Training in progress, step 5120, 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 sha256:1b5ffd83964f846990a7c79c90a519f2f5cfeb51c806abb1e6db68ab94104c2f
|
| 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 sha256:4b52da68d52032b19791d5e51b6779ca62a181d8c41a8acb4e11aec9fa557858
|
| 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 sha256:9409cde4b6b7bd938d6d8ad1540cbae7693eaa1cd270e3e7c0cc885741500455
|
| 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": 39.
|
| 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,
|
|
@@ -9206,6 +9206,24 @@
|
|
| 9206 |
"mean_token_accuracy": 0.6567441165447235,
|
| 9207 |
"num_tokens": 18635229.0,
|
| 9208 |
"step": 5110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9209 |
}
|
| 9210 |
],
|
| 9211 |
"logging_steps": 5,
|
|
@@ -9225,7 +9243,7 @@
|
|
| 9225 |
"attributes": {}
|
| 9226 |
}
|
| 9227 |
},
|
| 9228 |
-
"total_flos": 9.
|
| 9229 |
"train_batch_size": 4,
|
| 9230 |
"trial_name": null,
|
| 9231 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9206 |
"mean_token_accuracy": 0.6567441165447235,
|
| 9207 |
"num_tokens": 18635229.0,
|
| 9208 |
"step": 5110
|
| 9209 |
+
},
|
| 9210 |
+
{
|
| 9211 |
+
"epoch": 39.34615384615385,
|
| 9212 |
+
"grad_norm": 0.0,
|
| 9213 |
+
"learning_rate": 2.443e-05,
|
| 9214 |
+
"loss": 1.6926,
|
| 9215 |
+
"mean_token_accuracy": 0.6508637487888336,
|
| 9216 |
+
"num_tokens": 18654889.0,
|
| 9217 |
+
"step": 5115
|
| 9218 |
+
},
|
| 9219 |
+
{
|
| 9220 |
+
"epoch": 39.38461538461539,
|
| 9221 |
+
"grad_norm": 0.0,
|
| 9222 |
+
"learning_rate": 2.4405e-05,
|
| 9223 |
+
"loss": 1.7283,
|
| 9224 |
+
"mean_token_accuracy": 0.6576891779899597,
|
| 9225 |
+
"num_tokens": 18672794.0,
|
| 9226 |
+
"step": 5120
|
| 9227 |
}
|
| 9228 |
],
|
| 9229 |
"logging_steps": 5,
|
|
|
|
| 9243 |
"attributes": {}
|
| 9244 |
}
|
| 9245 |
},
|
| 9246 |
+
"total_flos": 9.461449262717338e+17,
|
| 9247 |
"train_batch_size": 4,
|
| 9248 |
"trial_name": null,
|
| 9249 |
"trial_params": null
|