Training in progress, step 9010, 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:f0b942694ca011812949e26804657c7489589a4c2854b4f1d164819e7e54e6cf
|
| 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:cbd478f15051a2475534a094221062969b6c0f03951080712ce91b9d8a944969
|
| 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 sha256:262b993e116b3e75859a643ec5f8a8298a99b337893c519a00bd8ad06a118ff2
|
| 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": 69.
|
| 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,
|
|
@@ -16208,6 +16208,24 @@
|
|
| 16208 |
"mean_token_accuracy": 0.6397767275571823,
|
| 16209 |
"num_tokens": 32822708.0,
|
| 16210 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16211 |
}
|
| 16212 |
],
|
| 16213 |
"logging_steps": 5,
|
|
@@ -16227,7 +16245,7 @@
|
|
| 16227 |
"attributes": {}
|
| 16228 |
}
|
| 16229 |
},
|
| 16230 |
-
"total_flos": 1.
|
| 16231 |
"train_batch_size": 4,
|
| 16232 |
"trial_name": null,
|
| 16233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16208 |
"mean_token_accuracy": 0.6397767275571823,
|
| 16209 |
"num_tokens": 32822708.0,
|
| 16210 |
"step": 9000
|
| 16211 |
+
},
|
| 16212 |
+
{
|
| 16213 |
+
"epoch": 69.26923076923077,
|
| 16214 |
+
"grad_norm": 0.0,
|
| 16215 |
+
"learning_rate": 4.98e-06,
|
| 16216 |
+
"loss": 1.724,
|
| 16217 |
+
"mean_token_accuracy": 0.6544425517320633,
|
| 16218 |
+
"num_tokens": 32841355.0,
|
| 16219 |
+
"step": 9005
|
| 16220 |
+
},
|
| 16221 |
+
{
|
| 16222 |
+
"epoch": 69.3076923076923,
|
| 16223 |
+
"grad_norm": 0.0,
|
| 16224 |
+
"learning_rate": 4.955e-06,
|
| 16225 |
+
"loss": 1.7819,
|
| 16226 |
+
"mean_token_accuracy": 0.6387849062681198,
|
| 16227 |
+
"num_tokens": 32859210.0,
|
| 16228 |
+
"step": 9010
|
| 16229 |
}
|
| 16230 |
],
|
| 16231 |
"logging_steps": 5,
|
|
|
|
| 16245 |
"attributes": {}
|
| 16246 |
}
|
| 16247 |
},
|
| 16248 |
+
"total_flos": 1.6662428095448678e+18,
|
| 16249 |
"train_batch_size": 4,
|
| 16250 |
"trial_name": null,
|
| 16251 |
"trial_params": null
|