Training in progress, step 3400, 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:d205a10ec746a2e621f265219dffa86a02638edbf5ec5a1fc74c7ff8891fb23d
|
| 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:ff8e69d6b3e91fe72610a7572602e11de1cb107ec8f2a123491d5e62d0998954
|
| 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:f848050763f228c45f41876f788201e463cbdcc748427dc62e8abf982f465e5e
|
| 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:a1ac3ef405adcd631e67f3a0c40ddc7e7d705d69b4fbe06bc5a1701aae09096a
|
| 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,
|
|
@@ -286,6 +286,13 @@
|
|
| 286 |
"learning_rate": 7.800000000000001e-05,
|
| 287 |
"loss": 1.2662,
|
| 288 |
"step": 3300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 289 |
}
|
| 290 |
],
|
| 291 |
"logging_steps": 100,
|
|
@@ -305,7 +312,7 @@
|
|
| 305 |
"attributes": {}
|
| 306 |
}
|
| 307 |
},
|
| 308 |
-
"total_flos": 5.
|
| 309 |
"train_batch_size": 8,
|
| 310 |
"trial_name": null,
|
| 311 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.798937665989689,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 286 |
"learning_rate": 7.800000000000001e-05,
|
| 287 |
"loss": 1.2662,
|
| 288 |
"step": 3300
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.798937665989689,
|
| 292 |
+
"grad_norm": 0.1722390055656433,
|
| 293 |
+
"learning_rate": 7.733333333333333e-05,
|
| 294 |
+
"loss": 1.2685,
|
| 295 |
+
"step": 3400
|
| 296 |
}
|
| 297 |
],
|
| 298 |
"logging_steps": 100,
|
|
|
|
| 312 |
"attributes": {}
|
| 313 |
}
|
| 314 |
},
|
| 315 |
+
"total_flos": 5.306494079176016e+18,
|
| 316 |
"train_batch_size": 8,
|
| 317 |
"trial_name": null,
|
| 318 |
"trial_params": null
|