Training in progress, step 9510, 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 sha256:8f56ce055f27e4d6c1a0fe82dbaad6d253980b1685b5f6431f4f811205b6fcdd
|
| 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:ec65f80395eca21cf1cbd87edf58b640a33d4edbd4673d94ba457deb609808c9
|
| 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 sha256:87828df43404a4bda04d64a6c933b12ef71126f64d8a16f846715810ef218ab6
|
| 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": 73.
|
| 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,
|
|
@@ -17108,6 +17108,24 @@
|
|
| 17108 |
"mean_token_accuracy": 0.6496747404336929,
|
| 17109 |
"num_tokens": 34645368.0,
|
| 17110 |
"step": 9500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17111 |
}
|
| 17112 |
],
|
| 17113 |
"logging_steps": 5,
|
|
@@ -17127,7 +17145,7 @@
|
|
| 17127 |
"attributes": {}
|
| 17128 |
}
|
| 17129 |
},
|
| 17130 |
-
"total_flos": 1.
|
| 17131 |
"train_batch_size": 4,
|
| 17132 |
"trial_name": null,
|
| 17133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17108 |
"mean_token_accuracy": 0.6496747404336929,
|
| 17109 |
"num_tokens": 34645368.0,
|
| 17110 |
"step": 9500
|
| 17111 |
+
},
|
| 17112 |
+
{
|
| 17113 |
+
"epoch": 73.11538461538461,
|
| 17114 |
+
"grad_norm": 0.0,
|
| 17115 |
+
"learning_rate": 2.48e-06,
|
| 17116 |
+
"loss": 1.7188,
|
| 17117 |
+
"mean_token_accuracy": 0.6584489345550537,
|
| 17118 |
+
"num_tokens": 34663574.0,
|
| 17119 |
+
"step": 9505
|
| 17120 |
+
},
|
| 17121 |
+
{
|
| 17122 |
+
"epoch": 73.15384615384616,
|
| 17123 |
+
"grad_norm": 0.0,
|
| 17124 |
+
"learning_rate": 2.4550000000000002e-06,
|
| 17125 |
+
"loss": 1.6701,
|
| 17126 |
+
"mean_token_accuracy": 0.664915868639946,
|
| 17127 |
+
"num_tokens": 34682190.0,
|
| 17128 |
+
"step": 9510
|
| 17129 |
}
|
| 17130 |
],
|
| 17131 |
"logging_steps": 5,
|
|
|
|
| 17145 |
"attributes": {}
|
| 17146 |
}
|
| 17147 |
},
|
| 17148 |
+
"total_flos": 1.7587299156590592e+18,
|
| 17149 |
"train_batch_size": 4,
|
| 17150 |
"trial_name": null,
|
| 17151 |
"trial_params": null
|