mariovigliar
commited on
Commit
•
74df9de
1
Parent(s):
b8b139a
All Dunn!!!
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +66 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_cer": 0.034291666666666665,
|
4 |
+
"eval_loss": 0.1479392945766449,
|
5 |
+
"eval_runtime": 299.3948,
|
6 |
+
"eval_samples_per_second": 13.36,
|
7 |
+
"eval_steps_per_second": 0.418,
|
8 |
+
"total_flos": 2.3945126111870976e+19,
|
9 |
+
"train_loss": 0.26610363578796387,
|
10 |
+
"train_runtime": 1667.9703,
|
11 |
+
"train_samples_per_second": 19.185,
|
12 |
+
"train_steps_per_second": 0.6
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_cer": 0.034291666666666665,
|
4 |
+
"eval_loss": 0.1479392945766449,
|
5 |
+
"eval_runtime": 299.3948,
|
6 |
+
"eval_samples_per_second": 13.36,
|
7 |
+
"eval_steps_per_second": 0.418
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 2.3945126111870976e+19,
|
4 |
+
"train_loss": 0.26610363578796387,
|
5 |
+
"train_runtime": 1667.9703,
|
6 |
+
"train_samples_per_second": 19.185,
|
7 |
+
"train_steps_per_second": 0.6
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.995e-05,
|
14 |
+
"loss": 10.5576,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"learning_rate": 2.5e-05,
|
20 |
+
"loss": 0.356,
|
21 |
+
"step": 500
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.0,
|
25 |
+
"eval_cer": 0.041,
|
26 |
+
"eval_loss": 0.1933690458536148,
|
27 |
+
"eval_runtime": 295.9636,
|
28 |
+
"eval_samples_per_second": 13.515,
|
29 |
+
"eval_steps_per_second": 0.422,
|
30 |
+
"step": 500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"learning_rate": 0.0,
|
35 |
+
"loss": 0.1558,
|
36 |
+
"step": 1000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_cer": 0.034291666666666665,
|
41 |
+
"eval_loss": 0.1479392945766449,
|
42 |
+
"eval_runtime": 296.9645,
|
43 |
+
"eval_samples_per_second": 13.47,
|
44 |
+
"eval_steps_per_second": 0.421,
|
45 |
+
"step": 1000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.0,
|
49 |
+
"step": 1000,
|
50 |
+
"total_flos": 2.3945126111870976e+19,
|
51 |
+
"train_loss": 0.26610363578796387,
|
52 |
+
"train_runtime": 1667.9703,
|
53 |
+
"train_samples_per_second": 19.185,
|
54 |
+
"train_steps_per_second": 0.6
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 1000,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 2,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 2.3945126111870976e+19,
|
63 |
+
"train_batch_size": 32,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": null
|
66 |
+
}
|