mohammadh128
commited on
Commit
·
3ffcd96
1
Parent(s):
83e3309
Training in progress, step 4000
Browse files- checkpoint-4000/config.json +42 -0
- checkpoint-4000/generation_config.json +113 -0
- checkpoint-4000/optimizer.pt +3 -0
- checkpoint-4000/preprocessor_config.json +0 -0
- checkpoint-4000/pytorch_model.bin +3 -0
- checkpoint-4000/rng_state.pth +3 -0
- checkpoint-4000/scaler.pt +3 -0
- checkpoint-4000/scheduler.pt +3 -0
- checkpoint-4000/trainer_state.json +64 -0
- checkpoint-4000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-4000/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-4000/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-4000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:601101092e1efb4172068c93d0178873e9a56c55167bb5789d29ed4750a712c2
|
3 |
+
size 1934158597
|
checkpoint-4000/preprocessor_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0a9e5660209cf04f005cd8d18275e76572f9e375d8426a9b7d36f3c3a87ac88
|
3 |
+
size 967099139
|
checkpoint-4000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70379eac538504d30ef24380be38c766144e9fede1c7a78db13cb6341677a1f2
|
3 |
+
size 14503
|
checkpoint-4000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa02d45812a0559e2a5e298a036be081271a1e8de095c1a9f7480edccaec5e9c
|
3 |
+
size 559
|
checkpoint-4000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace6e6b600224c400d0bed228d2f1fc5d9f3f70d7e0978e28df5f9eda9d66f37
|
3 |
+
size 623
|
checkpoint-4000/trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8592910848549946,
|
5 |
+
"global_step": 4000,
|
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": 6.10123648e-05,
|
13 |
+
"loss": 1.2324,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.21,
|
18 |
+
"learning_rate": 5.472524835555556e-05,
|
19 |
+
"loss": 0.7401,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.32,
|
24 |
+
"learning_rate": 4.789142613333333e-05,
|
25 |
+
"loss": 0.6104,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.43,
|
30 |
+
"learning_rate": 4.105760391111111e-05,
|
31 |
+
"loss": 0.5478,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.54,
|
36 |
+
"learning_rate": 3.4223781688888885e-05,
|
37 |
+
"loss": 0.4784,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.64,
|
42 |
+
"learning_rate": 2.7389959466666668e-05,
|
43 |
+
"loss": 0.4348,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.75,
|
48 |
+
"learning_rate": 2.0556137244444445e-05,
|
49 |
+
"loss": 0.3875,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.86,
|
54 |
+
"learning_rate": 1.3722315022222223e-05,
|
55 |
+
"loss": 0.3587,
|
56 |
+
"step": 4000
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"max_steps": 5000,
|
60 |
+
"num_train_epochs": 2,
|
61 |
+
"total_flos": 1.846946562048e+19,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": null
|
64 |
+
}
|
checkpoint-4000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a1c75d84d87e3d0838d46de30a891bf97e78786468d38612fc1413d5ee7b22
|
3 |
+
size 3695
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967099139
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0a9e5660209cf04f005cd8d18275e76572f9e375d8426a9b7d36f3c3a87ac88
|
3 |
size 967099139
|