marinone94
commited on
Commit
β’
6e3915f
1
Parent(s):
149260c
Training in progress, step 400
Browse files- checkpoint-100/trainer_state.json +0 -55
- {checkpoint-100 β checkpoint-400}/config.json +0 -0
- {checkpoint-100 β checkpoint-400}/optimizer.pt +2 -2
- {checkpoint-100 β checkpoint-400}/preprocessor_config.json +0 -0
- {checkpoint-100 β checkpoint-400}/pytorch_model.bin +1 -1
- {checkpoint-100 β checkpoint-400}/rng_state.pth +2 -2
- {checkpoint-100 β checkpoint-400}/scaler.pt +1 -1
- {checkpoint-100 β checkpoint-400}/scheduler.pt +1 -1
- checkpoint-400/trainer_state.json +172 -0
- {checkpoint-100 β checkpoint-400}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
checkpoint-100/trainer_state.json
DELETED
@@ -1,55 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.098360655737705,
|
5 |
-
"global_step": 100,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.22,
|
12 |
-
"learning_rate": 2.5e-06,
|
13 |
-
"loss": 3.5867,
|
14 |
-
"step": 20
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.44,
|
18 |
-
"learning_rate": 5e-06,
|
19 |
-
"loss": 3.5457,
|
20 |
-
"step": 40
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.66,
|
24 |
-
"learning_rate": 7.5e-06,
|
25 |
-
"loss": 3.4513,
|
26 |
-
"step": 60
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.87,
|
30 |
-
"learning_rate": 1e-05,
|
31 |
-
"loss": 3.3432,
|
32 |
-
"step": 80
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 1.1,
|
36 |
-
"learning_rate": 1.25e-05,
|
37 |
-
"loss": 3.3533,
|
38 |
-
"step": 100
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 1.1,
|
42 |
-
"eval_loss": 3.2806732654571533,
|
43 |
-
"eval_runtime": 190.4728,
|
44 |
-
"eval_samples_per_second": 25.426,
|
45 |
-
"eval_steps_per_second": 0.798,
|
46 |
-
"eval_wer": 1.0,
|
47 |
-
"step": 100
|
48 |
-
}
|
49 |
-
],
|
50 |
-
"max_steps": 4550,
|
51 |
-
"num_train_epochs": 50,
|
52 |
-
"total_flos": 1.5920272455652972e+18,
|
53 |
-
"trial_name": null,
|
54 |
-
"trial_params": null
|
55 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{checkpoint-100 β checkpoint-400}/config.json
RENAMED
File without changes
|
{checkpoint-100 β checkpoint-400}/optimizer.pt
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:b573eee933c6c36bd4ddb6906221d3843d7e3e13dab0b96a39404d3a30f74898
|
3 |
+
size 2490337809
|
{checkpoint-100 β checkpoint-400}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-100 β checkpoint-400}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28c7e3ec36d37a20298023cfa6ac730ae02e82d170ef8859ec5740936e2bc809
|
3 |
size 1262063089
|
{checkpoint-100 β checkpoint-400}/rng_state.pth
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 sha256:855318e4e46176f35f66cfa7dbcef4ac9632248b73c3328855184518a3b76d7f
|
3 |
+
size 14503
|
{checkpoint-100 β checkpoint-400}/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 sha256:476e510c8ea7edbd2b51d1e76a4e037820a5639381c0d8b5d32dafa492795a1e
|
3 |
size 559
|
{checkpoint-100 β checkpoint-400}/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 sha256:8d06447f3e192636cdb71ae042312281cde114831b8524799c0556275e17d331
|
3 |
size 623
|
checkpoint-400/trainer_state.json
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.39344262295082,
|
5 |
+
"global_step": 400,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 2.5e-06,
|
13 |
+
"loss": 3.5867,
|
14 |
+
"step": 20
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.44,
|
18 |
+
"learning_rate": 5e-06,
|
19 |
+
"loss": 3.5457,
|
20 |
+
"step": 40
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.66,
|
24 |
+
"learning_rate": 7.5e-06,
|
25 |
+
"loss": 3.4513,
|
26 |
+
"step": 60
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.87,
|
30 |
+
"learning_rate": 1e-05,
|
31 |
+
"loss": 3.3432,
|
32 |
+
"step": 80
