End of training
Browse files- check-500/config.json +0 -42
- check-500/optimizer.pt +0 -3
- check-500/preprocessor_config.json +0 -0
- check-500/pytorch_model.bin +0 -3
- check-500/rng_state.pth +0 -3
- check-500/trainer_state.json +0 -145
- check-500/training_args.bin +0 -3
- config.json +1 -1
- check-500/scheduler.pt → runs/Dec21_19-12-23_b52bb8012851/1671650010.2397504/events.out.tfevents.1671650010.b52bb8012851.757.3 +2 -2
- check-500/scaler.pt → runs/Dec21_19-12-23_b52bb8012851/events.out.tfevents.1671650010.b52bb8012851.757.2 +2 -2
- training_args.bin +1 -1
check-500/config.json
DELETED
@@ -1,42 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "Martha-987/whisper-small-Arabic-aar",
|
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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
check-500/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b6f71e37c76d17d37b6c49bb6a06e88743c3d4d0dd59c914c9ca0ab4201476e4
|
3 |
-
size 1934161093
|
|
|
|
|
|
|
|
check-500/preprocessor_config.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
check-500/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b23b42f5b3ab491865863fb24d42677e6befbc7b433819cd00967ec7a3d0b440
|
3 |
-
size 967102601
|
|
|
|
|
|
|
|
check-500/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:532443d81ef4fb524dc55aadfa88d56a742d906f97342a48a45079087affca6c
|
3 |
-
size 14575
|
|
|
|
|
|
|
|
check-500/trainer_state.json
DELETED
@@ -1,145 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 54.78835735928749,
|
3 |
-
"best_model_checkpoint": "./whisper-small-Arabic-aar11/checkpoint-500",
|
4 |
-
"epoch": 0.20781379883624274,
|
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": 0.01,
|
12 |
-
"learning_rate": 4.6000000000000004e-07,
|
13 |
-
"loss": 0.4095,
|
14 |
-
"step": 25
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.02,
|
18 |
-
"learning_rate": 9.600000000000001e-07,
|
19 |
-
"loss": 0.367,
|
20 |
-
"step": 50
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.03,
|
24 |
-
"learning_rate": 1.46e-06,
|
25 |
-
"loss": 0.3891,
|
26 |
-
"step": 75
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.04,
|
30 |
-
"learning_rate": 1.9600000000000003e-06,
|
31 |
-
"loss": 0.3948,
|
32 |
-
"step": 100
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.05,
|
36 |
-
"learning_rate": 2.46e-06,
|
37 |
-
"loss": 0.392,
|
38 |
-
"step": 125
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.06,
|
42 |
-
"learning_rate": 2.96e-06,
|
43 |
-
"loss": 0.3581,
|
44 |
-
"step": 150
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.07,
|
48 |
-
"learning_rate": 3.46e-06,
|
49 |
-
"loss": 0.3859,
|
50 |
-
"step": 175
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.08,
|
54 |
-
"learning_rate": 3.96e-06,
|
55 |
-
"loss": 0.3538,
|
56 |
-
"step": 200
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.09,
|
60 |
-
"learning_rate": 4.4600000000000005e-06,
|
61 |
-
"loss": 0.3655,
|
62 |
-
"step": 225
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.1,
|
66 |
-
"learning_rate": 4.960000000000001e-06,
|
67 |
-
"loss": 0.3524,
|
68 |
-
"step": 250
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.11,
|
72 |
-
"learning_rate": 5.460000000000001e-06,
|
73 |
-
"loss": 0.3462,
|
74 |
-
"step": 275
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 0.12,
|
78 |
-
"learning_rate": 5.94e-06,
|
79 |
-
"loss": 0.3635,
|
80 |
-
"step": 300
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 0.14,
|
84 |
-
"learning_rate": 6.440000000000001e-06,
|
85 |
-
"loss": 0.3448,
|
86 |
-
"step": 325
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.15,
|
90 |
-
"learning_rate": 6.9400000000000005e-06,
|
91 |
-
"loss": 0.3565,
|
92 |
-
"step": 350
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 0.16,
|
96 |
-
"learning_rate": 7.440000000000001e-06,
|
97 |
-
"loss": 0.3398,
|
98 |
-
"step": 375
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 0.17,
|
102 |
-
"learning_rate": 7.94e-06,
|
103 |
-
"loss": 0.3582,
|
104 |
-
"step": 400
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.18,
|
108 |
-
"learning_rate": 8.44e-06,
|
109 |
-
"loss": 0.3824,
|
110 |
-
"step": 425
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.19,
|
114 |
-
"learning_rate": 8.94e-06,
|
115 |
-
"loss": 0.3858,
|
116 |
-
"step": 450
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 0.2,
|
120 |
-
"learning_rate": 9.440000000000001e-06,
|
121 |
-
"loss": 0.3145,
|
122 |
-
"step": 475
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 0.21,
|
126 |
-
"learning_rate": 9.940000000000001e-06,
|
127 |
-
"loss": 0.3256,
|
128 |
-
"step": 500
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.21,
|
132 |
-
"eval_loss": 0.4237127900123596,
|
133 |
-
"eval_runtime": 4883.7495,
|
134 |
-
"eval_samples_per_second": 2.138,
|
135 |
-
"eval_steps_per_second": 0.267,
|
136 |
-
"eval_wer": 54.78835735928749,
|
137 |
-
"step": 500
|
138 |
-
}
|
139 |
-
],
|
140 |
-
"max_steps": 500,
|
141 |
-
"num_train_epochs": 1,
|
142 |
-
"total_flos": 2.30868320256e+18,
|
143 |
-
"trial_name": null,
|
144 |
-
"trial_params": null
|
145 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
check-500/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:72c9b4273b92e769ca0ed0bf95124af0ee366f4bc6706fbb1368bb9beff2810f
|
3 |
-
size 3643
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"architectures": [
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/whisper-small-Arabic-aar11/checkpoint-500",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"architectures": [
|
check-500/scheduler.pt → runs/Dec21_19-12-23_b52bb8012851/1671650010.2397504/events.out.tfevents.1671650010.b52bb8012851.757.3
RENAMED
@@ -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 sha256:126dd4c2ff412bd1dd74914279f0fbd9fca3ad631c5346b4fcefb4acabdd065c
|
3 |
+
size 5941
|
check-500/scaler.pt → runs/Dec21_19-12-23_b52bb8012851/events.out.tfevents.1671650010.b52bb8012851.757.2
RENAMED
@@ -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 sha256:7edb829a8b815a55cd914d6e89c5946034bcc4047e291a2e783540a884a9eac5
|
3 |
+
size 4744
|
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:efc68bb38ff3fe734ae72e289441a106c44d918d4f872a2b7696aa64deb03a6a
|
3 |
size 3643
|