Training in progress, step 320, 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:edf7198e8267b3b317d0bfa661e56918b0c602cad0ec4839218b000026dbad83
|
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:c99190bdd777fac27de12589cab5455d8c58569f98b515d3c0aeb3e4773b25a8
|
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:bb2d3a921ff2f34dee8d1e2a44b6c868c4f52dd0a9e88a06d804a47ee81494b4
|
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,
|
@@ -2240,6 +2240,13 @@
|
|
2240 |
"learning_rate": 3.409090909090909e-05,
|
2241 |
"loss": 1.2463,
|
2242 |
"step": 319
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2243 |
}
|
2244 |
],
|
2245 |
"logging_steps": 1,
|
@@ -2259,7 +2266,7 @@
|
|
2259 |
"attributes": {}
|
2260 |
}
|
2261 |
},
|
2262 |
-
"total_flos": 3.
|
2263 |
"train_batch_size": 4,
|
2264 |
"trial_name": null,
|
2265 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.877914951989026,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 320,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2240 |
"learning_rate": 3.409090909090909e-05,
|
2241 |
"loss": 1.2463,
|
2242 |
"step": 319
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.877914951989026,
|
2246 |
+
"grad_norm": 0.1728198379278183,
|
2247 |
+
"learning_rate": 3.3333333333333335e-05,
|
2248 |
+
"loss": 1.1552,
|
2249 |
+
"step": 320
|
2250 |
}
|
2251 |
],
|
2252 |
"logging_steps": 1,
|
|
|
2266 |
"attributes": {}
|
2267 |
}
|
2268 |
},
|
2269 |
+
"total_flos": 3.9666723522411725e+17,
|
2270 |
"train_batch_size": 4,
|
2271 |
"trial_name": null,
|
2272 |
"trial_params": null
|