Training in progress, step 8450, 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:d294b0639c74c69de9c053a5accb601408eb158a18edf3df8ea3ab80e40542c5
|
| 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:d670543f77af913058fbc1f16d1662dabc7d1157c5c273eb3927124558fee677
|
| 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:dbea37f9418917c7712a57c734e3dc54715eba6abb693b9f754c896de685d555
|
| 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,
|
|
@@ -15200,6 +15200,24 @@
|
|
| 15200 |
"mean_token_accuracy": 0.6393702328205109,
|
| 15201 |
"num_tokens": 30779931.0,
|
| 15202 |
"step": 8440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15203 |
}
|
| 15204 |
],
|
| 15205 |
"logging_steps": 5,
|
|
@@ -15219,7 +15237,7 @@
|
|
| 15219 |
"attributes": {}
|
| 15220 |
}
|
| 15221 |
},
|
| 15222 |
-
"total_flos": 1.
|
| 15223 |
"train_batch_size": 4,
|
| 15224 |
"trial_name": null,
|
| 15225 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15200 |
"mean_token_accuracy": 0.6393702328205109,
|
| 15201 |
"num_tokens": 30779931.0,
|
| 15202 |
"step": 8440
|
| 15203 |
+
},
|
| 15204 |
+
{
|
| 15205 |
+
"epoch": 64.96153846153847,
|
| 15206 |
+
"grad_norm": 0.0,
|
| 15207 |
+
"learning_rate": 7.78e-06,
|
| 15208 |
+
"loss": 1.6928,
|
| 15209 |
+
"mean_token_accuracy": 0.6551145076751709,
|
| 15210 |
+
"num_tokens": 30798591.0,
|
| 15211 |
+
"step": 8445
|
| 15212 |
+
},
|
| 15213 |
+
{
|
| 15214 |
+
"epoch": 65.0,
|
| 15215 |
+
"grad_norm": 0.0,
|
| 15216 |
+
"learning_rate": 7.755e-06,
|
| 15217 |
+
"loss": 1.7471,
|
| 15218 |
+
"mean_token_accuracy": 0.6472322821617127,
|
| 15219 |
+
"num_tokens": 30816825.0,
|
| 15220 |
+
"step": 8450
|
| 15221 |
}
|
| 15222 |
],
|
| 15223 |
"logging_steps": 5,
|
|
|
|
| 15237 |
"attributes": {}
|
| 15238 |
}
|
| 15239 |
},
|
| 15240 |
+
"total_flos": 1.5625168391223706e+18,
|
| 15241 |
"train_batch_size": 4,
|
| 15242 |
"trial_name": null,
|
| 15243 |
"trial_params": null
|