Training in progress, step 331, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e0972e809f636f714cabaf7760abced4e8ac62b9b0d7d1e5af1957fd879d856
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37431220
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e62a3caea9d1213a790ce42d8942f8d073a999f93a21cc68ae51d4b4cda784
|
3 |
size 37431220
|
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 sha256:72ad2ac46faf761aed288b5b7843e4fc844c5885618fe90eebd496352649b23c
|
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": 0.
|
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,
|
@@ -2310,6 +2310,20 @@
|
|
2310 |
"learning_rate": 2.6515151515151516e-05,
|
2311 |
"loss": 1.2392,
|
2312 |
"step": 329
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2313 |
}
|
2314 |
],
|
2315 |
"logging_steps": 1,
|
@@ -2329,7 +2343,7 @@
|
|
2329 |
"attributes": {}
|
2330 |
}
|
2331 |
},
|
2332 |
-
"total_flos": 4.
|
2333 |
"train_batch_size": 4,
|
2334 |
"trial_name": null,
|
2335 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9080932784636488,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 331,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2310 |
"learning_rate": 2.6515151515151516e-05,
|
2311 |
"loss": 1.2392,
|
2312 |
"step": 329
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.9053497942386831,
|
2316 |
+
"grad_norm": 0.15157172083854675,
|
2317 |
+
"learning_rate": 2.575757575757576e-05,
|
2318 |
+
"loss": 1.1812,
|
2319 |
+
"step": 330
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.9080932784636488,
|
2323 |
+
"grad_norm": 0.1556706726551056,
|
2324 |
+
"learning_rate": 2.5e-05,
|
2325 |
+
"loss": 1.1528,
|
2326 |
+
"step": 331
|
2327 |
}
|
2328 |
],
|
2329 |
"logging_steps": 1,
|
|
|
2343 |
"attributes": {}
|
2344 |
}
|
2345 |
},
|
2346 |
+
"total_flos": 4.1040816234142925e+17,
|
2347 |
"train_batch_size": 4,
|
2348 |
"trial_name": null,
|
2349 |
"trial_params": null
|