Upload 9 files
Browse files- config.json +42 -0
- optimizer.pt +3 -0
- preprocessor_config.json +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1012 -0
- training_args.bin +3 -0
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": "4.25.0.dev0",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 51865
|
42 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca8297d83886f44c37994c370987d7bd5daa532d82a2907e4916a10c23414da5
|
3 |
+
size 1934161093
|
preprocessor_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21dcfbd084578bf2ac04c939ef8037c223b97a51ba7e3fba1db6dcc3efca1263
|
3 |
+
size 967102601
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5409f6a73b1f84fa2790c79b9ca45b27a2eb9b6595e4747eb8139c1e79c48278
|
3 |
+
size 15597
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b52c3e387341445c8ba39921ab29ef6b3666f5695d208629ac56d41f19e06def
|
3 |
+
size 557
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:704b1a0b049fec0acafde69e4d157128ccfe20ff6f043233156342121f536311
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,1012 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 12.59661678594665,
|
3 |
+
"best_model_checkpoint": "./whisper-small-es/checkpoint-4000",
|
4 |
+
"epoch": 0.5202913631633714,
|
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": 0.0,
|
12 |
+
"learning_rate": 4.4e-07,
|
13 |
+
"loss": 3.6109,
|
14 |
+
"step": 25
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 9.400000000000001e-07,
|
19 |
+
"loss": 2.9572,
|
20 |
+
"step": 50
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.01,
|
24 |
+
"learning_rate": 1.44e-06,
|
25 |
+
"loss": 2.1006,
|
26 |
+
"step": 75
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.01,
|
30 |
+
"learning_rate": 1.94e-06,
|
31 |
+
"loss": 1.1929,
|
32 |
+
"step": 100
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.02,
|
36 |
+
"learning_rate": 2.4400000000000004e-06,
|
37 |
+
"loss": 0.9396,
|
38 |
+
"step": 125
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.02,
|
42 |
+
"learning_rate": 2.9400000000000002e-06,
|
43 |
+
"loss": 0.8505,
|
44 |
+
"step": 150
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.02,
|
48 |
+
"learning_rate": 3.44e-06,
|
49 |
+
"loss": 0.7412,
|
50 |
+
"step": 175
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.03,
|
54 |
+
"learning_rate": 3.94e-06,
|
55 |
+
"loss": 0.6639,
|
56 |
+
"step": 200
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.03,
|
60 |
+
"learning_rate": 4.440000000000001e-06,
|
61 |
+
"loss": 0.5763,
|
62 |
+
"step": 225
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.03,
|
66 |
+
"learning_rate": 4.94e-06,
|
67 |
+
"loss": 0.481,
|
68 |
+
"step": 250
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.04,
|
72 |
+
"learning_rate": 5.4400000000000004e-06,
|
73 |
+
"loss": 0.3388,
|
74 |
+
"step": 275
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.04,
|
78 |
+
"learning_rate": 5.94e-06,
|
79 |
+
"loss": 0.2682,
|
80 |
+
"step": 300
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.04,
|
84 |
+
"learning_rate": 6.440000000000001e-06,
|
85 |
+
"loss": 0.2751,
|
86 |
+
"step": 325
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.05,
|
90 |
+
"learning_rate": 6.9400000000000005e-06,
|
91 |
+
"loss": 0.2599,
|
92 |
+
"step": 350
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.05,
|
96 |
+
"learning_rate": 7.440000000000001e-06,
|
97 |
+
"loss": 0.2554,
|
98 |
+
"step": 375
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.05,
|
102 |
+
"learning_rate": 7.94e-06,
|
103 |
+
"loss": 0.263,
|
104 |
+
"step": 400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.06,
|
108 |
+
"learning_rate": 8.44e-06,
|
109 |
+
"loss": 0.255,
|
110 |
+
"step": 425
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.06,
|
114 |
+
"learning_rate": 8.94e-06,
|
115 |
+
"loss": 0.2631,
|
116 |
+
"step": 450
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.06,
|
120 |
+
