Upload 12 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +32 -128
- training_args.bin +1 -1
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490594117
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5acf3b5453e7ae9cf209df888fb143d9f2da40adf070d6a3d025caa438f8739
|
3 |
size 2490594117
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262168365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71bda9f90725233cac8670bf36b60117f18383968a3933b4a0555a23b7c15279
|
3 |
size 1262168365
|
rng_state.pth
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:bb7602cd5e8794b2d59d7a8b65b5ec6bf6159ef05734d0ad6928196a70d07daf
|
3 |
+
size 14639
|
scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8cbeae9563088ca9bba5c5c22688b1f3ca3cf93bb99af3f85f8c6cc9cab6fa6
|
3 |
size 557
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6b46c84ae4fe317e348faba65da33d430fc6f16849dfa16b90ea095086de29d
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,163 +1,67 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 1.
|
12 |
-
"learning_rate":
|
13 |
-
"loss": 0.
|
14 |
"step": 150
|
15 |
},
|
16 |
{
|
17 |
-
"epoch":
|
18 |
-
"learning_rate":
|
19 |
-
"loss": 0.
|
20 |
"step": 300
|
21 |
},
|
22 |
{
|
23 |
-
"epoch":
|
24 |
-
"learning_rate":
|
25 |
-
"loss": 0.
|
26 |
"step": 450
|
27 |
},
|
28 |
{
|
29 |
-
"epoch":
|
30 |
-
"learning_rate":
|
31 |
-
"loss": 0.
|
32 |
"step": 600
|
33 |
},
|
34 |
{
|
35 |
-
"epoch":
|
36 |
-
"learning_rate":
|
37 |
-
"loss": 0.
|
38 |
"step": 750
|
39 |
},
|
40 |
{
|
41 |
-
"epoch":
|
42 |
-
"learning_rate":
|
43 |
-
"loss": 0.
|
44 |
"step": 900
|
45 |
},
|
46 |
{
|
47 |
-
"epoch":
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"eval_samples_per_second": 9.443,
|
51 |
-
"eval_steps_per_second": 1.18,
|
52 |
-
"eval_wer": 0.1666585139167441,
|
53 |
-
"step": 1000
|
54 |
-
},
|
55 |
-
{
|
56 |
-
"epoch": 9.21,
|
57 |
-
"learning_rate": 9.991674708307746e-06,
|
58 |
-
"loss": 0.0207,
|
59 |
"step": 1050
|
60 |
},
|
61 |
{
|
62 |
-
"epoch":
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
|
67 |
-
|
68 |
-
"
|
69 |
-
"learning_rate": 9.989042898499869e-06,
|
70 |
-
"loss": 0.0193,
|
71 |
-
"step": 1350
|
72 |
-
},
|
73 |
-
{
|
74 |
-
"epoch": 13.16,
|
75 |
-
"learning_rate": 9.98772699359593e-06,
|
76 |
-
"loss": 0.02,
|
77 |
-
"step": 1500
|
78 |
-
},
|
79 |
-
{
|
80 |
-
"epoch": 14.47,
|
81 |
-
"learning_rate": 9.986411088691991e-06,
|
82 |
-
"loss": 0.0191,
|
83 |
-
"step": 1650
|
84 |
-
},
|
85 |
-
{
|
86 |
-
"epoch": 15.79,
|
87 |
-
"learning_rate": 9.985095183788054e-06,
|
88 |
-
"loss": 0.0189,
|
89 |
-
"step": 1800
|
90 |
-
},
|
91 |
-
{
|
92 |
-
"epoch": 17.1,
|
93 |
-
"learning_rate": 9.983779278884114e-06,
|
94 |
-
"loss": 0.0185,
|
95 |
-
"step": 1950
|
96 |
-
},
|
97 |
-
{
|
98 |
-
"epoch": 17.54,
|
99 |
-
"eval_loss": 0.2301694005727768,
|
100 |
-
"eval_runtime": 231.0348,
|
101 |
-
"eval_samples_per_second": 17.66,
|
102 |
-
"eval_steps_per_second": 2.207,
|
103 |
-
"eval_wer": 0.16558235092696766,
|
104 |
-
"step": 2000
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 18.42,
|
108 |
-
"learning_rate": 9.982463373980174e-06,
|
109 |
-
"loss": 0.0184,
|
110 |
-
"step": 2100
