Training in progress, step 4030, 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:c7649ebf4e521751470a2a9d0f01b459178546ed3b0a138105022cf9eb7831eb
|
| 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 sha256:35f442400a6f2ac0177ac43ec5bba10f446de9d0adc35ff495f595d62b69ec26
|
| 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 sha256:4cf75a8599600476a5a11fcc03283c749d3a00879be40513350917ef994ffdfc
|
| 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,
|
|
@@ -7244,6 +7244,24 @@
|
|
| 7244 |
"mean_token_accuracy": 0.6440500050783158,
|
| 7245 |
"num_tokens": 14661469.0,
|
| 7246 |
"step": 4020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7247 |
}
|
| 7248 |
],
|
| 7249 |
"logging_steps": 5,
|
|
@@ -7263,7 +7281,7 @@
|
|
| 7263 |
"attributes": {}
|
| 7264 |
}
|
| 7265 |
},
|
| 7266 |
-
"total_flos": 7.
|
| 7267 |
"train_batch_size": 4,
|
| 7268 |
"trial_name": null,
|
| 7269 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7244 |
"mean_token_accuracy": 0.6440500050783158,
|
| 7245 |
"num_tokens": 14661469.0,
|
| 7246 |
"step": 4020
|
| 7247 |
+
},
|
| 7248 |
+
{
|
| 7249 |
+
"epoch": 30.96153846153846,
|
| 7250 |
+
"grad_norm": 0.0,
|
| 7251 |
+
"learning_rate": 2.9880000000000002e-05,
|
| 7252 |
+
"loss": 1.7175,
|
| 7253 |
+
"mean_token_accuracy": 0.6576481223106384,
|
| 7254 |
+
"num_tokens": 14679555.0,
|
| 7255 |
+
"step": 4025
|
| 7256 |
+
},
|
| 7257 |
+
{
|
| 7258 |
+
"epoch": 31.0,
|
| 7259 |
+
"grad_norm": 0.0,
|
| 7260 |
+
"learning_rate": 2.9855e-05,
|
| 7261 |
+
"loss": 1.7706,
|
| 7262 |
+
"mean_token_accuracy": 0.6471602261066437,
|
| 7263 |
+
"num_tokens": 14697255.0,
|
| 7264 |
+
"step": 4030
|
| 7265 |
}
|
| 7266 |
],
|
| 7267 |
"logging_steps": 5,
|
|
|
|
| 7281 |
"attributes": {}
|
| 7282 |
}
|
| 7283 |
},
|
| 7284 |
+
"total_flos": 7.448121749436826e+17,
|
| 7285 |
"train_batch_size": 4,
|
| 7286 |
"trial_name": null,
|
| 7287 |
"trial_params": null
|