rscolati commited on
Commit
a4ad34a
1 Parent(s): 41cb0d4

Training in progress, step 500

Browse files
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.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 51865
42
+ }
last-checkpoint/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.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 51865
42
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3019d592ac2214bc34c970a13e858f6a548e2f3c6a8529ed995697d3017ddf2
3
+ size 1934158597
last-checkpoint/preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db5428df45748f5cef71a46ba6d813033461045b670de58e60a0d04c73f3187
3
+ size 967099139
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91df483d76db818e32264a4bed794781b8c0596f68ba0c37ccc0e11599204a99
3
+ size 14439
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:260a33848ea3e9ae911e570cae9bcabce5ca488fc1c8b3df9ab2ca3c3443394c
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016fe8e8a044cb8b996a30294312b233b45f5a8658dbff1e6856e6b8a5f831c6
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 23.903632599284773,
3
+ "best_model_checkpoint": "drive/MyDrive/whisper-small-sv/checkpoint-500",
4
+ "epoch": 0.6468305304010349,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 4.92e-06,
13
+ "loss": 1.683,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.65,
18
+ "learning_rate": 9.920000000000002e-06,
19
+ "loss": 0.326,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.65,
24
+ "eval_loss": 0.32677161693573,
25
+ "eval_runtime": 2129.4049,
26
+ "eval_samples_per_second": 2.38,
27
+ "eval_steps_per_second": 0.298,
28
+ "eval_wer": 23.903632599284773,
29
+ "step": 500
30
+ }
31
+ ],
32
+ "max_steps": 4000,
33
+ "num_train_epochs": 6,
34
+ "total_flos": 2.30868320256e+18,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e1db512506afa070e85c2110e25009481ea0e30add79b38ed7e6b55384b1f1
3
+ size 3567
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db5428df45748f5cef71a46ba6d813033461045b670de58e60a0d04c73f3187
3
+ size 967099139
runs/Dec07_10-13-58_5b012053c450/1670408086.057574/events.out.tfevents.1670408086.5b012053c450.76.1 CHANGED
Binary files a/runs/Dec07_10-13-58_5b012053c450/1670408086.057574/events.out.tfevents.1670408086.5b012053c450.76.1 and b/runs/Dec07_10-13-58_5b012053c450/1670408086.057574/events.out.tfevents.1670408086.5b012053c450.76.1 differ
 
runs/Dec07_10-13-58_5b012053c450/events.out.tfevents.1670408086.5b012053c450.76.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f36c0674570e3ff7d5abd65d722c847cc6ea5e9d73730d2064e007f6ba79aa6
3
+ size 4906
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e1db512506afa070e85c2110e25009481ea0e30add79b38ed7e6b55384b1f1
3
+ size 3567