noflm
commited on
Commit
·
3f9a553
1
Parent(s):
e9e6b57
Training in progress, step 1000
Browse files- .gitignore +0 -1
- checkpoint-1000/config.json +54 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/preprocessor_config.json +0 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +85 -0
- checkpoint-1000/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Dec29_11-02-08_srv/1672311810.0087752/events.out.tfevents.1672311810.srv.4532.1 +3 -0
- runs/Dec29_11-02-08_srv/events.out.tfevents.1672311809.srv.4532.0 +3 -0
- runs/Dec29_11-05-20_srv/1672311942.5617375/events.out.tfevents.1672311942.srv.13534.1 +3 -0
- runs/Dec29_11-05-20_srv/events.out.tfevents.1672311942.srv.13534.0 +3 -0
- training_args.bin +1 -1
.gitignore
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
checkpoint-*/
|
|
|
|
checkpoint-1000/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-base",
|
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": 512,
|
15 |
+
"decoder_attention_heads": 8,
|
16 |
+
"decoder_ffn_dim": 2048,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 50258,
|
20 |
+
"dropout": 0.0,
|
21 |
+
"encoder_attention_heads": 8,
|
22 |
+
"encoder_ffn_dim": 2048,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 6,
|
25 |
+
"eos_token_id": 50257,
|
26 |
+
"forced_decoder_ids": [
|
27 |
+
[
|
28 |
+
1,
|
29 |
+
50266
|
30 |
+
],
|
31 |
+
[
|
32 |
+
2,
|
33 |
+
50359
|
34 |
+
],
|
35 |
+
[
|
36 |
+
3,
|
37 |
+
50363
|
38 |
+
]
|
39 |
+
],
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"max_length": 448,
|
43 |
+
"max_source_positions": 1500,
|
44 |
+
"max_target_positions": 448,
|
45 |
+
"model_type": "whisper",
|
46 |
+
"num_hidden_layers": 6,
|
47 |
+
"num_mel_bins": 80,
|
48 |
+
"pad_token_id": 50257,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.26.0.dev0",
|
52 |
+
"use_cache": false,
|
53 |
+
"vocab_size": 51865
|
54 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac8255e0f6947c846a5f70b6d53d9a1b174e181a5a015aa1b9020c1ebfd62c85
|
3 |
+
size 580895237
|
checkpoint-1000/preprocessor_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8302b40127705f268df65823fd39f0b81495cad1e6797296cc2e38a41669c1db
|
3 |
+
size 290458721
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e48ff16cb4fad6505df65eb42a8223754d980c33de81cca2a185f842b510518b
|
3 |
+
size 14575
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dce1d2ae382ebe376f59073c1e3e94fa0133976fb67ca102a1b392494adc915
|
3 |
+
size 557
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9565f673f605d16aa4ea9a6a1af1f7c3c9c337cf3c667f3f7f7d61fb0a42e637
|
3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 111.0001,
|
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": 11.0,
|
12 |
+
"learning_rate": 4.85e-06,
|
13 |
+
"loss": 0.716,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 22.0,
|
18 |
+
"learning_rate": 9.85e-06,
|
19 |
+
"loss": 0.0615,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 33.0,
|
24 |
+
"learning_rate": 1e-05,
|
25 |
+
"loss": 0.0043,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 44.0,
|
30 |
+
"learning_rate": 1e-05,
|
31 |
+
"loss": 0.002,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 55.0,
|
36 |
+
"learning_rate": 1e-05,
|
37 |
+
"loss": 0.0008,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 66.0,
|
42 |
+
"learning_rate": 1e-05,
|
43 |
+
"loss": 0.0006,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 77.0,
|
48 |
+
"learning_rate": 1e-05,
|
49 |
+
"loss": 0.0004,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 88.0,
|
54 |
+
"learning_rate": 1e-05,
|
55 |
+
"loss": 0.0003,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 99.0,
|
60 |
+
"learning_rate": 1e-05,
|
61 |
+
"loss": 0.0003,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 111.0,
|
66 |
+
"learning_rate": 1e-05,
|
67 |
+
"loss": 0.0002,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 111.0,
|
72 |
+
"eval_loss": 0.21552081406116486,
|
73 |
+
"eval_runtime": 10.773,
|
74 |
+
"eval_samples_per_second": 1.671,
|
75 |
+
"eval_steps_per_second": 0.093,
|
76 |
+
"eval_wer": 9.75609756097561,
|
77 |
+
"step": 1000
|
78 |
+
}
|
79 |
+
],
|
80 |
+
"max_steps": 10000,
|
81 |
+
"num_train_epochs": 9223372036854775807,
|
82 |
+
"total_flos": 1.96032852393984e+18,
|
83 |
+
"trial_name": null,
|
84 |
+
"trial_params": null
|
85 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c36b35e37212c7c09dbca6abb82e5ea958e60ecae5b6ed572ed342d641b50f3
|
3 |
+
size 3643
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290458721
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8302b40127705f268df65823fd39f0b81495cad1e6797296cc2e38a41669c1db
|
3 |
size 290458721
|
runs/Dec29_11-02-08_srv/1672311810.0087752/events.out.tfevents.1672311810.srv.4532.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5e09c80b463ac5daf5bb71dbc2aea81a879afa35d2b2141491ca7f1fa690910
|
3 |
+
size 5935
|
runs/Dec29_11-02-08_srv/events.out.tfevents.1672311809.srv.4532.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70ee320ef3a5d16241061e8688df61dba693b2bd6b7fc1b72d0500632f8e58aa
|
3 |
+
size 4431
|
runs/Dec29_11-05-20_srv/1672311942.5617375/events.out.tfevents.1672311942.srv.13534.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce6dbee9444d59f921b000fe38060c7b63eb505d3b64044a1e910749ef43af36
|
3 |
+
size 5935
|
runs/Dec29_11-05-20_srv/events.out.tfevents.1672311942.srv.13534.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeed09adde4bf566279be710545476d82a7691167f10d6e35f5837b3db7c8381
|
3 |
+
size 6316
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3643
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c36b35e37212c7c09dbca6abb82e5ea958e60ecae5b6ed572ed342d641b50f3
|
3 |
size 3643
|