Training in progress, step 100, 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:c6fe1d25b9de58bba0b0d0a67d42f89c6a8ce31451afe42a6bb5c94c35c3bd03
|
| 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 sha256:6fd1248bd067385a06d4ccbcad7e7b7d152eb8227cca4da36b3cbfd97353c003
|
| 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:f042a51cc0094a3c688025699ab1a7245e3b2f90a78397b5ad7b4754ae93b3dd
|
| 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,
|
|
@@ -170,6 +170,24 @@
|
|
| 170 |
"mean_token_accuracy": 0.6573584616184235,
|
| 171 |
"num_tokens": 328164.0,
|
| 172 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
}
|
| 174 |
],
|
| 175 |
"logging_steps": 5,
|
|
@@ -189,7 +207,7 @@
|
|
| 189 |
"attributes": {}
|
| 190 |
}
|
| 191 |
},
|
| 192 |
-
"total_flos": 1.
|
| 193 |
"train_batch_size": 4,
|
| 194 |
"trial_name": null,
|
| 195 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 170 |
"mean_token_accuracy": 0.6573584616184235,
|
| 171 |
"num_tokens": 328164.0,
|
| 172 |
"step": 90
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.7307692307692307,
|
| 176 |
+
"grad_norm": 0.0,
|
| 177 |
+
"learning_rate": 4.953e-05,
|
| 178 |
+
"loss": 1.7877,
|
| 179 |
+
"mean_token_accuracy": 0.636717626452446,
|
| 180 |
+
"num_tokens": 346359.0,
|
| 181 |
+
"step": 95
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7692307692307693,
|
| 185 |
+
"grad_norm": 0.0,
|
| 186 |
+
"learning_rate": 4.9505e-05,
|
| 187 |
+
"loss": 1.6851,
|
| 188 |
+
"mean_token_accuracy": 0.6630265355110169,
|
| 189 |
+
"num_tokens": 364985.0,
|
| 190 |
+
"step": 100
|
| 191 |
}
|
| 192 |
],
|
| 193 |
"logging_steps": 5,
|
|
|
|
| 207 |
"attributes": {}
|
| 208 |
}
|
| 209 |
},
|
| 210 |
+
"total_flos": 1.845442383003648e+16,
|
| 211 |
"train_batch_size": 4,
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|