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 sha256:0b544fae9f9530f2d9e7d0eef64a70d936afbf0f4479904eeb8249fd42c3e5ea
|
| 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:b78218acb04319669f4cd4589629efa2e0f845bad4703764f504f4fc3f9d509c
|
| 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 sha256:1f67482a5793b69036e983f69a5235483ea09b22142da3bad20f7a650f186f6d
|
| 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": 4.272,
|
| 21 |
"eval_steps_per_second": 0.171,
|
| 22 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"logging_steps": 200,
|
| 26 |
"max_steps": 960,
|
| 27 |
"num_train_epochs": 16,
|
| 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": 6.666666666666667,
|
| 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": 4.272,
|
| 21 |
"eval_steps_per_second": 0.171,
|
| 22 |
"step": 200
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 6.67,
|
| 26 |
+
"learning_rate": 0.0002,
|
| 27 |
+
"loss": 0.0295,
|
| 28 |
+
"step": 400
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 6.67,
|
| 32 |
+
"eval_runtime": 23.4439,
|
| 33 |
+
"eval_samples_per_second": 4.266,
|
| 34 |
+
"eval_steps_per_second": 0.171,
|
| 35 |
+
"step": 400
|
| 36 |
}
|
| 37 |
],
|
| 38 |
"logging_steps": 200,
|
| 39 |
"max_steps": 960,
|
| 40 |
"num_train_epochs": 16,
|
| 41 |
"save_steps": 200,
|
| 42 |
+
"total_flos": 2.55949242630144e+17,
|
| 43 |
"trial_name": null,
|
| 44 |
"trial_params": null
|
| 45 |
}
|