marinone94
commited on
Commit
β’
287246d
1
Parent(s):
ae8505c
Training in progress, step 150
Browse files- {checkpoint-5 β checkpoint-150}/config.json +0 -0
- {checkpoint-5 β checkpoint-150}/optimizer.pt +1 -1
- {checkpoint-5 β checkpoint-150}/preprocessor_config.json +0 -0
- {checkpoint-5 β checkpoint-150}/pytorch_model.bin +1 -1
- {checkpoint-5 β checkpoint-150}/rng_state.pth +1 -1
- {checkpoint-5 β checkpoint-150}/scaler.pt +1 -1
- {checkpoint-5 β checkpoint-150}/scheduler.pt +1 -1
- checkpoint-150/trainer_state.json +133 -0
- {checkpoint-5 β checkpoint-150}/training_args.bin +1 -1
- checkpoint-5/trainer_state.json +0 -55
- pytorch_model.bin +1 -1
{checkpoint-5 β checkpoint-150}/config.json
RENAMED
File without changes
|
{checkpoint-5 β checkpoint-150}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490361937
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9f8e6594c4e496478e4866e70b042c6a88c87612acaf661f65750f58a301e4f
|
3 |
size 2490361937
|
{checkpoint-5 β checkpoint-150}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-5 β checkpoint-150}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262075377
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386439db8a06ec7bb8279d96099b6db5fee78683933dd8e79efdb684fee3e2c0
|
3 |
size 1262075377
|
{checkpoint-5 β checkpoint-150}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f704415bae2d9ff4df8dc44b817ddfc862d4dd0c72e611cb60926dc7d7e582d1
|
3 |
size 14567
|
{checkpoint-5 β checkpoint-150}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:968c71c75fc57c68b8d331de92abbf974f36bbab2c395cec452f6a60d0999a20
|
3 |
size 559
|
{checkpoint-5 β checkpoint-150}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dac0ff029249bda5eded6c55167fca809c071e881ce886494b4c2d2d40b64c39
|
3 |
size 623
|
checkpoint-150/trainer_state.json
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.43509789702683105,
|
5 |
+
"global_step": 150,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 3.75e-05,
|
13 |
+
"loss": 12.1562,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 7.125e-05,
|
19 |
+
"loss": 8.7679,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.09,
|
24 |
+
"learning_rate": 7.398952095808383e-05,
|
25 |
+
"loss": 5.3683,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 7.286676646706586e-05,
|
31 |
+
"loss": 4.3219,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.15,
|
36 |
+
"learning_rate": 7.17440119760479e-05,
|
37 |
+
"loss": 3.7182,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.15,
|
42 |
+
"eval_loss": 3.836604595184326,
|
43 |
+
"eval_runtime": 133.4846,
|
44 |
+
"eval_samples_per_second": 34.611,
|
45 |
+
"eval_steps_per_second": 4.33,
|
46 |
+
"eval_wer": 1.0,
|
47 |
+
"step": 50
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.17,
|
51 |
+
"learning_rate": 7.062125748502993e-05,
|
52 |
+
"loss": 3.478,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.2,
|
57 |
+
"learning_rate": 6.949850299401197e-05,
|
58 |
+
"loss": 3.4492,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.23,
|
63 |
+
"learning_rate": 6.837574850299401e-05,
|
64 |
+
"loss": 3.3928,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.26,
|
69 |
+
"learning_rate": 6.725299401197604e-05,
|
70 |
+
"loss": 3.3183,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.29,
|
75 |
+
"learning_rate": 6.613023952095809e-05,
|
76 |
+
"loss": 3.2075,
|
77 |
+
"step": 100
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.29,
|
81 |
+
"eval_loss": 3.258362293243408,
|
82 |
+
"eval_runtime": 126.6078,
|
83 |
+
"eval_samples_per_second": 36.491,
|
84 |
+
"eval_steps_per_second": 4.565,
|
85 |
+
"eval_wer": 1.0,
|
86 |
+
"step": 100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.32,
|
90 |
+
"learning_rate": 6.500748502994012e-05,
|
91 |
+
"loss": 3.14,
|
92 |
+
"step": 110
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.35,
|
96 |
+
"learning_rate": 6.388473053892215e-05,
|
97 |
+
"loss": 3.1281,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.38,
|
102 |
+
"learning_rate": 6.276197604790418e-05,
|
103 |
+
"loss": 3.0987,
|
104 |
+
"step": 130
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.41,
|
108 |
+
"learning_rate": 6.163922155688622e-05,
|
109 |
+
"loss": 3.1003,
|
110 |
+
"step": 140
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.44,
|
114 |
+
"learning_rate": 6.0516467065868256e-05,
|
115 |
+
"loss": 3.0922,
|
116 |
+
"step": 150
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.44,
|
120 |
+
"eval_loss": 3.127869129180908,
|
121 |
+
"eval_runtime": 126.3837,
|
122 |
+
"eval_samples_per_second": 36.555,
|
123 |
+
"eval_steps_per_second": 4.573,
|
124 |
+
"eval_wer": 1.0,
|
125 |
+
"step": 150
|
126 |
+
}
|
127 |
+
],
|
128 |
+
"max_steps": 688,
|
129 |
+
"num_train_epochs": 2,
|
130 |
+
"total_flos": 4.4091799296804864e+17,
|
131 |
+
"trial_name": null,
|
132 |
+
"trial_params": null
|
133 |
+
}
|
{checkpoint-5 β checkpoint-150}/training_args.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2991
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77806a16ec6ef209c8a5c1c085159a0bc8e45c23f2d143f2c13e01527f13b5b2
|
3 |
size 2991
|
checkpoint-5/trainer_state.json
DELETED
@@ -1,55 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.014503263234227702,
|
5 |
-
"global_step": 5,
|
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": 3.75e-06,
|
13 |
-
"loss": 13.605,
|
14 |
-
"step": 1
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.01,
|
18 |
-
"learning_rate": 7.5e-06,
|
19 |
-
"loss": 11.0063,
|
20 |
-
"step": 2
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.01,
|
24 |
-
"learning_rate": 1.1249999999999999e-05,
|
25 |
-
"loss": 11.6693,
|
26 |
-
"step": 3
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.01,
|
30 |
-
"learning_rate": 1.5e-05,
|
31 |
-
"loss": 13.432,
|
32 |
-
"step": 4
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.01,
|
36 |
-
"learning_rate": 1.875e-05,
|
37 |
-
"loss": 10.3458,
|
38 |
-
"step": 5
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.01,
|
42 |
-
"eval_loss": 15.09913444519043,
|
43 |
-
"eval_runtime": 139.8551,
|
44 |
-
"eval_samples_per_second": 33.034,
|
45 |
-
"eval_steps_per_second": 4.133,
|
46 |
-
"eval_wer": 1.0,
|
47 |
-
"step": 5
|
48 |
-
}
|
49 |
-
],
|
50 |
-
"max_steps": 10,
|
51 |
-
"num_train_epochs": 1,
|
52 |
-
"total_flos": 2.486436496625664e+16,
|
53 |
-
"trial_name": null,
|
54 |
-
"trial_params": null
|
55 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262075377
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386439db8a06ec7bb8279d96099b6db5fee78683933dd8e79efdb684fee3e2c0
|
3 |
size 1262075377
|