Training in progress, step 180, 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:dc52676e0ff0e10106359b0cc72bd9b2243385897047097e7930b77e9085d3bc
|
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 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:526558c8dda43a4a5e2f3c62cc3129ba9d6c50d57d27bd647e10d4609230cabf
|
3 |
size 37430836
|
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 sha256:42efa5ba52feb76fc1897ce2307dd38af4712e51a9c31c20c2f24c914af80473
|
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,
|
@@ -1260,6 +1260,13 @@
|
|
1260 |
"learning_rate": 0.00014015151515151518,
|
1261 |
"loss": 1.2584,
|
1262 |
"step": 179
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1263 |
}
|
1264 |
],
|
1265 |
"logging_steps": 1,
|
@@ -1279,7 +1286,7 @@
|
|
1279 |
"attributes": {}
|
1280 |
}
|
1281 |
},
|
1282 |
-
"total_flos": 2.
|
1283 |
"train_batch_size": 4,
|
1284 |
"trial_name": null,
|
1285 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.49382716049382713,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 180,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1260 |
"learning_rate": 0.00014015151515151518,
|
1261 |
"loss": 1.2584,
|
1262 |
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.49382716049382713,
|
1266 |
+
"grad_norm": 0.153547003865242,
|
1267 |
+
"learning_rate": 0.0001393939393939394,
|
1268 |
+
"loss": 1.1958,
|
1269 |
+
"step": 180
|
1270 |
}
|
1271 |
],
|
1272 |
"logging_steps": 1,
|
|
|
1286 |
"attributes": {}
|
1287 |
}
|
1288 |
},
|
1289 |
+
"total_flos": 2.2346819156282573e+17,
|
1290 |
"train_batch_size": 4,
|
1291 |
"trial_name": null,
|
1292 |
"trial_params": null
|