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.1,
|
36 |
+
"learning_rate": 1.25e-05,
|
37 |
+
"loss": 3.3533,
|
38 |
+
"step": 100
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.1,
|
42 |
+
"eval_loss": 3.2806732654571533,
|
43 |
+
"eval_runtime": 190.4728,
|
44 |
+
"eval_samples_per_second": 25.426,
|
45 |
+
"eval_steps_per_second": 0.798,
|
46 |
+
"eval_wer": 1.0,
|
47 |
+
"step": 100
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.32,
|
51 |
+
"learning_rate": 1.5e-05,
|
52 |
+
"loss": 3.2217,
|
53 |
+
"step": 120
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.54,
|
57 |
+
"learning_rate": 1.7500000000000002e-05,
|
58 |
+
"loss": 3.1765,
|
59 |
+
"step": 140
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.75,
|
63 |
+
"learning_rate": 2e-05,
|
64 |
+
"loss": 3.1408,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.97,
|
69 |
+
"learning_rate": 2.2499999999999998e-05,
|
70 |
+
"loss": 3.1165,
|
71 |
+
"step": 180
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 2.2,
|
75 |
+
"learning_rate": 2.5e-05,
|
76 |
+
"loss": 3.1709,
|
77 |
+
"step": 200
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 2.2,
|
81 |
+
"eval_loss": 3.1325438022613525,
|
82 |
+
"eval_runtime": 192.4978,
|
83 |
+
"eval_samples_per_second": 25.159,
|
84 |
+
"eval_steps_per_second": 0.79,
|
85 |
+
"eval_wer": 1.0,
|
86 |
+
"step": 200
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.42,
|
90 |
+
"learning_rate": 2.75e-05,
|
91 |
+
"loss": 3.079,
|
92 |
+
"step": 220
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.63,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 3.0677,
|
98 |
+
"step": 240
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.85,
|
102 |
+
"learning_rate": 3.2500000000000004e-05,
|
103 |
+
"loss": 3.0656,
|
104 |
+
"step": 260
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 3.08,
|
108 |
+
"learning_rate": 3.5000000000000004e-05,
|
109 |
+
"loss": 3.1463,
|
110 |
+
"step": 280
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 3.3,
|
114 |
+
"learning_rate": 3.75e-05,
|
115 |
+
"loss": 3.0573,
|
116 |
+
"step": 300
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.3,
|
120 |
+
"eval_loss": 3.0614514350891113,
|
121 |
+
"eval_runtime": 194.36,
|
122 |
+
"eval_samples_per_second": 24.918,
|
123 |
+
"eval_steps_per_second": 0.782,
|
124 |
+
"eval_wer": 1.0,
|
125 |
+
"step": 300
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.51,
|
129 |
+
"learning_rate": 4e-05,
|
130 |
+
"loss": 3.0511,
|
131 |
+
"step": 320
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.73,
|
135 |
+
"learning_rate": 4.25e-05,
|
136 |
+
"loss": 3.0358,
|
137 |
+
"step": 340
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 3.95,
|
141 |
+
"learning_rate": 4.4999999999999996e-05,
|
142 |
+
"loss": 3.0416,
|
143 |
+
"step": 360
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 4.17,
|
147 |
+
"learning_rate": 4.75e-05,
|
148 |
+
"loss": 3.1053,
|
149 |
+
"step": 380
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.39,
|
153 |
+
"learning_rate": 5e-05,
|
154 |
+
"loss": 3.0314,
|
155 |
+
"step": 400
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 4.39,
|
159 |
+
"eval_loss": 3.0990231037139893,
|
160 |
+
"eval_runtime": 198.3688,
|
161 |
+
"eval_samples_per_second": 24.414,
|
162 |
+
"eval_steps_per_second": 0.766,
|
163 |
+
"eval_wer": 1.0,
|
164 |
+
"step": 400
|
165 |
+
}
|
166 |
+
],
|
167 |
+
"max_steps": 4550,
|
168 |
+
"num_train_epochs": 50,
|
169 |
+
"total_flos": 6.222452805866187e+18,
|
170 |
+
"trial_name": null,
|
171 |
+
"trial_params": null
|
172 |
+
}
|
{checkpoint-100 β checkpoint-400}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28c7e3ec36d37a20298023cfa6ac730ae02e82d170ef8859ec5740936e2bc809
|
3 |
size 1262063089
|