Training in progress, step 5110, 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 sha256:222c6f0dfca28af30cf86223dd1e4f5b100ea397af6163b18d616662384debfe
|
| 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 sha256:8750633ee3105858749028ff03d8be99e3f98390255d79e6f9b4c5bf706a17f6
|
| 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:a2d13b4570faff3d0c88e2c9efe533e310413308c6790e1c569b97a4035e6d3d
|
| 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,
|
|
@@ -9188,6 +9188,24 @@
|
|
| 9188 |
"mean_token_accuracy": 0.6537098169326783,
|
| 9189 |
"num_tokens": 18599186.0,
|
| 9190 |
"step": 5100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9191 |
}
|
| 9192 |
],
|
| 9193 |
"logging_steps": 5,
|
|
@@ -9207,7 +9225,7 @@
|
|
| 9207 |
"attributes": {}
|
| 9208 |
}
|
| 9209 |
},
|
| 9210 |
-
"total_flos": 9.
|
| 9211 |
"train_batch_size": 4,
|
| 9212 |
"trial_name": null,
|
| 9213 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9188 |
"mean_token_accuracy": 0.6537098169326783,
|
| 9189 |
"num_tokens": 18599186.0,
|
| 9190 |
"step": 5100
|
| 9191 |
+
},
|
| 9192 |
+
{
|
| 9193 |
+
"epoch": 39.26923076923077,
|
| 9194 |
+
"grad_norm": 0.0,
|
| 9195 |
+
"learning_rate": 2.448e-05,
|
| 9196 |
+
"loss": 1.817,
|
| 9197 |
+
"mean_token_accuracy": 0.6370946735143661,
|
| 9198 |
+
"num_tokens": 18616131.0,
|
| 9199 |
+
"step": 5105
|
| 9200 |
+
},
|
| 9201 |
+
{
|
| 9202 |
+
"epoch": 39.30769230769231,
|
| 9203 |
+
"grad_norm": 0.0,
|
| 9204 |
+
"learning_rate": 2.4455e-05,
|
| 9205 |
+
"loss": 1.6847,
|
| 9206 |
+
"mean_token_accuracy": 0.6567441165447235,
|
| 9207 |
+
"num_tokens": 18635229.0,
|
| 9208 |
+
"step": 5110
|
| 9209 |
}
|
| 9210 |
],
|
| 9211 |
"logging_steps": 5,
|
|
|
|
| 9225 |
"attributes": {}
|
| 9226 |
}
|
| 9227 |
},
|
| 9228 |
+
"total_flos": 9.442619643764736e+17,
|
| 9229 |
"train_batch_size": 4,
|
| 9230 |
"trial_name": null,
|
| 9231 |
"trial_params": null
|