Training in progress, step 7890, 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:d6bf8fe40ca04e9aab58143017596d9eb09fabd9ec3fd03bf491fb4a62750f03
|
| 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:d8c0c121dd64fc0b57efd7bbbe7593106a9074cbdcadeed08f607dbc49feec84
|
| 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 sha256:5493d32fcfcdd22e1b2e878798505302f3dfb5e4f2b56a961393cbc21dcb80b3
|
| 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": 60.
|
| 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,
|
|
@@ -14192,6 +14192,24 @@
|
|
| 14192 |
"mean_token_accuracy": 0.6454852074384689,
|
| 14193 |
"num_tokens": 28738693.0,
|
| 14194 |
"step": 7880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14195 |
}
|
| 14196 |
],
|
| 14197 |
"logging_steps": 5,
|
|
@@ -14211,7 +14229,7 @@
|
|
| 14211 |
"attributes": {}
|
| 14212 |
}
|
| 14213 |
},
|
| 14214 |
-
"total_flos": 1.
|
| 14215 |
"train_batch_size": 4,
|
| 14216 |
"trial_name": null,
|
| 14217 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14192 |
"mean_token_accuracy": 0.6454852074384689,
|
| 14193 |
"num_tokens": 28738693.0,
|
| 14194 |
"step": 7880
|
| 14195 |
+
},
|
| 14196 |
+
{
|
| 14197 |
+
"epoch": 60.65384615384615,
|
| 14198 |
+
"grad_norm": 0.0,
|
| 14199 |
+
"learning_rate": 1.058e-05,
|
| 14200 |
+
"loss": 1.7185,
|
| 14201 |
+
"mean_token_accuracy": 0.6532977163791657,
|
| 14202 |
+
"num_tokens": 28757044.0,
|
| 14203 |
+
"step": 7885
|
| 14204 |
+
},
|
| 14205 |
+
{
|
| 14206 |
+
"epoch": 60.69230769230769,
|
| 14207 |
+
"grad_norm": 0.0,
|
| 14208 |
+
"learning_rate": 1.0555000000000001e-05,
|
| 14209 |
+
"loss": 1.749,
|
| 14210 |
+
"mean_token_accuracy": 0.651301595568657,
|
| 14211 |
+
"num_tokens": 28775068.0,
|
| 14212 |
+
"step": 7890
|
| 14213 |
}
|
| 14214 |
],
|
| 14215 |
"logging_steps": 5,
|
|
|
|
| 14229 |
"attributes": {}
|
| 14230 |
}
|
| 14231 |
},
|
| 14232 |
+
"total_flos": 1.4590647627271373e+18,
|
| 14233 |
"train_batch_size": 4,
|
| 14234 |
"trial_name": null,
|
| 14235 |
"trial_params": null
|