Training in progress, step 1250, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5616f477fd639cdf29ad5c7d118b3e915d2b27f07c4d208cd0ace5cd3bf5bc01
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d948c44a079a96a9a9cdaeebea3b3583d465b51a14ea5d12d7942da62b9778c
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:280a4a0a7e9600df169eef0cfd95b920be72c06632c470a2a48e52ec9a82f22f
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de4e95e7c05aac68a45971509c4b26f22299fdf966b12971000c0752608308db
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1258,6 +1258,16 @@
|
|
| 1258 |
"mean_token_accuracy": 0.7489309534430504,
|
| 1259 |
"num_tokens": 5776891.0,
|
| 1260 |
"step": 1240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1261 |
}
|
| 1262 |
],
|
| 1263 |
"logging_steps": 10,
|
|
@@ -1277,7 +1287,7 @@
|
|
| 1277 |
"attributes": {}
|
| 1278 |
}
|
| 1279 |
},
|
| 1280 |
-
"total_flos": 2.
|
| 1281 |
"train_batch_size": 4,
|
| 1282 |
"trial_name": null,
|
| 1283 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.26666666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1258 |
"mean_token_accuracy": 0.7489309534430504,
|
| 1259 |
"num_tokens": 5776891.0,
|
| 1260 |
"step": 1240
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"entropy": 0.9446908816695213,
|
| 1264 |
+
"epoch": 0.26666666666666666,
|
| 1265 |
+
"grad_norm": 0.2996140718460083,
|
| 1266 |
+
"learning_rate": 9.732653526357612e-05,
|
| 1267 |
+
"loss": 1.0297443389892578,
|
| 1268 |
+
"mean_token_accuracy": 0.7673991709947586,
|
| 1269 |
+
"num_tokens": 5817721.0,
|
| 1270 |
+
"step": 1250
|
| 1271 |
}
|
| 1272 |
],
|
| 1273 |
"logging_steps": 10,
|
|
|
|
| 1287 |
"attributes": {}
|
| 1288 |
}
|
| 1289 |
},
|
| 1290 |
+
"total_flos": 2.7567098994668544e+16,
|
| 1291 |
"train_batch_size": 4,
|
| 1292 |
"trial_name": null,
|
| 1293 |
"trial_params": null
|