"learning_rate": 9.440000000000001e-06,
|
121 |
+
"loss": 0.2428,
|
122 |
+
"step": 475
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.07,
|
126 |
+
"learning_rate": 9.940000000000001e-06,
|
127 |
+
"loss": 0.2676,
|
128 |
+
"step": 500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.07,
|
132 |
+
"learning_rate": 9.937142857142858e-06,
|
133 |
+
"loss": 0.2562,
|
134 |
+
"step": 525
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.07,
|
138 |
+
"learning_rate": 9.865714285714285e-06,
|
139 |
+
"loss": 0.2691,
|
140 |
+
"step": 550
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.07,
|
144 |
+
"learning_rate": 9.794285714285714e-06,
|
145 |
+
"loss": 0.2629,
|
146 |
+
"step": 575
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.08,
|
150 |
+
"learning_rate": 9.722857142857143e-06,
|
151 |
+
"loss": 0.249,
|
152 |
+
"step": 600
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.08,
|
156 |
+
"learning_rate": 9.651428571428572e-06,
|
157 |
+
"loss": 0.241,
|
158 |
+
"step": 625
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.08,
|
162 |
+
"learning_rate": 9.58e-06,
|
163 |
+
"loss": 0.2466,
|
164 |
+
"step": 650
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.09,
|
168 |
+
"learning_rate": 9.508571428571429e-06,
|
169 |
+
"loss": 0.2437,
|
170 |
+
"step": 675
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.09,
|
174 |
+
"learning_rate": 9.437142857142858e-06,
|
175 |
+
"loss": 0.2359,
|
176 |
+
"step": 700
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.09,
|
180 |
+
"learning_rate": 9.365714285714287e-06,
|
181 |
+
"loss": 0.2563,
|
182 |
+
"step": 725
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.1,
|
186 |
+
"learning_rate": 9.294285714285714e-06,
|
187 |
+
"loss": 0.2474,
|
188 |
+
"step": 750
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.1,
|
192 |
+
"learning_rate": 9.222857142857143e-06,
|
193 |
+
"loss": 0.2464,
|
194 |
+
"step": 775
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.1,
|
198 |
+
"learning_rate": 9.151428571428572e-06,
|
199 |
+
"loss": 0.2355,
|
200 |
+
"step": 800
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.11,
|
204 |
+
"learning_rate": 9.080000000000001e-06,
|
205 |
+
"loss": 0.2375,
|
206 |
+
"step": 825
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.11,
|
210 |
+
"learning_rate": 9.00857142857143e-06,
|
211 |
+
"loss": 0.2339,
|
212 |
+
"step": 850
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.11,
|
216 |
+
"learning_rate": 8.937142857142857e-06,
|
217 |
+
"loss": 0.2473,
|
218 |
+
"step": 875
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.12,
|
222 |
+
"learning_rate": 8.865714285714287e-06,
|
223 |
+
"loss": 0.2271,
|
224 |
+
"step": 900
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.12,
|
228 |
+
"learning_rate": 8.794285714285716e-06,
|
229 |
+
"loss": 0.2204,
|
230 |
+
"step": 925
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.12,
|
234 |
+
"learning_rate": 8.722857142857145e-06,
|
235 |
+
"loss": 0.2399,
|
236 |
+
"step": 950
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.13,
|
240 |
+
"learning_rate": 8.651428571428572e-06,
|
241 |
+
"loss": 0.2277,
|
242 |
+
"step": 975
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.13,
|
246 |
+
"learning_rate": 8.580000000000001e-06,
|
247 |
+
"loss": 0.2281,
|
248 |
+
"step": 1000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.13,
|
252 |
+
"eval_loss": 0.23893514275550842,
|
253 |
+
"eval_runtime": 3335.1749,
|
254 |
+
"eval_samples_per_second": 4.653,
|
255 |
+
"eval_steps_per_second": 0.291,
|
256 |
+
"eval_wer": 14.776187378009109,
|
257 |
+
"step": 1000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.13,
|
261 |
+
"learning_rate": 8.50857142857143e-06,
|
262 |
+
"loss": 0.2364,
|
263 |
+
"step": 1025
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.14,
|
267 |
+
"learning_rate": 8.437142857142859e-06,
|
268 |
+
"loss": 0.2224,
|
269 |
+
"step": 1050
