meet-dagur4
commited on
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +33 -3
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -22,6 +22,36 @@
|
|
22 |
"eval_samples_per_second": 9.651,
|
23 |
"eval_steps_per_second": 1.608,
|
24 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 25,
|
@@ -41,7 +71,7 @@
|
|
41 |
"attributes": {}
|
42 |
}
|
43 |
},
|
44 |
-
"total_flos":
|
45 |
"train_batch_size": 1,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.25,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 75,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
22 |
"eval_samples_per_second": 9.651,
|
23 |
"eval_steps_per_second": 1.608,
|
24 |
"step": 25
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 4.166666666666667,
|
28 |
+
"grad_norm": 0.3806462287902832,
|
29 |
+
"learning_rate": 0.00010101010101010102,
|
30 |
+
"loss": 1.0128,
|
31 |
+
"step": 50
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 4.166666666666667,
|
35 |
+
"eval_loss": 0.8326404094696045,
|
36 |
+
"eval_runtime": 1.129,
|
37 |
+
"eval_samples_per_second": 10.629,
|
38 |
+
"eval_steps_per_second": 1.772,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.25,
|
43 |
+
"grad_norm": 0.427622526884079,
|
44 |
+
"learning_rate": 5.050505050505051e-05,
|
45 |
+
"loss": 0.733,
|
46 |
+
"step": 75
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 6.25,
|
50 |
+
"eval_loss": 0.7211847901344299,
|
51 |
+
"eval_runtime": 1.1314,
|
52 |
+
"eval_samples_per_second": 10.606,
|
53 |
+
"eval_steps_per_second": 1.768,
|
54 |
+
"step": 75
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 25,
|
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
+
"total_flos": 197741133926400.0,
|
75 |
"train_batch_size": 1,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|