Training in progress, step 4020, 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 sha256:99a9099118a50866b5bfc5a481d299a62ffd2e512f09abc19ba442e790f51fda
|
| 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 sha256:869c5bae7e73f584570d2877c9ecc837978e3c9fd5bc513aae810625554643d1
|
| 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 sha256:4b038f8f08f21488b0f0561b68167e107fdd5090384d03309c69fe2452cce19f
|
| 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": 30.
|
| 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,
|
|
@@ -7226,6 +7226,24 @@
|
|
| 7226 |
"mean_token_accuracy": 0.6434893846511841,
|
| 7227 |
"num_tokens": 14624861.0,
|
| 7228 |
"step": 4010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7229 |
}
|
| 7230 |
],
|
| 7231 |
"logging_steps": 5,
|
|
@@ -7245,7 +7263,7 @@
|
|
| 7245 |
"attributes": {}
|
| 7246 |
}
|
| 7247 |
},
|
| 7248 |
-
"total_flos": 7.
|
| 7249 |
"train_batch_size": 4,
|
| 7250 |
"trial_name": null,
|
| 7251 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4020,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7226 |
"mean_token_accuracy": 0.6434893846511841,
|
| 7227 |
"num_tokens": 14624861.0,
|
| 7228 |
"step": 4010
|
| 7229 |
+
},
|
| 7230 |
+
{
|
| 7231 |
+
"epoch": 30.884615384615383,
|
| 7232 |
+
"grad_norm": 0.0,
|
| 7233 |
+
"learning_rate": 2.9930000000000003e-05,
|
| 7234 |
+
"loss": 1.6634,
|
| 7235 |
+
"mean_token_accuracy": 0.6664941430091857,
|
| 7236 |
+
"num_tokens": 14643597.0,
|
| 7237 |
+
"step": 4015
|
| 7238 |
+
},
|
| 7239 |
+
{
|
| 7240 |
+
"epoch": 30.923076923076923,
|
| 7241 |
+
"grad_norm": 0.0,
|
| 7242 |
+
"learning_rate": 2.9905e-05,
|
| 7243 |
+
"loss": 1.7814,
|
| 7244 |
+
"mean_token_accuracy": 0.6440500050783158,
|
| 7245 |
+
"num_tokens": 14661469.0,
|
| 7246 |
+
"step": 4020
|
| 7247 |
}
|
| 7248 |
],
|
| 7249 |
"logging_steps": 5,
|
|
|
|
| 7263 |
"attributes": {}
|
| 7264 |
}
|
| 7265 |
},
|
| 7266 |
+
"total_flos": 7.429962178481357e+17,
|
| 7267 |
"train_batch_size": 4,
|
| 7268 |
"trial_name": null,
|
| 7269 |
"trial_params": null
|