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.14,
|
273 |
+
"learning_rate": 8.365714285714286e-06,
|
274 |
+
"loss": 0.2229,
|
275 |
+
"step": 1075
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.14,
|
279 |
+
"learning_rate": 8.294285714285715e-06,
|
280 |
+
"loss": 0.2459,
|
281 |
+
"step": 1100
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.15,
|
285 |
+
"learning_rate": 8.222857142857144e-06,
|
286 |
+
"loss": 0.2323,
|
287 |
+
"step": 1125
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.15,
|
291 |
+
"learning_rate": 8.151428571428572e-06,
|
292 |
+
"loss": 0.2277,
|
293 |
+
"step": 1150
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.15,
|
297 |
+
"learning_rate": 8.08e-06,
|
298 |
+
"loss": 0.2389,
|
299 |
+
"step": 1175
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.16,
|
303 |
+
"learning_rate": 8.00857142857143e-06,
|
304 |
+
"loss": 0.2101,
|
305 |
+
"step": 1200
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.16,
|
309 |
+
"learning_rate": 7.937142857142857e-06,
|
310 |
+
"loss": 0.2198,
|
311 |
+
"step": 1225
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.16,
|
315 |
+
"learning_rate": 7.865714285714286e-06,
|
316 |
+
"loss": 0.2212,
|
317 |
+
"step": 1250
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.17,
|
321 |
+
"learning_rate": 7.794285714285715e-06,
|
322 |
+
"loss": 0.2343,
|
323 |
+
"step": 1275
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 0.17,
|
327 |
+
"learning_rate": 7.722857142857142e-06,
|
328 |
+
"loss": 0.2291,
|
329 |
+
"step": 1300
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.17,
|
333 |
+
"learning_rate": 7.651428571428571e-06,
|
334 |
+
"loss": 0.2464,
|
335 |
+
"step": 1325
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.18,
|
339 |
+
"learning_rate": 7.58e-06,
|
340 |
+
"loss": 0.2234,
|
341 |
+
"step": 1350
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.18,
|
345 |
+
"learning_rate": 7.508571428571429e-06,
|
346 |
+
"loss": 0.2357,
|
347 |
+
"step": 1375
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.18,
|
351 |
+
"learning_rate": 7.4371428571428575e-06,
|
352 |
+
"loss": 0.2115,
|
353 |
+
"step": 1400
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.19,
|
357 |
+
"learning_rate": 7.365714285714286e-06,
|
358 |
+
"loss": 0.2329,
|
359 |
+
"step": 1425
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.19,
|
363 |
+
"learning_rate": 7.294285714285715e-06,
|
364 |
+
"loss": 0.2278,
|
365 |
+
"step": 1450
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.19,
|
369 |
+
"learning_rate": 7.222857142857144e-06,
|
370 |
+
"loss": 0.2132,
|
371 |
+
"step": 1475
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.2,
|
375 |
+
"learning_rate": 7.151428571428573e-06,
|
376 |
+
"loss": 0.2194,
|
377 |
+
"step": 1500
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.2,
|
381 |
+
"learning_rate": 7.08e-06,
|
382 |
+
"loss": 0.212,
|
383 |
+
"step": 1525
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 0.2,
|
387 |
+
"learning_rate": 7.008571428571429e-06,
|
388 |
+
"loss": 0.1977,
|
389 |
+
"step": 1550
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.2,
|
393 |
+
"learning_rate": 6.937142857142858e-06,
|
394 |
+
"loss": 0.2046,
|
395 |
+
"step": 1575
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.21,
|
399 |
+
"learning_rate": 6.865714285714287e-06,
|
400 |
+
"loss": 0.2166,
|
401 |
+
"step": 1600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.21,
|
405 |
+
"learning_rate": 6.794285714285714e-06,
|
406 |
+
"loss": 0.1992,
|
407 |
+
"step": 1625
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.21,
|
411 |
+
"learning_rate": 6.722857142857143e-06,
|
412 |
+
"loss": 0.2208,
|
413 |
+
"step": 1650
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 0.22,
|
417 |
+
"learning_rate": 6.651428571428572e-06,
|
418 |
+
"loss": 0.2302,
|
419 |
+
"step": 1675
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.22,
