Training in progress, step 3300, 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:d6545aa59c2e8249336814c84ef6307b82552bb94db1efe3538137313ca2a68a
|
| 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 sha256:6510685423e6534059c860922b011651dd0160834fd9204be792668d526bab05
|
| 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:b3c205f1948eaa0aa75397dca50c45cf5715a062b1668abe236ca1432b22ee24
|
| 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:a9da6cd39d60ae09f7827127a83d38c34fd58cd18d7594965ff37b5036d511fd
|
| 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": 6.
|
| 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,
|
|
@@ -279,6 +279,13 @@
|
|
| 279 |
"learning_rate": 7.866666666666666e-05,
|
| 280 |
"loss": 1.2743,
|
| 281 |
"step": 3200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 282 |
}
|
| 283 |
],
|
| 284 |
"logging_steps": 100,
|
|
@@ -298,7 +305,7 @@
|
|
| 298 |
"attributes": {}
|
| 299 |
}
|
| 300 |
},
|
| 301 |
-
"total_flos":
|
| 302 |
"train_batch_size": 8,
|
| 303 |
"trial_name": null,
|
| 304 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.598968911107639,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 279 |
"learning_rate": 7.866666666666666e-05,
|
| 280 |
"loss": 1.2743,
|
| 281 |
"step": 3200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.598968911107639,
|
| 285 |
+
"grad_norm": 0.16894273459911346,
|
| 286 |
+
"learning_rate": 7.800000000000001e-05,
|
| 287 |
+
"loss": 1.2662,
|
| 288 |
+
"step": 3300
|
| 289 |
}
|
| 290 |
],
|
| 291 |
"logging_steps": 100,
|
|
|
|
| 305 |
"attributes": {}
|
| 306 |
}
|
| 307 |
},
|
| 308 |
+
"total_flos": 5.150419107987849e+18,
|
| 309 |
"train_batch_size": 8,
|
| 310 |
"trial_name": null,
|
| 311 |
"trial_params": null
|