positions": 448,
|
| 32 |
+
"model_type": "whisper",
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_mel_bins": 80,
|
| 35 |
+
"pad_token_id": 50257,
|
| 36 |
+
"scale_embedding": false,
|
| 37 |
+
"suppress_tokens": [],
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.26.0.dev0",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 51865
|
| 42 |
+
}
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e998281c90cb2088bf125fe7aa5522eadcf2f6d5d3f5e10bc05d840673984a
|
| 3 |
+
size 1934158597
|
checkpoint-2000/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96d8c52bb1e888af36d8d3419ba0dd8dbd65a6111c41851593a11792c92bcad5
|
| 3 |
+
size 967099139
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:294bcfdd7ca461d5ba575caf19533254d1b3470a86aa7742f9d3c2c4aa7829af
|
| 3 |
+
size 14503
|
checkpoint-2000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b2535af9f2c74a0486296353d2f4e455169f73672817e7cff5626da1ce86ecb
|
| 3 |
+
size 559
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4e9ede57b8c49b5ac602b1b63cc708cacbb42dba42d54ca83553aecd7b08da4
|
| 3 |
+
size 623
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,532 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 20.935172487967517,
|
| 3 |
+
"best_model_checkpoint": "/content/checkpoint/whisper-small-hi/checkpoint-2000",
|
| 4 |
+
"epoch": 2.5873221216041395,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.2000000000000006e-07,
|
| 13 |
+
"loss": 4.1984,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 9.200000000000001e-07,
|
| 19 |
+
"loss": 3.3699,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 1.42e-06,
|
| 25 |
+
"loss": 2.4858,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"learning_rate": 1.9200000000000003e-06,
|
| 31 |
+
"loss": 1.4969,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.16,
|
| 36 |
+
"learning_rate": 2.42e-06,
|
| 37 |
+
"loss": 1.1419,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.19,
|
| 42 |
+
"learning_rate": 2.92e-06,
|
| 43 |
+
"loss": 1.0148,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23,
|
| 48 |
+
"learning_rate": 3.4200000000000007e-06,
|
| 49 |
+
"loss": 0.9297,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.26,
|
| 54 |
+
"learning_rate": 3.920000000000001e-06,
|
| 55 |
+
"loss": 0.8621,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.29,
|
| 60 |
+
"learning_rate": 4.42e-06,
|
| 61 |
+
"loss": 0.712,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.32,
|
| 66 |
+
"learning_rate": 4.92e-06,
|
| 67 |
+
"loss": 0.6186,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.36,
|
| 72 |
+
"learning_rate": 5.420000000000001e-06,
|
| 73 |
+
"loss": 0.4717,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.39,
|
| 78 |
+
"learning_rate": 5.92e-06,
|
| 79 |
+
"loss": 0.3114,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.42,
|
| 84 |
+
"learning_rate": 6.42e-06,
|
| 85 |
+
"loss": 0.3384,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45,
|
| 90 |
+
"learning_rate": 6.92e-06,
|
| 91 |
+
"loss": 0.2962,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.49,
|
| 96 |
+
"learning_rate": 7.420000000000001e-06,
|
| 97 |
+
"loss": 0.3173,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.52,
|
| 102 |
+
"learning_rate": 7.92e-06,
|
| 103 |
+
"loss": 0.3202,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.55,
|
| 108 |
+
"learning_rate": 8.42e-06,
|
| 109 |
+
"loss": 0.3133,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.58,
|
| 114 |
+
"learning_rate": 8.920000000000001e-06,
|
| 115 |
+
"loss": 0.3045,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.61,
|
| 120 |
+
"learning_rate": 9.42e-06,
|
| 121 |
+
"loss": 0.2761,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.65,
