Training in progress, step 3190, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cd3b2792f38f21074f094fd473982b56eb8202fa8b841fddb218ee2df3dc6d0
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfd39a5c512141fa2cff39c5aaac1a8acf039b1ce1ebb247d7bb3726f28c286f
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f6575ed3809fa6cc5bb999ca31d02511963d41f0433cb26341501baf624236d
|
| 3 |
size 14645
|
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 sha256:018ca0f0abc022963f128fc4d080d145ac07b5fba4cd78857cb7aee3ab397b38
|
| 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,
|
|
@@ -3198,6 +3198,16 @@
|
|
| 3198 |
"mean_token_accuracy": 0.7741461530327797,
|
| 3199 |
"num_tokens": 14803777.0,
|
| 3200 |
"step": 3180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3201 |
}
|
| 3202 |
],
|
| 3203 |
"logging_steps": 10,
|
|
@@ -3217,7 +3227,7 @@
|
|
| 3217 |
"attributes": {}
|
| 3218 |
}
|
| 3219 |
},
|
| 3220 |
-
"total_flos": 7.
|
| 3221 |
"train_batch_size": 4,
|
| 3222 |
"trial_name": null,
|
| 3223 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6805333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3198 |
"mean_token_accuracy": 0.7741461530327797,
|
| 3199 |
"num_tokens": 14803777.0,
|
| 3200 |
"step": 3180
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"entropy": 0.9152800880372525,
|
| 3204 |
+
"epoch": 0.6805333333333333,
|
| 3205 |
+
"grad_norm": 0.25680598616600037,
|
| 3206 |
+
"learning_rate": 7.701483169861713e-05,
|
| 3207 |
+
"loss": 0.9781417846679688,
|
| 3208 |
+
"mean_token_accuracy": 0.7678594440221786,
|
| 3209 |
+
"num_tokens": 14851182.0,
|
| 3210 |
+
"step": 3190
|
| 3211 |
}
|
| 3212 |
],
|
| 3213 |
"logging_steps": 10,
|
|
|
|
| 3227 |
"attributes": {}
|
| 3228 |
}
|
| 3229 |
},
|
| 3230 |
+
"total_flos": 7.033748178319258e+16,
|
| 3231 |
"train_batch_size": 4,
|
| 3232 |
"trial_name": null,
|
| 3233 |
"trial_params": null
|