Training in progress, step 4550, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4341df95e173f4cb0231fec392f79e9becb7b0cbbcd540a0807e11919821ddbb
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ce67d4186a6d58d965816da2e60f9723a3f01f28d87baf43e35f6aec6f3497
|
| 3 |
size 14709
|
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:ae31b4af5ad90f73228c2cc7baaa1dd88b92272f1a90b701e2631e60e1c226b0
|
| 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":
|
| 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,
|
|
@@ -8180,6 +8180,24 @@
|
|
| 8180 |
"mean_token_accuracy": 0.6472138792276383,
|
| 8181 |
"num_tokens": 16556927.0,
|
| 8182 |
"step": 4540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8183 |
}
|
| 8184 |
],
|
| 8185 |
"logging_steps": 5,
|
|
@@ -8199,7 +8217,7 @@
|
|
| 8199 |
"attributes": {}
|
| 8200 |
}
|
| 8201 |
},
|
| 8202 |
-
"total_flos": 8.
|
| 8203 |
"train_batch_size": 4,
|
| 8204 |
"trial_name": null,
|
| 8205 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8180 |
"mean_token_accuracy": 0.6472138792276383,
|
| 8181 |
"num_tokens": 16556927.0,
|
| 8182 |
"step": 4540
|
| 8183 |
+
},
|
| 8184 |
+
{
|
| 8185 |
+
"epoch": 34.96153846153846,
|
| 8186 |
+
"grad_norm": 0.0,
|
| 8187 |
+
"learning_rate": 2.728e-05,
|
| 8188 |
+
"loss": 1.7334,
|
| 8189 |
+
"mean_token_accuracy": 0.6492251008749008,
|
| 8190 |
+
"num_tokens": 16575521.0,
|
| 8191 |
+
"step": 4545
|
| 8192 |
+
},
|
| 8193 |
+
{
|
| 8194 |
+
"epoch": 35.0,
|
| 8195 |
+
"grad_norm": 0.0,
|
| 8196 |
+
"learning_rate": 2.7255000000000002e-05,
|
| 8197 |
+
"loss": 1.7436,
|
| 8198 |
+
"mean_token_accuracy": 0.6502075582742691,
|
| 8199 |
+
"num_tokens": 16593675.0,
|
| 8200 |
+
"step": 4550
|
| 8201 |
}
|
| 8202 |
],
|
| 8203 |
"logging_steps": 5,
|
|
|
|
| 8217 |
"attributes": {}
|
| 8218 |
}
|
| 8219 |
},
|
| 8220 |
+
"total_flos": 8.410282093073203e+17,
|
| 8221 |
"train_batch_size": 4,
|
| 8222 |
"trial_name": null,
|
| 8223 |
"trial_params": null
|