|
| 126 |
+
"learning_rate": 9.920000000000002e-06,
|
| 127 |
+
"loss": 0.3105,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.65,
|
| 132 |
+
"eval_loss": 0.32677161693573,
|
| 133 |
+
"eval_runtime": 1909.0381,
|
| 134 |
+
"eval_samples_per_second": 2.655,
|
| 135 |
+
"eval_steps_per_second": 0.332,
|
| 136 |
+
"eval_wer": 23.903632599284773,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.68,
|
| 141 |
+
"learning_rate": 4.800000000000001e-07,
|
| 142 |
+
"loss": 0.2945,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.71,
|
| 147 |
+
"learning_rate": 9.800000000000001e-07,
|
| 148 |
+
"loss": 0.2947,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.74,
|
| 153 |
+
"learning_rate": 1.48e-06,
|
| 154 |
+
"loss": 0.2997,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.78,
|
| 159 |
+
"learning_rate": 1.98e-06,
|
| 160 |
+
"loss": 0.301,
|
| 161 |
+
"step": 600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.81,
|
| 165 |
+
"learning_rate": 2.4800000000000004e-06,
|
| 166 |
+
"loss": 0.2875,
|
| 167 |
+
"step": 625
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.84,
|
| 171 |
+
"learning_rate": 2.9800000000000003e-06,
|
| 172 |
+
"loss": 0.3012,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.87,
|
| 177 |
+
"learning_rate": 3.48e-06,
|
| 178 |
+
"loss": 0.2679,
|
| 179 |
+
"step": 675
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.91,
|
| 183 |
+
"learning_rate": 3.980000000000001e-06,
|
| 184 |
+
"loss": 0.2838,
|
| 185 |
+
"step": 700
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.94,
|
| 189 |
+
"learning_rate": 4.48e-06,
|
| 190 |
+
"loss": 0.2789,
|
| 191 |
+
"step": 725
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.97,
|
| 195 |
+
"learning_rate": 4.960000000000001e-06,
|
| 196 |
+
"loss": 0.273,
|
| 197 |
+
"step": 750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.0,
|
| 201 |
+
"learning_rate": 5.460000000000001e-06,
|
| 202 |
+
"loss": 0.2716,
|
| 203 |
+
"step": 775
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.03,
|
| 207 |
+
"learning_rate": 5.9600000000000005e-06,
|
| 208 |
+
"loss": 0.1651,
|
| 209 |
+
"step": 800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.07,
|
| 213 |
+
"learning_rate": 6.460000000000001e-06,
|
| 214 |
+
"loss": 0.1718,
|
| 215 |
+
"step": 825
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.1,
|
| 219 |
+
"learning_rate": 6.96e-06,
|
| 220 |
+
"loss": 0.1631,
|
| 221 |
+
"step": 850
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.13,
|
| 225 |
+
"learning_rate": 7.4600000000000006e-06,
|
| 226 |
+
"loss": 0.1572,
|
| 227 |
+
"step": 875
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.16,
|
| 231 |
+
"learning_rate": 7.960000000000002e-06,
|
| 232 |
+
"loss": 0.1742,
|
| 233 |
+
"step": 900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2,
|
| 237 |
+
"learning_rate": 8.46e-06,
|
| 238 |
+
"loss": 0.1899,
|
| 239 |
+
"step": 925
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.23,
|
| 243 |
+
"learning_rate": 8.96e-06,
|
| 244 |
+
"loss": 0.1787,
|
| 245 |
+
"step": 950
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.26,
|
| 249 |
+
"learning_rate": 9.460000000000001e-06,
|
| 250 |
+
"loss": 0.1836,
|
| 251 |
+
"step": 975
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.29,
|
| 255 |
+
"learning_rate": 9.960000000000001e-06,
|
| 256 |
+
"loss": 0.1775,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.29,
|
| 261 |
+
"eval_loss": 0.3070180416107178,
|
| 262 |
+
"eval_runtime": 2136.5113,
|
| 263 |
+
"eval_samples_per_second": 2.373,
|
| 264 |
+
"eval_steps_per_second": 0.297,
|
| 265 |
+
"eval_wer": 22.419402543626145,
|
| 266 |
+
