Commit
·
bfbd37a
1
Parent(s):
d28405e
Upload with huggingface_hub
Browse files- config.json +42 -0
- generation_config.json +110 -0
- optimizer.pt +3 -0
- preprocessor_config.json +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +292 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-large-v2",
|
| 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": 1280,
|
| 15 |
+
"decoder_attention_heads": 20,
|
| 16 |
+
"decoder_ffn_dim": 5120,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 32,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 20,
|
| 22 |
+
"encoder_ffn_dim": 5120,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 32,
|
| 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": 32,
|
| 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",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 51865
|
| 42 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"begin_suppress_tokens": [
|
| 3 |
+
220,
|
| 4 |
+
50257
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 50257,
|
| 7 |
+
"decoder_start_token_id": 50258,
|
| 8 |
+
"eos_token_id": 50257,
|
| 9 |
+
"forced_decoder_ids": [
|
| 10 |
+
[
|
| 11 |
+
1,
|
| 12 |
+
null
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
2,
|
| 16 |
+
50359
|
| 17 |
+
]
|
| 18 |
+
],
|
| 19 |
+
"max_length": 448,
|
| 20 |
+
"pad_token_id": 50257,
|
| 21 |
+
"suppress_tokens": [
|
| 22 |
+
1,
|
| 23 |
+
2,
|
| 24 |
+
7,
|
| 25 |
+
8,
|
| 26 |
+
9,
|
| 27 |
+
10,
|
| 28 |
+
14,
|
| 29 |
+
25,
|
| 30 |
+
26,
|
| 31 |
+
27,
|
| 32 |
+
28,
|
| 33 |
+
29,
|
| 34 |
+
31,
|
| 35 |
+
58,
|
| 36 |
+
59,
|
| 37 |
+
60,
|
| 38 |
+
61,
|
| 39 |
+
62,
|
| 40 |
+
63,
|
| 41 |
+
90,
|
| 42 |
+
91,
|
| 43 |
+
92,
|
| 44 |
+
93,
|
| 45 |
+
359,
|
| 46 |
+
503,
|
| 47 |
+
522,
|
| 48 |
+
542,
|
| 49 |
+
873,
|
| 50 |
+
893,
|
| 51 |
+
902,
|
| 52 |
+
918,
|
| 53 |
+
922,
|
| 54 |
+
931,
|
| 55 |
+
1350,
|
| 56 |
+
1853,
|
| 57 |
+
1982,
|
| 58 |
+
2460,
|
| 59 |
+
2627,
|
| 60 |
+
3246,
|
| 61 |
+
3253,
|
| 62 |
+
3268,
|
| 63 |
+
3536,
|
| 64 |
+
3846,
|
| 65 |
+
3961,
|
| 66 |
+
4183,
|
| 67 |
+
4667,
|
| 68 |
+
6585,
|
| 69 |
+
6647,
|
| 70 |
+
7273,
|
| 71 |
+
9061,
|
| 72 |
+
9383,
|
| 73 |
+
10428,
|
| 74 |
+
10929,
|
| 75 |
+
11938,
|
| 76 |
+
12033,
|
| 77 |
+
12331,
|
| 78 |
+
12562,
|
| 79 |
+
13793,
|
| 80 |
+
14157,
|
| 81 |
+
14635,
|
| 82 |
+
15265,
|
| 83 |
+
15618,
|
| 84 |
+
16553,
|
| 85 |
+
16604,
|
| 86 |
+
18362,
|
| 87 |
+
18956,
|
| 88 |
+
20075,
|
| 89 |
+
21675,
|
| 90 |
+
22520,
|
| 91 |
+
26130,
|
| 92 |
+
26161,
|
| 93 |
+
26435,
|
| 94 |
+
28279,
|
| 95 |
+
29464,
|
| 96 |
+
31650,
|
| 97 |
+
32302,
|
| 98 |
+
32470,
|
| 99 |
+
36865,
|
| 100 |
+
42863,
|
| 101 |
+
47425,
|
| 102 |
+
49870,
|
| 103 |
+
50254,
|
| 104 |
+
50258,
|
| 105 |
+
50360,
|
| 106 |
+
50361,
|
| 107 |
+
50362
|
| 108 |
+
],
|
| 109 |
+
"transformers_version": "4.26.0"
|
| 110 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2624b978b63e333746695aeaba2215d84f3ae2c78a2d09acef9dc4918144d06
|
| 3 |
+
size 12347192855
|
preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c292a6c8a245d2f642972ffa2f990f68fe1ae45065ad5f49f4aa6095cb1f39cc
|
| 3 |
+
size 6173655480
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4945e0121f845df89f2b0db9831e9e7d064ef5da2bb53d3a1314db926b9f3902
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:998d4eacdbef91608d198f105a089c75ab1afe20a76754d937a6d94a961d56ae
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:755ca42b61149b7620b23e35201f706865dde7e8bb4e79019f726f13eddf8278
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 27.0875,
|
| 3 |
+
"best_model_checkpoint": "./whisper-large-v2-with-google-fleurs-ar/checkpoint-750",
