Training in progress, step 750, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 265470032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ea3d1fee0cf94f18c76aded546bd00636402c5d3d8873ce1df5f560490a2ae
|
3 |
size 265470032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 531000890
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c57f2a2e0d84885a37b25be92d6eb3a16854b88a05cf9befca36265f955848a7
|
3 |
size 531000890
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:950da3e90ce3ce1c506179b66ccc7e74355553896596d9d1885bfe0bd3b8375e
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab03192a60c4fb6ec6096a859424dfb24171c6b3fc801b38b85ab0fd723b1704
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -22,6 +22,14 @@
|
|
22 |
"learning_rate": 6.666666666666667e-05,
|
23 |
"loss": 1.8909,
|
24 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 500,
|
@@ -36,12 +44,12 @@
|
|
36 |
"should_evaluate": false,
|
37 |
"should_log": false,
|
38 |
"should_save": true,
|
39 |
-
"should_training_stop":
|
40 |
},
|
41 |
"attributes": {}
|
42 |
}
|
43 |
},
|
44 |
-
"total_flos":
|
45 |
"train_batch_size": 16,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 750,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
22 |
"learning_rate": 6.666666666666667e-05,
|
23 |
"loss": 1.8909,
|
24 |
"step": 500
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"eval_loss": 1.6887657642364502,
|
29 |
+
"eval_runtime": 11.4017,
|
30 |
+
"eval_samples_per_second": 87.706,
|
31 |
+
"eval_steps_per_second": 5.526,
|
32 |
+
"step": 500
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 500,
|
|
|
44 |
"should_evaluate": false,
|
45 |
"should_log": false,
|
46 |
"should_save": true,
|
47 |
+
"should_training_stop": true
|
48 |
},
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
+
"total_flos": 1175877900288000.0,
|
53 |
"train_batch_size": 16,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|