|
423 |
+
"learning_rate": 6.5800000000000005e-06,
|
424 |
+
"loss": 0.2109,
|
425 |
+
"step": 1700
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.22,
|
429 |
+
"learning_rate": 6.5085714285714295e-06,
|
430 |
+
"loss": 0.2234,
|
431 |
+
"step": 1725
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 0.23,
|
435 |
+
"learning_rate": 6.437142857142858e-06,
|
436 |
+
"loss": 0.2244,
|
437 |
+
"step": 1750
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.23,
|
441 |
+
"learning_rate": 6.365714285714286e-06,
|
442 |
+
"loss": 0.2146,
|
443 |
+
"step": 1775
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.23,
|
447 |
+
"learning_rate": 6.294285714285715e-06,
|
448 |
+
"loss": 0.2085,
|
449 |
+
"step": 1800
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 0.24,
|
453 |
+
"learning_rate": 6.222857142857144e-06,
|
454 |
+
"loss": 0.2091,
|
455 |
+
"step": 1825
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.24,
|
459 |
+
"learning_rate": 6.151428571428571e-06,
|
460 |
+
"loss": 0.2104,
|
461 |
+
"step": 1850
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.24,
|
465 |
+
"learning_rate": 6.08e-06,
|
466 |
+
"loss": 0.215,
|
467 |
+
"step": 1875
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.25,
|
471 |
+
"learning_rate": 6.008571428571429e-06,
|
472 |
+
"loss": 0.2243,
|
473 |
+
"step": 1900
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 0.25,
|
477 |
+
"learning_rate": 5.937142857142858e-06,
|
478 |
+
"loss": 0.2108,
|
479 |
+
"step": 1925
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.25,
|
483 |
+
"learning_rate": 5.865714285714286e-06,
|
484 |
+
"loss": 0.2066,
|
485 |
+
"step": 1950
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.26,
|
489 |
+
"learning_rate": 5.794285714285715e-06,
|
490 |
+
"loss": 0.2032,
|
491 |
+
"step": 1975
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.26,
|
495 |
+
"learning_rate": 5.722857142857144e-06,
|
496 |
+
"loss": 0.2164,
|
497 |
+
"step": 2000
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 0.26,
|
501 |
+
"eval_loss": 0.21823225915431976,
|
502 |
+
"eval_runtime": 3432.4709,
|
503 |
+
"eval_samples_per_second": 4.522,
|
504 |
+
"eval_steps_per_second": 0.283,
|
505 |
+
"eval_wer": 13.67078724788549,
|
506 |
+
"step": 2000
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.26,
|
510 |
+
"learning_rate": 5.651428571428572e-06,
|
511 |
+
"loss": 0.2052,
|
512 |
+
"step": 2025
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.27,
|
516 |
+
"learning_rate": 5.580000000000001e-06,
|
517 |
+
"loss": 0.2166,
|
518 |
+
"step": 2050
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.27,
|
522 |
+
"learning_rate": 5.508571428571429e-06,
|
523 |
+
"loss": 0.1913,
|
524 |
+
"step": 2075
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.27,
|
528 |
+
"learning_rate": 5.437142857142857e-06,
|
529 |
+
"loss": 0.2101,
|
530 |
+
"step": 2100
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.28,
|
534 |
+
"learning_rate": 5.365714285714286e-06,
|
535 |
+
"loss": 0.2018,
|
536 |
+
"step": 2125
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.28,
|
540 |
+
"learning_rate": 5.294285714285715e-06,
|
541 |
+
"loss": 0.1918,
|
542 |
+
"step": 2150
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.28,
|
546 |
+
"learning_rate": 5.2228571428571425e-06,
|
547 |
+
"loss": 0.1953,
|
548 |
+
"step": 2175
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.29,
|
552 |
+
"learning_rate": 5.1514285714285715e-06,
|
553 |
+
"loss": 0.2102,
|
554 |
+
"step": 2200
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.29,
|
558 |
+
"learning_rate": 5.0800000000000005e-06,
|
559 |
+
"loss": 0.2137,
|
560 |
+
"step": 2225
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.29,
|
564 |
+
"learning_rate": 5.0085714285714295e-06,
|
565 |
+
"loss": 0.1992,
|
566 |
+
"step": 2250
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.3,
|
570 |
+