|
| 4 |
+
"epoch": 3.802281368821293,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 13 |
+
"loss": 1.2614,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.19,
|
| 18 |
+
"learning_rate": 9.000000000000001e-07,
|
| 19 |
+
"loss": 0.8943,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.29,
|
| 24 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 25 |
+
"loss": 0.5812,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.38,
|
| 30 |
+
"learning_rate": 1.8800000000000002e-06,
|
| 31 |
+
"loss": 0.4916,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.48,
|
| 36 |
+
"learning_rate": 2.38e-06,
|
| 37 |
+
"loss": 0.4206,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.57,
|
| 42 |
+
"learning_rate": 2.86e-06,
|
| 43 |
+
"loss": 0.3381,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.67,
|
| 48 |
+
"learning_rate": 3.3600000000000004e-06,
|
| 49 |
+
"loss": 0.2693,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.76,
|
| 54 |
+
"learning_rate": 3.86e-06,
|
| 55 |
+
"loss": 0.2596,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.86,
|
| 60 |
+
"learning_rate": 4.360000000000001e-06,
|
| 61 |
+
"loss": 0.2374,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.95,
|
| 66 |
+
"learning_rate": 4.86e-06,
|
| 67 |
+
"loss": 0.258,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.95,
|
| 72 |
+
"eval_loss": 0.22044143080711365,
|
| 73 |
+
"eval_runtime": 377.2375,
|
| 74 |
+
"eval_samples_per_second": 1.135,
|
| 75 |
+
"eval_steps_per_second": 0.143,
|
| 76 |
+
"eval_wer": 49.675000000000004,
|
| 77 |
+
"step": 250
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.05,
|
| 81 |
+
"learning_rate": 5.36e-06,
|
| 82 |
+
"loss": 0.2108,
|
| 83 |
+
"step": 275
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.14,
|
| 87 |
+
"learning_rate": 5.86e-06,
|
| 88 |
+
"loss": 0.1385,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.24,
|
| 93 |
+
"learning_rate": 6.360000000000001e-06,
|
| 94 |
+
"loss": 0.1565,
|
| 95 |
+
"step": 325
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.33,
|
| 99 |
+
"learning_rate": 6.860000000000001e-06,
|
| 100 |
+
"loss": 0.1777,
|
| 101 |
+
"step": 350
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.43,
|
| 105 |
+
"learning_rate": 7.360000000000001e-06,
|
| 106 |
+
"loss": 0.1401,
|
| 107 |
+
"step": 375
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.52,
|
| 111 |
+
"learning_rate": 7.860000000000001e-06,
|
| 112 |
+
"loss": 0.1584,
|
| 113 |
+
"step": 400
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.62,
|
| 117 |
+
"learning_rate": 8.36e-06,
|
| 118 |
+
"loss": 0.1569,
|
| 119 |
+
"step": 425
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.71,
|
| 123 |
+
"learning_rate": 8.860000000000002e-06,
|
| 124 |
+
"loss": 0.1836,
|
| 125 |
+
"step": 450
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.81,
|
| 129 |
+
"learning_rate": 9.360000000000002e-06,
|
| 130 |
+
"loss": 0.182,
|
| 131 |
+
"step": 475
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.9,
|
| 135 |
+
"learning_rate": 9.86e-06,
|
| 136 |
+
"loss": 0.1762,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.9,
|
| 141 |
+
"eval_loss": 0.24587205052375793,
|
| 142 |
+
"eval_runtime": 397.383,
|
| 143 |
+
"eval_samples_per_second": 1.077,
|
| 144 |
+
"eval_steps_per_second": 0.136,
|
| 145 |
+
"eval_wer": 29.562500000000004,
|
| 146 |
+
"step": 500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.0,
|
| 150 |
+
"learning_rate": 9.640000000000001e-06,
|
| 151 |
+
"loss": 0.1894,
|
| 152 |
+
"step": 525
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.09,
|
| 156 |
+
"learning_rate": 9.14e-06,
|
| 157 |
+
"loss": 0.0819,
