Training in progress, step 5170, 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:ae1f9dc4d9ae160cabe4b757a3b260d00035b0fbca128781b576e8512a9c6ccd
|
| 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 sha256:155834ec9889041a3ed3680f56cbd8fc4c36d009d550353a6eba6bc5346fe76f
|
| 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:cb1a270202bd2fd6607c775dbb3975e9cc6fe775af6d3617b6ef61e51c4bfba3
|
| 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,
|
|
@@ -9296,6 +9296,24 @@
|
|
| 9296 |
"mean_token_accuracy": 0.6388770550489425,
|
| 9297 |
"num_tokens": 18821103.0,
|
| 9298 |
"step": 5160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9299 |
}
|
| 9300 |
],
|
| 9301 |
"logging_steps": 5,
|
|
@@ -9315,7 +9333,7 @@
|
|
| 9315 |
"attributes": {}
|
| 9316 |
}
|
| 9317 |
},
|
| 9318 |
-
"total_flos": 9.
|
| 9319 |
"train_batch_size": 4,
|
| 9320 |
"trial_name": null,
|
| 9321 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9296 |
"mean_token_accuracy": 0.6388770550489425,
|
| 9297 |
"num_tokens": 18821103.0,
|
| 9298 |
"step": 5160
|
| 9299 |
+
},
|
| 9300 |
+
{
|
| 9301 |
+
"epoch": 39.73076923076923,
|
| 9302 |
+
"grad_norm": 0.0,
|
| 9303 |
+
"learning_rate": 2.418e-05,
|
| 9304 |
+
"loss": 1.8602,
|
| 9305 |
+
"mean_token_accuracy": 0.6244511514902115,
|
| 9306 |
+
"num_tokens": 18838884.0,
|
| 9307 |
+
"step": 5165
|
| 9308 |
+
},
|
| 9309 |
+
{
|
| 9310 |
+
"epoch": 39.76923076923077,
|
| 9311 |
+
"grad_norm": 0.0,
|
| 9312 |
+
"learning_rate": 2.4154999999999998e-05,
|
| 9313 |
+
"loss": 1.7841,
|
| 9314 |
+
"mean_token_accuracy": 0.6422644227743148,
|
| 9315 |
+
"num_tokens": 18856713.0,
|
| 9316 |
+
"step": 5170
|
| 9317 |
}
|
| 9318 |
],
|
| 9319 |
"logging_steps": 5,
|
|
|
|
| 9333 |
"attributes": {}
|
| 9334 |
}
|
| 9335 |
},
|
| 9336 |
+
"total_flos": 9.555133722373325e+17,
|
| 9337 |
"train_batch_size": 4,
|
| 9338 |
"trial_name": null,
|
| 9339 |
"trial_params": null
|