Training in progress, step 100
Browse files- config.json +9 -9
- model.safetensors +2 -2
- runs/Apr18_11-49-58_ai-matrix-train/events.out.tfevents.1713441000.ai-matrix-train.458140.0 +3 -0
- runs/Apr18_11-50-29_ai-matrix-train/events.out.tfevents.1713441032.ai-matrix-train.458205.0 +3 -0
- runs/Apr18_11-53-26_ai-matrix-train/events.out.tfevents.1713441208.ai-matrix-train.458340.0 +3 -0
- runs/Apr18_11-54-49_ai-matrix-train/events.out.tfevents.1713441290.ai-matrix-train.458978.0 +3 -0
- runs/Apr18_12-22-08_ai-matrix-train/events.out.tfevents.1713442930.ai-matrix-train.460543.0 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "openai/whisper-
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
@@ -13,17 +13,17 @@
|
|
13 |
],
|
14 |
"bos_token_id": 50257,
|
15 |
"classifier_proj_size": 256,
|
16 |
-
"d_model":
|
17 |
-
"decoder_attention_heads":
|
18 |
-
"decoder_ffn_dim":
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
-
"decoder_layers":
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
-
"encoder_attention_heads":
|
24 |
-
"encoder_ffn_dim":
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
-
"encoder_layers":
|
27 |
"eos_token_id": 50257,
|
28 |
"forced_decoder_ids": [
|
29 |
[
|
@@ -52,7 +52,7 @@
|
|
52 |
"max_target_positions": 448,
|
53 |
"median_filter_width": 7,
|
54 |
"model_type": "whisper",
|
55 |
-
"num_hidden_layers":
|
56 |
"num_mel_bins": 80,
|
57 |
"pad_token_id": 50257,
|
58 |
"scale_embedding": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "openai/whisper-medium",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
13 |
],
|
14 |
"bos_token_id": 50257,
|
15 |
"classifier_proj_size": 256,
|
16 |
+
"d_model": 1024,
|
17 |
+
"decoder_attention_heads": 16,
|
18 |
+
"decoder_ffn_dim": 4096,
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 24,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 24,
|
27 |
"eos_token_id": 50257,
|
28 |
"forced_decoder_ids": [
|
29 |
[
|
|
|
52 |
"max_target_positions": 448,
|
53 |
"median_filter_width": 7,
|
54 |
"model_type": "whisper",
|
55 |
+
"num_hidden_layers": 24,
|
56 |
"num_mel_bins": 80,
|
57 |
"pad_token_id": 50257,
|
58 |
"scale_embedding": false,
|
model.safetensors
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 sha256:93ecf09cf73ed66bb6342fa32bbad38581c441edd6ed78218666551f10c274aa
|
3 |
+
size 3055544304
|
runs/Apr18_11-49-58_ai-matrix-train/events.out.tfevents.1713441000.ai-matrix-train.458140.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c9eb78e20c13c6c871d1554df69f3d0b1e08d30d1f62260cae695a25fbc4d4
|
3 |
+
size 6411
|
runs/Apr18_11-50-29_ai-matrix-train/events.out.tfevents.1713441032.ai-matrix-train.458205.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8a8c0fb6824ab9929369530db7df508d1b804b7e23301181bca0e82680e4985
|
3 |
+
size 5399
|
runs/Apr18_11-53-26_ai-matrix-train/events.out.tfevents.1713441208.ai-matrix-train.458340.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8570a87e3547856fc807e296de5fd242e5b63f19520585c5c318ba76962475c9
|
3 |
+
size 6411
|
runs/Apr18_11-54-49_ai-matrix-train/events.out.tfevents.1713441290.ai-matrix-train.458978.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de468590ab4eb47833d8f9ddbf4cb75d011b6a5fbd3827a91fa3d30bb892d54b
|
3 |
+
size 10611
|
runs/Apr18_12-22-08_ai-matrix-train/events.out.tfevents.1713442930.ai-matrix-train.460543.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c3b7d5bb633ae9d814b72477049840d6e095b7b6ef9a144d41ea7dfc5cabe6e
|
3 |
+
size 7951
|
tokenizer_config.json
CHANGED
@@ -12980,7 +12980,7 @@
|
|
12980 |
"clean_up_tokenization_spaces": true,
|
12981 |
"eos_token": "<|endoftext|>",
|
12982 |
"errors": "replace",
|
12983 |
-
"model_max_length":
|
12984 |
"pad_token": "<|endoftext|>",
|
12985 |
"processor_class": "WhisperProcessor",
|
12986 |
"return_attention_mask": false,
|
|
|
12980 |
"clean_up_tokenization_spaces": true,
|
12981 |
"eos_token": "<|endoftext|>",
|
12982 |
"errors": "replace",
|
12983 |
+
"model_max_length": 1024,
|
12984 |
"pad_token": "<|endoftext|>",
|
12985 |
"processor_class": "WhisperProcessor",
|
12986 |
"return_attention_mask": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0133dc206bc8ddf1070d381929df4dc85cc255450e8746826161000475900106
|
3 |
size 5112
|