"learning_rate": 4.937142857142858e-06,
|
571 |
+
"loss": 0.1964,
|
572 |
+
"step": 2275
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.3,
|
576 |
+
"learning_rate": 4.865714285714287e-06,
|
577 |
+
"loss": 0.2112,
|
578 |
+
"step": 2300
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.3,
|
582 |
+
"learning_rate": 4.794285714285715e-06,
|
583 |
+
"loss": 0.2023,
|
584 |
+
"step": 2325
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.31,
|
588 |
+
"learning_rate": 4.722857142857144e-06,
|
589 |
+
"loss": 0.2002,
|
590 |
+
"step": 2350
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.31,
|
594 |
+
"learning_rate": 4.651428571428572e-06,
|
595 |
+
"loss": 0.1945,
|
596 |
+
"step": 2375
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.31,
|
600 |
+
"learning_rate": 4.58e-06,
|
601 |
+
"loss": 0.2009,
|
602 |
+
"step": 2400
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.32,
|
606 |
+
"learning_rate": 4.508571428571429e-06,
|
607 |
+
"loss": 0.2132,
|
608 |
+
"step": 2425
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.32,
|
612 |
+
"learning_rate": 4.437142857142857e-06,
|
613 |
+
"loss": 0.2044,
|
614 |
+
"step": 2450
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.32,
|
618 |
+
"learning_rate": 4.3657142857142855e-06,
|
619 |
+
"loss": 0.2173,
|
620 |
+
"step": 2475
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.33,
|
624 |
+
"learning_rate": 4.2942857142857146e-06,
|
625 |
+
"loss": 0.2053,
|
626 |
+
"step": 2500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.33,
|
630 |
+
"learning_rate": 4.222857142857143e-06,
|
631 |
+
"loss": 0.214,
|
632 |
+
"step": 2525
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.33,
|
636 |
+
"learning_rate": 4.151428571428572e-06,
|
637 |
+
"loss": 0.1971,
|
638 |
+
"step": 2550
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.33,
|
642 |
+
"learning_rate": 4.08e-06,
|
643 |
+
"loss": 0.1954,
|
644 |
+
"step": 2575
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.34,
|
648 |
+
"learning_rate": 4.008571428571429e-06,
|
649 |
+
"loss": 0.194,
|
650 |
+
"step": 2600
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.34,
|
654 |
+
"learning_rate": 3.937142857142858e-06,
|
655 |
+
"loss": 0.1921,
|
656 |
+
"step": 2625
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.34,
|
660 |
+
"learning_rate": 3.865714285714286e-06,
|
661 |
+
"loss": 0.1968,
|
662 |
+
"step": 2650
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.35,
|
666 |
+
"learning_rate": 3.7942857142857147e-06,
|
667 |
+
"loss": 0.1984,
|
668 |
+
"step": 2675
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.35,
|
672 |
+
"learning_rate": 3.722857142857143e-06,
|
673 |
+
"loss": 0.1925,
|
674 |
+
"step": 2700
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.35,
|
678 |
+
"learning_rate": 3.651428571428572e-06,
|
679 |
+
"loss": 0.1998,
|
680 |
+
"step": 2725
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.36,
|
684 |
+
"learning_rate": 3.58e-06,
|
685 |
+
"loss": 0.1758,
|
686 |
+
"step": 2750
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.36,
|
690 |
+
"learning_rate": 3.508571428571429e-06,
|
691 |
+
"loss": 0.1924,
|
692 |
+
"step": 2775
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.36,
|
696 |
+
"learning_rate": 3.437142857142857e-06,
|
697 |
+
"loss": 0.2127,
|
698 |
+
"step": 2800
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.37,
|
702 |
+
"learning_rate": 3.3657142857142862e-06,
|
703 |
+
"loss": 0.2172,
|
704 |
+
"step": 2825
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.37,
|
708 |
+
"learning_rate": 3.2942857142857144e-06,
|
709 |
+
"loss": 0.1868,
|
710 |
+
"step": 2850
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.37,
|
714 |
+
"learning_rate": 3.222857142857143e-06,
|
715 |
+
"loss": 0.1918,
|
716 |
+
"step": 2875
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.38,
|
720 |
+
"learning_rate": 3.151428571428572e-06,
|