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 19.73,
|
114 |
-
"learning_rate": 9.981147469076235e-06,
|
115 |
-
"loss": 0.0186,
|
116 |
-
"step": 2250
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 21.05,
|
120 |
-
"learning_rate": 9.979831564172297e-06,
|
121 |
-
"loss": 0.0174,
|
122 |
-
"step": 2400
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 22.37,
|
126 |
-
"learning_rate": 9.978515659268357e-06,
|
127 |
-
"loss": 0.0175,
|
128 |
-
"step": 2550
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 23.68,
|
132 |
-
"learning_rate": 9.977199754364418e-06,
|
133 |
-
"loss": 0.0169,
|
134 |
-
"step": 2700
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 25.0,
|
138 |
-
"learning_rate": 9.97588384946048e-06,
|
139 |
-
"loss": 0.0174,
|
140 |
-
"step": 2850
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 26.31,
|
144 |
-
"learning_rate": 9.974567944556542e-06,
|
145 |
-
"loss": 0.0175,
|
146 |
-
"step": 3000
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 26.31,
|
150 |
-
"eval_loss": 0.23709918558597565,
|
151 |
-
"eval_runtime": 224.4917,
|
152 |
-
"eval_samples_per_second": 18.174,
|
153 |
-
"eval_steps_per_second": 2.272,
|
154 |
-
"eval_wer": 0.16504426943207945,
|
155 |
-
"step": 3000
|
156 |
}
|
157 |
],
|
158 |
-
"max_steps":
|
159 |
"num_train_epochs": 10000,
|
160 |
-
"total_flos":
|
161 |
"trial_name": null,
|
162 |
"trial_params": null
|
163 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 12.087431693989071,
|
5 |
+
"global_step": 1100,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 1.64,
|
12 |
+
"learning_rate": 4.999725244532367e-06,
|
13 |
+
"loss": 0.0243,
|
14 |
"step": 150
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 3.3,
|
18 |
+
"learning_rate": 4.998900978129465e-06,
|
19 |
+
"loss": 0.0192,
|
20 |
"step": 300
|
21 |
},
|
22 |
{
|
23 |
+
"epoch": 4.94,
|
24 |
+
"learning_rate": 4.998076711726564e-06,
|
25 |
+
"loss": 0.0175,
|
26 |
"step": 450
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 6.59,
|
30 |
+
"learning_rate": 4.997252445323663e-06,
|
31 |
+
"loss": 0.0174,
|
32 |
"step": 600
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 8.24,
|
36 |
+
"learning_rate": 4.996428178920761e-06,
|
37 |
+
"loss": 0.0168,
|
38 |
"step": 750
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 9.89,
|
42 |
+
"learning_rate": 4.995609407627212e-06,
|
43 |
+
"loss": 0.0175,
|
44 |
"step": 900
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 11.54,
|
48 |
+
"learning_rate": 4.994785141224311e-06,
|
49 |
+
"loss": 0.0168,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
"step": 1050
|
51 |
},
|
52 |
{
|
53 |
+
"epoch": 12.09,
|
54 |
+
"eval_loss": 0.23020002245903015,
|
55 |
+
"eval_runtime": 433.719,
|
56 |
+
"eval_samples_per_second": 9.407,
|
57 |
+
"eval_steps_per_second": 1.176,
|
58 |
+
"eval_wer": 0.16092909535452324,
|
59 |
+
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
}
|
61 |
],
|
62 |
+
"max_steps": 910000,
|
63 |
"num_train_epochs": 10000,
|
64 |
+
"total_flos": 3.930570221142893e+19,
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3323
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac89f9984dd853509f158f5c63d67654b0bc1d76d097b923ea0fef638f790ce5
|
3 |
size 3323
|