Training in progress, step 400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a7fdb8442a604865a0b0e8689682e644cb3ad92aea98f1b6cdc6307a1a19578
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350da4ab15783f58b2cf4eb2e0684bdb075f66bfdf2a2159831b6e8f2e59b81b
|
3 |
+
size 126034975
|
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:cc0d8e73218d0fdeddd71b139983fa8b6366ec00acef921d2abf70ced2eebd05
|
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 sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
|
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":
|
5 |
"eval_steps": 200,
|
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": 7.938,
|
21 |
"eval_steps_per_second": 0.505,
|
22 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
24 |
],
|
25 |
"logging_steps": 200,
|
26 |
"max_steps": 2472,
|
27 |
"num_train_epochs": 12,
|
28 |
"save_steps": 200,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.941747572815534,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
20 |
"eval_samples_per_second": 7.938,
|
21 |
"eval_steps_per_second": 0.505,
|
22 |
"step": 200
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 1.94,
|
26 |
+
"learning_rate": 0.0002,
|
27 |
+
"loss": 0.0814,
|
28 |
+
"step": 400
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 1.94,
|
32 |
+
"eval_runtime": 21.8179,
|
33 |
+
"eval_samples_per_second": 7.929,
|
34 |
+
"eval_steps_per_second": 0.504,
|
35 |
+
"step": 400
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 200,
|
39 |
"max_steps": 2472,
|
40 |
"num_train_epochs": 12,
|
41 |
"save_steps": 200,
|
42 |
+
"total_flos": 1.289636996186112e+17,
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|