Commit ·
e965745
1
Parent(s): 565f988
Training in progress, step 2500
Browse files- checkpoint-2500/config.json +42 -0
- checkpoint-2500/generation_config.json +113 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/preprocessor_config.json +0 -0
- checkpoint-2500/pytorch_model.bin +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +46 -0
- checkpoint-2500/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Sep08_17-01-28_instance-20230908-000618/events.out.tfevents.1694192498.instance-20230908-000618 +2 -2
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/whisper-small",
|
| 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",
|
| 40 |
+
"use_cache": false,
|
| 41 |
+
"vocab_size": 51865
|
| 42 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
50358,
|
| 106 |
+
50359,
|
| 107 |
+
50360,
|
| 108 |
+
50361,
|
| 109 |
+
50362
|
| 110 |
+
],
|
| 111 |
+
"transformers_version": "4.26.0",
|
| 112 |
+
"use_cache": false
|
| 113 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:877b84a32ea33be3b66b033f5e451cd22830c818a3eb61e3f933cdc1c3959c22
|
| 3 |
+
size 1934161093
|
checkpoint-2500/preprocessor_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1795a2cd2e4bd2dc66c0c19cf6f19b337f846d9099ea7d1cdcd91602934bfd3
|
| 3 |
+
size 967102601
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baf026186c23e2f5e31c7cd7113cd39e8727cf1ca1d351a1f9adbb7cebd3d57f
|
| 3 |
+
size 14511
|
checkpoint-2500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee2831543285e5034b20010ff85efa196269ceeb26ba30eaa8ccf147105d8d01
|
| 3 |
+
size 557
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4da76cb794365cdcefbb37fbdd7ecf8fb21cc47abe53091ad97600eda29a4a93
|
| 3 |
+
size 627
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5370569280343717,
|
| 5 |
+
"global_step": 2500,
|
| 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": 9.920000000000002e-06,
|
| 13 |
+
"loss": 1.1198,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 8.897777777777779e-06,
|
| 19 |
+
"loss": 0.3108,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 7.786666666666666e-06,
|
| 25 |
+
"loss": 0.262,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 6.675555555555556e-06,
|
| 31 |
+
"loss": 0.2259,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.54,
|
| 36 |
+
"learning_rate": 5.566666666666667e-06,
|
| 37 |
+
"loss": 0.2037,
|
| 38 |
+
"step": 2500
|
| 39 |
+
}
|
| 40 |
+
],
|
| 41 |
+
"max_steps": 5000,
|
| 42 |
+
"num_train_epochs": 2,
|
| 43 |
+
"total_flos": 5.7717080064e+18,
|
| 44 |
+
"trial_name": null,
|
| 45 |
+
"trial_params": null
|
| 46 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e284696fe9fedcdc941e04f5677ff751558c41d1305edb2945de30d7c83dee
|
| 3 |
+
size 3707
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 967102601
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1795a2cd2e4bd2dc66c0c19cf6f19b337f846d9099ea7d1cdcd91602934bfd3
|
| 3 |
size 967102601
|
runs/Sep08_17-01-28_instance-20230908-000618/events.out.tfevents.1694192498.instance-20230908-000618
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 sha256:0a8a22585718b220b1bda57dfba8c50091868ffcf9770869f85695682f9605a2
|
| 3 |
+
size 5009
|