Training in progress, step 200, 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 40036040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aeb0f3d8cb0c6cceae8d176fd9910065808eddbe668ce02ad6c766324e549d0
|
| 3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 20523679
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54e811b66b611f8eee50a1a119da97017378e2cfbf18d8f07e2905fe71f5a8d7
|
| 3 |
size 20523679
|
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 sha256:0183662d0d1e1defb18d6a6722cff75be84082b51828aa0a11325f086e995eb6
|
| 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:d966f0842db2ea11a27285ca469b15da90babb80bd5bf4472e1f13256015639c
|
| 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": 1.76,
|
| 21 |
"eval_steps_per_second": 0.221,
|
| 22 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"logging_steps": 100,
|
| 26 |
"max_steps": 957,
|
| 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": 0.6269592476489029,
|
| 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": 1.76,
|
| 21 |
"eval_steps_per_second": 0.221,
|
| 22 |
"step": 100
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.63,
|
| 26 |
+
"learning_rate": 0.0002,
|
| 27 |
+
"loss": 0.6216,
|
| 28 |
+
"step": 200
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.63,
|
| 32 |
+
"eval_runtime": 512.8833,
|
| 33 |
+
"eval_samples_per_second": 1.755,
|
| 34 |
+
"eval_steps_per_second": 0.22,
|
| 35 |
+
"step": 200
|
| 36 |
}
|
| 37 |
],
|
| 38 |
"logging_steps": 100,
|
| 39 |
"max_steps": 957,
|
| 40 |
"num_train_epochs": 3,
|
| 41 |
"save_steps": 100,
|
| 42 |
+
"total_flos": 3.32202164355072e+16,
|
| 43 |
"trial_name": null,
|
| 44 |
"trial_params": null
|
| 45 |
}
|