Training in progress, step 1220, 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 sha256:39fbd7a3d6217c94b7db508500ab298991ed1850c4ac58e32c8a96f732136ff6
|
| 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 sha256:8eea18e47f62adb7b05b4d2a3824fe7fbc98177ef2305472377597fa898b7317
|
| 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 sha256:9e89a46997a07bfaa47acacf95ba9f700317474c2958a93fe66e1df02eb9d869
|
| 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:ffa732fe1546976a8e6a700cbfa883b43a4e2d20983bedfdae9fa8fc2fc85151
|
| 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,
|
|
@@ -1228,6 +1228,16 @@
|
|
| 1228 |
"mean_token_accuracy": 0.7372826255857945,
|
| 1229 |
"num_tokens": 5637868.0,
|
| 1230 |
"step": 1210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1231 |
}
|
| 1232 |
],
|
| 1233 |
"logging_steps": 10,
|
|
@@ -1247,7 +1257,7 @@
|
|
| 1247 |
"attributes": {}
|
| 1248 |
}
|
| 1249 |
},
|
| 1250 |
-
"total_flos": 2.
|
| 1251 |
"train_batch_size": 4,
|
| 1252 |
"trial_name": null,
|
| 1253 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.26026666666666665,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1228 |
"mean_token_accuracy": 0.7372826255857945,
|
| 1229 |
"num_tokens": 5637868.0,
|
| 1230 |
"step": 1210
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"entropy": 0.9640243485569954,
|
| 1234 |
+
"epoch": 0.26026666666666665,
|
| 1235 |
+
"grad_norm": 0.23221854865550995,
|
| 1236 |
+
"learning_rate": 9.749148625151908e-05,
|
| 1237 |
+
"loss": 1.0559998512268067,
|
| 1238 |
+
"mean_token_accuracy": 0.7624265968799591,
|
| 1239 |
+
"num_tokens": 5684479.0,
|
| 1240 |
+
"step": 1220
|
| 1241 |
}
|
| 1242 |
],
|
| 1243 |
"logging_steps": 10,
|
|
|
|
| 1257 |
"attributes": {}
|
| 1258 |
}
|
| 1259 |
},
|
| 1260 |
+
"total_flos": 2.693042849672909e+16,
|
| 1261 |
"train_batch_size": 4,
|
| 1262 |
"trial_name": null,
|
| 1263 |
"trial_params": null
|