Upload trainer_state.json
Browse files- trainer_state.json +58 -0
trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 3570,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 3.7037037037037037e-05,
|
13 |
+
"loss": 3.3017,
|
14 |
+
"step": 1190
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.5758862495422363,
|
19 |
+
"eval_runtime": 19.298,
|
20 |
+
"eval_samples_per_second": 98.559,
|
21 |
+
"eval_steps_per_second": 1.036,
|
22 |
+
"step": 1190
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 1.8518518518518518e-05,
|
27 |
+
"loss": 2.3813,
|
28 |
+
"step": 2380
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 2.15813946723938,
|
33 |
+
"eval_runtime": 2.3483,
|
34 |
+
"eval_samples_per_second": 809.952,
|
35 |
+
"eval_steps_per_second": 8.517,
|
36 |
+
"step": 2380
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 0.0,
|
41 |
+
"loss": 2.0668,
|
42 |
+
"step": 3570
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 2.0412185192108154,
|
47 |
+
"eval_runtime": 2.4452,
|
48 |
+
"eval_samples_per_second": 777.841,
|
49 |
+
"eval_steps_per_second": 8.179,
|
50 |
+
"step": 3570
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"max_steps": 3570,
|
54 |
+
"num_train_epochs": 3,
|
55 |
+
"total_flos": 6990766248960000.0,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|