721 |
+
"loss": 0.2047,
|
722 |
+
"step": 2900
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.38,
|
726 |
+
"learning_rate": 3.08e-06,
|
727 |
+
"loss": 0.2005,
|
728 |
+
"step": 2925
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.38,
|
732 |
+
"learning_rate": 3.008571428571429e-06,
|
733 |
+
"loss": 0.2047,
|
734 |
+
"step": 2950
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.39,
|
738 |
+
"learning_rate": 2.9371428571428573e-06,
|
739 |
+
"loss": 0.1821,
|
740 |
+
"step": 2975
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.39,
|
744 |
+
"learning_rate": 2.865714285714286e-06,
|
745 |
+
"loss": 0.1882,
|
746 |
+
"step": 3000
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.39,
|
750 |
+
"eval_loss": 0.20569948852062225,
|
751 |
+
"eval_runtime": 3414.7908,
|
752 |
+
"eval_samples_per_second": 4.545,
|
753 |
+
"eval_steps_per_second": 0.284,
|
754 |
+
"eval_wer": 12.744957709824334,
|
755 |
+
"step": 3000
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 0.39,
|
759 |
+
"learning_rate": 2.7942857142857145e-06,
|
760 |
+
"loss": 0.2145,
|
761 |
+
"step": 3025
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.4,
|
765 |
+
"learning_rate": 2.722857142857143e-06,
|
766 |
+
"loss": 0.1963,
|
767 |
+
"step": 3050
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.4,
|
771 |
+
"learning_rate": 2.6514285714285713e-06,
|
772 |
+
"loss": 0.1969,
|
773 |
+
"step": 3075
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.4,
|
777 |
+
"learning_rate": 2.5800000000000003e-06,
|
778 |
+
"loss": 0.2012,
|
779 |
+
"step": 3100
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.41,
|
783 |
+
"learning_rate": 2.5085714285714285e-06,
|
784 |
+
"loss": 0.2108,
|
785 |
+
"step": 3125
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 0.41,
|
789 |
+
"learning_rate": 2.4371428571428575e-06,
|
790 |
+
"loss": 0.1977,
|
791 |
+
"step": 3150
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 0.41,
|
795 |
+
"learning_rate": 2.365714285714286e-06,
|
796 |
+
"loss": 0.2056,
|
797 |
+
"step": 3175
|
798 |
+
},
|
799 |
+
{
|
800 |
+
"epoch": 0.42,
|
801 |
+
"learning_rate": 2.2942857142857146e-06,
|
802 |
+
"loss": 0.2022,
|
803 |
+
"step": 3200
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 0.42,
|
807 |
+
"learning_rate": 2.222857142857143e-06,
|
808 |
+
"loss": 0.1952,
|
809 |
+
"step": 3225
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.42,
|
813 |
+
"learning_rate": 2.1514285714285714e-06,
|
814 |
+
"loss": 0.2001,
|
815 |
+
"step": 3250
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.43,
|
819 |
+
"learning_rate": 2.08e-06,
|
820 |
+
"loss": 0.1961,
|
821 |
+
"step": 3275
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.43,
|
825 |
+
"learning_rate": 2.0085714285714286e-06,
|
826 |
+
"loss": 0.207,
|
827 |
+
"step": 3300
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 0.43,
|
831 |
+
"learning_rate": 1.9371428571428576e-06,
|
832 |
+
"loss": 0.1752,
|
833 |
+
"step": 3325
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 0.44,
|
837 |
+
"learning_rate": 1.865714285714286e-06,
|
838 |
+
"loss": 0.2032,
|
839 |
+
"step": 3350
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 0.44,
|
843 |
+
"learning_rate": 1.7942857142857146e-06,
|
844 |
+
"loss": 0.1942,
|
845 |
+
"step": 3375
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 0.44,
|
849 |
+
"learning_rate": 1.7228571428571432e-06,
|
850 |
+
"loss": 0.1946,
|
851 |
+
"step": 3400
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.45,
|
855 |
+
"learning_rate": 1.6514285714285715e-06,
|
856 |
+
"loss": 0.1856,
|
857 |
+
"step": 3425
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.45,
|
861 |
+
"learning_rate": 1.5800000000000001e-06,
|
862 |
+
"loss": 0.1932,
|
863 |
+
"step": 3450
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.45,
|
867 |
+
"learning_rate": 1.5085714285714287e-06,
|
868 |
+
"loss": 0.2013,
|
869 |
+