"step": 1000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.33,
|
| 270 |
+
"learning_rate": 9.934285714285715e-06,
|
| 271 |
+
"loss": 0.1974,
|
| 272 |
+
"step": 1025
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.36,
|
| 276 |
+
"learning_rate": 9.862857142857144e-06,
|
| 277 |
+
"loss": 0.1784,
|
| 278 |
+
"step": 1050
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.39,
|
| 282 |
+
"learning_rate": 9.791428571428571e-06,
|
| 283 |
+
"loss": 0.1785,
|
| 284 |
+
"step": 1075
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.42,
|
| 288 |
+
"learning_rate": 9.72e-06,
|
| 289 |
+
"loss": 0.1861,
|
| 290 |
+
"step": 1100
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.46,
|
| 294 |
+
"learning_rate": 9.648571428571429e-06,
|
| 295 |
+
"loss": 0.1808,
|
| 296 |
+
"step": 1125
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.49,
|
| 300 |
+
"learning_rate": 9.577142857142858e-06,
|
| 301 |
+
"loss": 0.1741,
|
| 302 |
+
"step": 1150
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.52,
|
| 306 |
+
"learning_rate": 9.505714285714287e-06,
|
| 307 |
+
"loss": 0.184,
|
| 308 |
+
"step": 1175
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.55,
|
| 312 |
+
"learning_rate": 9.434285714285714e-06,
|
| 313 |
+
"loss": 0.1962,
|
| 314 |
+
"step": 1200
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.58,
|
| 318 |
+
"learning_rate": 9.362857142857143e-06,
|
| 319 |
+
"loss": 0.1834,
|
| 320 |
+
"step": 1225
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.62,
|
| 324 |
+
"learning_rate": 9.291428571428572e-06,
|
| 325 |
+
"loss": 0.177,
|
| 326 |
+
"step": 1250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.65,
|
| 330 |
+
"learning_rate": 9.220000000000002e-06,
|
| 331 |
+
"loss": 0.1855,
|
| 332 |
+
"step": 1275
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.68,
|
| 336 |
+
"learning_rate": 9.148571428571429e-06,
|
| 337 |
+
"loss": 0.1675,
|
| 338 |
+
"step": 1300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.71,
|
| 342 |
+
"learning_rate": 9.077142857142858e-06,
|
| 343 |
+
"loss": 0.1822,
|
| 344 |
+
"step": 1325
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.75,
|
| 348 |
+
"learning_rate": 9.005714285714287e-06,
|
| 349 |
+
"loss": 0.1666,
|
| 350 |
+
"step": 1350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.78,
|
| 354 |
+
"learning_rate": 8.934285714285716e-06,
|
| 355 |
+
"loss": 0.196,
|
| 356 |
+
"step": 1375
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.81,
|
| 360 |
+
"learning_rate": 8.862857142857143e-06,
|
| 361 |
+
"loss": 0.1843,
|
| 362 |
+
"step": 1400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.84,
|
| 366 |
+
"learning_rate": 8.791428571428572e-06,
|
| 367 |
+
"loss": 0.1698,
|
| 368 |
+
"step": 1425
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.88,
|
| 372 |
+
"learning_rate": 8.720000000000001e-06,
|
| 373 |
+
"loss": 0.161,
|
| 374 |
+
"step": 1450
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.91,
|
| 378 |
+
"learning_rate": 8.64857142857143e-06,
|
| 379 |
+
"loss": 0.1897,
|
| 380 |
+
"step": 1475
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.94,
|
| 384 |
+
"learning_rate": 8.577142857142858e-06,
|
| 385 |
+
"loss": 0.1658,
|
| 386 |
+
"step": 1500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.94,
|
| 390 |
+
"eval_loss": 0.2858450710773468,
|
| 391 |
+
"eval_runtime": 1954.9187,
|
| 392 |
+
"eval_samples_per_second": 2.593,
|
| 393 |
+
"eval_steps_per_second": 0.324,
|
| 394 |
+
"eval_wer": 21.284719421365384,
|
| 395 |
+
"step": 1500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.97,
|
| 399 |
+
"learning_rate": 8.505714285714287e-06,
|
| 400 |
+
"loss": 0.1836,
|
| 401 |
+
"step": 1525
