Training in progress, step 4560, 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 sha256:625ea6e41f1685de98d3d701813bd4a6eca87872ab941607b6a324a5e51b2b2e
|
| 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:ce9e38fbfe981639758c4e4439821882f2e9d714842cac44ac572da6b3eed1fb
|
| 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:eafd5cfd72ffb3b5eff3adbf01c560f5ef242e9ca5917bbb522f085caf9c9917
|
| 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": 35.
|
| 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,
|
|
@@ -8198,6 +8198,24 @@
|
|
| 8198 |
"mean_token_accuracy": 0.6502075582742691,
|
| 8199 |
"num_tokens": 16593675.0,
|
| 8200 |
"step": 4550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8201 |
}
|
| 8202 |
],
|
| 8203 |
"logging_steps": 5,
|
|
@@ -8217,7 +8235,7 @@
|
|
| 8217 |
"attributes": {}
|
| 8218 |
}
|
| 8219 |
},
|
| 8220 |
-
"total_flos": 8.
|
| 8221 |
"train_batch_size": 4,
|
| 8222 |
"trial_name": null,
|
| 8223 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8198 |
"mean_token_accuracy": 0.6502075582742691,
|
| 8199 |
"num_tokens": 16593675.0,
|
| 8200 |
"step": 4550
|
| 8201 |
+
},
|
| 8202 |
+
{
|
| 8203 |
+
"epoch": 35.03846153846154,
|
| 8204 |
+
"grad_norm": 0.0,
|
| 8205 |
+
"learning_rate": 2.723e-05,
|
| 8206 |
+
"loss": 1.7475,
|
| 8207 |
+
"mean_token_accuracy": 0.6530224084854126,
|
| 8208 |
+
"num_tokens": 16612033.0,
|
| 8209 |
+
"step": 4555
|
| 8210 |
+
},
|
| 8211 |
+
{
|
| 8212 |
+
"epoch": 35.07692307692308,
|
| 8213 |
+
"grad_norm": 0.0,
|
| 8214 |
+
"learning_rate": 2.7205e-05,
|
| 8215 |
+
"loss": 1.7608,
|
| 8216 |
+
"mean_token_accuracy": 0.6467309683561325,
|
| 8217 |
+
"num_tokens": 16630046.0,
|
| 8218 |
+
"step": 4560
|
| 8219 |
}
|
| 8220 |
],
|
| 8221 |
"logging_steps": 5,
|
|
|
|
| 8235 |
"attributes": {}
|
| 8236 |
}
|
| 8237 |
},
|
| 8238 |
+
"total_flos": 8.429032322452685e+17,
|
| 8239 |
"train_batch_size": 4,
|
| 8240 |
"trial_name": null,
|
| 8241 |
"trial_params": null
|