"step": 3475
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 0.46,
|
873 |
+
"learning_rate": 1.4371428571428573e-06,
|
874 |
+
"loss": 0.189,
|
875 |
+
"step": 3500
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 0.46,
|
879 |
+
"learning_rate": 1.3657142857142857e-06,
|
880 |
+
"loss": 0.1765,
|
881 |
+
"step": 3525
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 0.46,
|
885 |
+
"learning_rate": 1.2942857142857143e-06,
|
886 |
+
"loss": 0.1912,
|
887 |
+
"step": 3550
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 0.47,
|
891 |
+
"learning_rate": 1.222857142857143e-06,
|
892 |
+
"loss": 0.1746,
|
893 |
+
"step": 3575
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.47,
|
897 |
+
"learning_rate": 1.1514285714285714e-06,
|
898 |
+
"loss": 0.2028,
|
899 |
+
"step": 3600
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.47,
|
903 |
+
"learning_rate": 1.08e-06,
|
904 |
+
"loss": 0.1869,
|
905 |
+
"step": 3625
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.47,
|
909 |
+
"learning_rate": 1.0085714285714286e-06,
|
910 |
+
"loss": 0.1978,
|
911 |
+
"step": 3650
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 0.48,
|
915 |
+
"learning_rate": 9.371428571428571e-07,
|
916 |
+
"loss": 0.1796,
|
917 |
+
"step": 3675
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 0.48,
|
921 |
+
"learning_rate": 8.657142857142858e-07,
|
922 |
+
"loss": 0.1832,
|
923 |
+
"step": 3700
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.48,
|
927 |
+
"learning_rate": 7.942857142857144e-07,
|
928 |
+
"loss": 0.1986,
|
929 |
+
"step": 3725
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 0.49,
|
933 |
+
"learning_rate": 7.228571428571429e-07,
|
934 |
+
"loss": 0.1785,
|
935 |
+
"step": 3750
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.49,
|
939 |
+
"learning_rate": 6.514285714285715e-07,
|
940 |
+
"loss": 0.1903,
|
941 |
+
"step": 3775
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.49,
|
945 |
+
"learning_rate": 5.800000000000001e-07,
|
946 |
+
"loss": 0.199,
|
947 |
+
"step": 3800
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.5,
|
951 |
+
"learning_rate": 5.085714285714286e-07,
|
952 |
+
"loss": 0.2056,
|
953 |
+
"step": 3825
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 0.5,
|
957 |
+
"learning_rate": 4.371428571428572e-07,
|
958 |
+
"loss": 0.1765,
|
959 |
+
"step": 3850
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.5,
|
963 |
+
"learning_rate": 3.657142857142858e-07,
|
964 |
+
"loss": 0.1929,
|
965 |
+
"step": 3875
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.51,
|
969 |
+
"learning_rate": 2.942857142857143e-07,
|
970 |
+
"loss": 0.1893,
|
971 |
+
"step": 3900
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.51,
|
975 |
+
"learning_rate": 2.228571428571429e-07,
|
976 |
+
"loss": 0.1987,
|
977 |
+
"step": 3925
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.51,
|
981 |
+
"learning_rate": 1.5142857142857144e-07,
|
982 |
+
"loss": 0.1899,
|
983 |
+
"step": 3950
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.52,
|
987 |
+
"learning_rate": 8e-08,
|
988 |
+
"loss": 0.1795,
|
989 |
+
"step": 3975
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.52,
|
993 |
+
"learning_rate": 8.571428571428572e-09,
|
994 |
+
"loss": 0.1842,
|
995 |
+
"step": 4000
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 0.52,
|
999 |
+
"eval_loss": 0.1998378336429596,
|
1000 |
+
"eval_runtime": 3156.5927,
|
1001 |
+
"eval_samples_per_second": 4.917,
|
1002 |
+
"eval_steps_per_second": 0.307,
|
1003 |
+
"eval_wer": 12.59661678594665,
|
1004 |
+
"step": 4000
|
1005 |
+
}
|
1006 |
+
],
|
1007 |
+
"max_steps": 4000,
|
1008 |
+
"num_train_epochs": 1,
|
1009 |
+
"total_flos": 3.693893124096e+19,
|
1010 |
+
"trial_name": null,
|
1011 |
+
"trial_params": null
|
1012 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f47e3c4a242574379cbd31cff7555ea0792be1cb222205801eb464c2ed9ef62
|
3 |
+
size 3515
|