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.01,
|
| 405 |
+
"learning_rate": 8.434285714285716e-06,
|
| 406 |
+
"loss": 0.1407,
|
| 407 |
+
"step": 1550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.04,
|
| 411 |
+
"learning_rate": 8.362857142857143e-06,
|
| 412 |
+
"loss": 0.067,
|
| 413 |
+
"step": 1575
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.07,
|
| 417 |
+
"learning_rate": 8.291428571428572e-06,
|
| 418 |
+
"loss": 0.0688,
|
| 419 |
+
"step": 1600
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.1,
|
| 423 |
+
"learning_rate": 8.220000000000001e-06,
|
| 424 |
+
"loss": 0.0763,
|
| 425 |
+
"step": 1625
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.13,
|
| 429 |
+
"learning_rate": 8.148571428571428e-06,
|
| 430 |
+
"loss": 0.0751,
|
| 431 |
+
"step": 1650
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.17,
|
| 435 |
+
"learning_rate": 8.077142857142857e-06,
|
| 436 |
+
"loss": 0.0774,
|
| 437 |
+
"step": 1675
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.2,
|
| 441 |
+
"learning_rate": 8.005714285714286e-06,
|
| 442 |
+
"loss": 0.0796,
|
| 443 |
+
"step": 1700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.23,
|
| 447 |
+
"learning_rate": 7.934285714285715e-06,
|
| 448 |
+
"loss": 0.0671,
|
| 449 |
+
"step": 1725
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.26,
|
| 453 |
+
"learning_rate": 7.862857142857143e-06,
|
| 454 |
+
"loss": 0.0655,
|
| 455 |
+
"step": 1750
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.3,
|
| 459 |
+
"learning_rate": 7.791428571428572e-06,
|
| 460 |
+
"loss": 0.0691,
|
| 461 |
+
"step": 1775
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.33,
|
| 465 |
+
"learning_rate": 7.72e-06,
|
| 466 |
+
"loss": 0.0634,
|
| 467 |
+
"step": 1800
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.36,
|
| 471 |
+
"learning_rate": 7.64857142857143e-06,
|
| 472 |
+
"loss": 0.0695,
|
| 473 |
+
"step": 1825
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.39,
|
| 477 |
+
"learning_rate": 7.577142857142857e-06,
|
| 478 |
+
"loss": 0.0704,
|
| 479 |
+
"step": 1850
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.43,
|
| 483 |
+
"learning_rate": 7.505714285714286e-06,
|
| 484 |
+
"loss": 0.0706,
|
| 485 |
+
"step": 1875
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.46,
|
| 489 |
+
"learning_rate": 7.434285714285715e-06,
|
| 490 |
+
"loss": 0.0641,
|
| 491 |
+
"step": 1900
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.49,
|
| 495 |
+
"learning_rate": 7.362857142857144e-06,
|
| 496 |
+
"loss": 0.0683,
|
| 497 |
+
"step": 1925
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.52,
|
| 501 |
+
"learning_rate": 7.291428571428571e-06,
|
| 502 |
+
"loss": 0.0605,
|
| 503 |
+
"step": 1950
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.55,
|
| 507 |
+
"learning_rate": 7.22e-06,
|
| 508 |
+
"loss": 0.0674,
|
| 509 |
+
"step": 1975
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.59,
|
| 513 |
+
"learning_rate": 7.148571428571429e-06,
|
| 514 |
+
"loss": 0.0684,
|
| 515 |
+
"step": 2000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.59,
|
| 519 |
+
"eval_loss": 0.29735004901885986,
|
| 520 |
+
"eval_runtime": 1980.7436,
|
| 521 |
+
"eval_samples_per_second": 2.559,
|
| 522 |
+
"eval_steps_per_second": 0.32,
|
| 523 |
+
"eval_wer": 20.935172487967517,
|
| 524 |
+
"step": 2000
|
| 525 |
+
}
|
| 526 |
+
],
|
| 527 |
+
"max_steps": 4000,
|
| 528 |
+
"num_train_epochs": 6,
|
| 529 |
+
"total_flos": 9.23011544383488e+18,
|
| 530 |
+
"trial_name": null,
|
| 531 |
+
"trial_params": null
|
| 532 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fe6a2fa6b1cbf943d4fb1846caee0cc939dac5235971bdda2a2bc90bf580d52
|
| 3 |
+
size 3567
|