|
| 158 |
+
"step": 550
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.19,
|
| 162 |
+
"learning_rate": 8.64e-06,
|
| 163 |
+
"loss": 0.0843,
|
| 164 |
+
"step": 575
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.28,
|
| 168 |
+
"learning_rate": 8.14e-06,
|
| 169 |
+
"loss": 0.0843,
|
| 170 |
+
"step": 600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.38,
|
| 174 |
+
"learning_rate": 7.640000000000001e-06,
|
| 175 |
+
"loss": 0.0823,
|
| 176 |
+
"step": 625
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.47,
|
| 180 |
+
"learning_rate": 7.14e-06,
|
| 181 |
+
"loss": 0.0783,
|
| 182 |
+
"step": 650
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.57,
|
| 186 |
+
"learning_rate": 6.640000000000001e-06,
|
| 187 |
+
"loss": 0.08,
|
| 188 |
+
"step": 675
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.66,
|
| 192 |
+
"learning_rate": 6.1400000000000005e-06,
|
| 193 |
+
"loss": 0.07,
|
| 194 |
+
"step": 700
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.76,
|
| 198 |
+
"learning_rate": 5.64e-06,
|
| 199 |
+
"loss": 0.0798,
|
| 200 |
+
"step": 725
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.85,
|
| 204 |
+
"learning_rate": 5.140000000000001e-06,
|
| 205 |
+
"loss": 0.0578,
|
| 206 |
+
"step": 750
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.85,
|
| 210 |
+
"eval_loss": 0.24375540018081665,
|
| 211 |
+
"eval_runtime": 398.6003,
|
| 212 |
+
"eval_samples_per_second": 1.074,
|
| 213 |
+
"eval_steps_per_second": 0.135,
|
| 214 |
+
"eval_wer": 27.0875,
|
| 215 |
+
"step": 750
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.95,
|
| 219 |
+
"learning_rate": 4.6400000000000005e-06,
|
| 220 |
+
"loss": 0.0559,
|
| 221 |
+
"step": 775
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.04,
|
| 225 |
+
"learning_rate": 4.14e-06,
|
| 226 |
+
"loss": 0.0408,
|
| 227 |
+
"step": 800
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.14,
|
| 231 |
+
"learning_rate": 3.6400000000000003e-06,
|
| 232 |
+
"loss": 0.0289,
|
| 233 |
+
"step": 825
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.23,
|
| 237 |
+
"learning_rate": 3.1400000000000004e-06,
|
| 238 |
+
"loss": 0.0238,
|
| 239 |
+
"step": 850
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.33,
|
| 243 |
+
"learning_rate": 2.64e-06,
|
| 244 |
+
"loss": 0.0167,
|
| 245 |
+
"step": 875
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.42,
|
| 249 |
+
"learning_rate": 2.1400000000000003e-06,
|
| 250 |
+
"loss": 0.0171,
|
| 251 |
+
"step": 900
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.52,
|
| 255 |
+
"learning_rate": 1.6400000000000002e-06,
|
| 256 |
+
"loss": 0.0219,
|
| 257 |
+
"step": 925
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.61,
|
| 261 |
+
"learning_rate": 1.14e-06,
|
| 262 |
+
"loss": 0.0147,
|
| 263 |
+
"step": 950
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.71,
|
| 267 |
+
"learning_rate": 6.4e-07,
|
| 268 |
+
"loss": 0.0211,
|
| 269 |
+
"step": 975
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.8,
|
| 273 |
+
"learning_rate": 1.4e-07,
|
| 274 |
+
"loss": 0.0186,
|
| 275 |
+
"step": 1000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.8,
|
| 279 |
+
"eval_loss": 0.2395983189344406,
|
| 280 |
+
"eval_runtime": 444.9144,
|
| 281 |
+
"eval_samples_per_second": 0.962,
|
| 282 |
+
"eval_steps_per_second": 0.121,
|
| 283 |
+
"eval_wer": 34.65,
|
| 284 |
+
"step": 1000
|
| 285 |
+
}
|
| 286 |
+
],
|
| 287 |
+
"max_steps": 1000,
|
| 288 |
+
"num_train_epochs": 4,
|
| 289 |
+
"total_flos": 1.69853681664e+19,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c802fdf54fe9595195c971b352cda96c2c0b0ed91d43049d318e6e51037990d
|
| 3 |
+
size 3643
|