Training in progress, step 5620, 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:b755ee5aa08034be8a6201b49ee4f7111e922351adcdb6b7118ce34f95fe3a2d
|
| 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:d405844697a2d1a03e09c398c239a0aa9459e66057fc6608989824445b8d0582
|
| 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 sha256:0e08d2740355f1275abc37d17088e438011d04421a7141bdda08b200c351b983
|
| 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": 43.
|
| 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,
|
|
@@ -10106,6 +10106,24 @@
|
|
| 10106 |
"mean_token_accuracy": 0.6698237389326096,
|
| 10107 |
"num_tokens": 20459519.0,
|
| 10108 |
"step": 5610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10109 |
}
|
| 10110 |
],
|
| 10111 |
"logging_steps": 5,
|
|
@@ -10125,7 +10143,7 @@
|
|
| 10125 |
"attributes": {}
|
| 10126 |
}
|
| 10127 |
},
|
| 10128 |
-
"total_flos": 1.
|
| 10129 |
"train_batch_size": 4,
|
| 10130 |
"trial_name": null,
|
| 10131 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5620,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10106 |
"mean_token_accuracy": 0.6698237389326096,
|
| 10107 |
"num_tokens": 20459519.0,
|
| 10108 |
"step": 5610
|
| 10109 |
+
},
|
| 10110 |
+
{
|
| 10111 |
+
"epoch": 43.19230769230769,
|
| 10112 |
+
"grad_norm": 0.0,
|
| 10113 |
+
"learning_rate": 2.1930000000000002e-05,
|
| 10114 |
+
"loss": 1.7039,
|
| 10115 |
+
"mean_token_accuracy": 0.6586238622665406,
|
| 10116 |
+
"num_tokens": 20478450.0,
|
| 10117 |
+
"step": 5615
|
| 10118 |
+
},
|
| 10119 |
+
{
|
| 10120 |
+
"epoch": 43.23076923076923,
|
| 10121 |
+
"grad_norm": 0.0,
|
| 10122 |
+
"learning_rate": 2.1905e-05,
|
| 10123 |
+
"loss": 1.733,
|
| 10124 |
+
"mean_token_accuracy": 0.650734207034111,
|
| 10125 |
+
"num_tokens": 20497721.0,
|
| 10126 |
+
"step": 5620
|
| 10127 |
}
|
| 10128 |
],
|
| 10129 |
"logging_steps": 5,
|
|
|
|
| 10143 |
"attributes": {}
|
| 10144 |
}
|
| 10145 |
},
|
| 10146 |
+
"total_flos": 1.0387085639344128e+18,
|
| 10147 |
"train_batch_size": 4,
|
| 10148 |
"trial_name": null,
|
| 10149 |
"trial_params": null
|