Training in progress, step 1240, 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:ee78fbe3e1e0371fbd7e1d99cd209484a0864e5963e372d87bd75f8e957f8b0d
|
| 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 sha256:06beec4deae6ef65f2b37fdb301344580a5bc16b9931d6b1472ea6a07666ab85
|
| 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 sha256:986528bb1512d6f9428bb2e2b1ae3f65e21747eeffc9b252ab651061033a2945
|
| 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:c2912d9609fc2e0e0f874bc4a1c28fd4eb9c7ad4cf18690751be68d4c9f99c05
|
| 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,
|
|
@@ -1248,6 +1248,16 @@
|
|
| 1248 |
"mean_token_accuracy": 0.7580445930361748,
|
| 1249 |
"num_tokens": 5726626.0,
|
| 1250 |
"step": 1230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1251 |
}
|
| 1252 |
],
|
| 1253 |
"logging_steps": 10,
|
|
@@ -1267,7 +1277,7 @@
|
|
| 1267 |
"attributes": {}
|
| 1268 |
}
|
| 1269 |
},
|
| 1270 |
-
"total_flos": 2.
|
| 1271 |
"train_batch_size": 4,
|
| 1272 |
"trial_name": null,
|
| 1273 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.26453333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1248 |
"mean_token_accuracy": 0.7580445930361748,
|
| 1249 |
"num_tokens": 5726626.0,
|
| 1250 |
"step": 1230
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"entropy": 1.0462738864123822,
|
| 1254 |
+
"epoch": 0.26453333333333334,
|
| 1255 |
+
"grad_norm": 0.21800817549228668,
|
| 1256 |
+
"learning_rate": 9.738208685317611e-05,
|
| 1257 |
+
"loss": 1.172841453552246,
|
| 1258 |
+
"mean_token_accuracy": 0.7489309534430504,
|
| 1259 |
+
"num_tokens": 5776891.0,
|
| 1260 |
+
"step": 1240
|
| 1261 |
}
|
| 1262 |
],
|
| 1263 |
"logging_steps": 10,
|
|
|
|
| 1277 |
"attributes": {}
|
| 1278 |
}
|
| 1279 |
},
|
| 1280 |
+
"total_flos": 2.73719740141824e+16,
|
| 1281 |
"train_batch_size": 4,
|
| 1282 |
"trial_name": null,
|
| 1283 |
"trial_params": null
|