Training in progress, step 11600, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f412f5a0abe9bd62436dbbedb5cea724fb811d69ed956353b8a8c87ba782efe
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a4487a523534f889396375b7800dd86fdab486e819b71d6c297a6f9e10831c
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8d6fa075ec821303dbc65767acb716ac0521336d7793ec40f936c89d6c91b7b
|
| 3 |
size 15006
|
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:bfaba695d709aff29feada9169cc46e562a18b1b50ef57a8f6e6edc4175c9192
|
| 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,
|
|
@@ -996,6 +996,13 @@
|
|
| 996 |
"eval_samples_per_second": 19.902,
|
| 997 |
"eval_steps_per_second": 2.489,
|
| 998 |
"step": 11500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 999 |
}
|
| 1000 |
],
|
| 1001 |
"logging_steps": 100,
|
|
@@ -1015,7 +1022,7 @@
|
|
| 1015 |
"attributes": {}
|
| 1016 |
}
|
| 1017 |
},
|
| 1018 |
-
"total_flos": 1.
|
| 1019 |
"train_batch_size": 8,
|
| 1020 |
"trial_name": null,
|
| 1021 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 23.196375566317762,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 996 |
"eval_samples_per_second": 19.902,
|
| 997 |
"eval_steps_per_second": 2.489,
|
| 998 |
"step": 11500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 23.196375566317762,
|
| 1002 |
+
"grad_norm": 0.2390895038843155,
|
| 1003 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 1004 |
+
"loss": 1.224,
|
| 1005 |
+
"step": 11600
|
| 1006 |
}
|
| 1007 |
],
|
| 1008 |
"logging_steps": 100,
|
|
|
|
| 1022 |
"attributes": {}
|
| 1023 |
}
|
| 1024 |
},
|
| 1025 |
+
"total_flos": 1.8104486049811005e+19,
|
| 1026 |
"train_batch_size": 8,
|
| 1027 |
"trial_name": null,
|
| 1028 |
"trial_params": null
|