Training in progress, step 200, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05c968488c791ec048ca50fe94b28e4af2ac5434b8a4bdde4b076f549b715a06
|
3 |
size 160285149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42764f328df0c11e665a3d1f1a28175b6cf44a65517dfb8430cf18864c4fb5f5
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:054d52bab859a6d48721e83cd6abdf3a605011904b735d5df023417b14dbfa7b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -20,13 +20,26 @@
|
|
20 |
"eval_samples_per_second": 1.903,
|
21 |
"eval_steps_per_second": 0.239,
|
22 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
"logging_steps": 100,
|
26 |
"max_steps": 2025,
|
27 |
"num_train_epochs": 3,
|
28 |
"save_steps": 100,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2962962962962963,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
20 |
"eval_samples_per_second": 1.903,
|
21 |
"eval_steps_per_second": 0.239,
|
22 |
"step": 100
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.3,
|
26 |
+
"learning_rate": 0.0,
|
27 |
+
"loss": 8.4542,
|
28 |
+
"step": 200
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.3,
|
32 |
+
"eval_runtime": 788.181,
|
33 |
+
"eval_samples_per_second": 1.903,
|
34 |
+
"eval_steps_per_second": 0.239,
|
35 |
+
"step": 200
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 100,
|
39 |
"max_steps": 2025,
|
40 |
"num_train_epochs": 3,
|
41 |
"save_steps": 100,
|
42 |
+
"total_flos": 4.1648079765504e+16,
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|