Training in progress, step 2430, 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:b2d40d7492871af818a873575b1d040357f413c4b45faac915257aca9ce74ccf
|
| 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 sha256:205dd08a8ac6dfe70d2a42024f071ab7aedb8e10d1ab20704a10140fa8a15694
|
| 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 sha256:094f939666c127e9eee608294e39b9611b097812ae0e2d330e577d580110aa69
|
| 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": 18.
|
| 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,
|
|
@@ -4364,6 +4364,24 @@
|
|
| 4364 |
"mean_token_accuracy": 0.6637963593006134,
|
| 4365 |
"num_tokens": 8823585.0,
|
| 4366 |
"step": 2420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4367 |
}
|
| 4368 |
],
|
| 4369 |
"logging_steps": 5,
|
|
@@ -4383,7 +4401,7 @@
|
|
| 4383 |
"attributes": {}
|
| 4384 |
}
|
| 4385 |
},
|
| 4386 |
-
"total_flos": 4.
|
| 4387 |
"train_batch_size": 4,
|
| 4388 |
"trial_name": null,
|
| 4389 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4364 |
"mean_token_accuracy": 0.6637963593006134,
|
| 4365 |
"num_tokens": 8823585.0,
|
| 4366 |
"step": 2420
|
| 4367 |
+
},
|
| 4368 |
+
{
|
| 4369 |
+
"epoch": 18.653846153846153,
|
| 4370 |
+
"grad_norm": 0.0,
|
| 4371 |
+
"learning_rate": 3.788e-05,
|
| 4372 |
+
"loss": 1.7647,
|
| 4373 |
+
"mean_token_accuracy": 0.648153355717659,
|
| 4374 |
+
"num_tokens": 8841533.0,
|
| 4375 |
+
"step": 2425
|
| 4376 |
+
},
|
| 4377 |
+
{
|
| 4378 |
+
"epoch": 18.692307692307693,
|
| 4379 |
+
"grad_norm": 0.0,
|
| 4380 |
+
"learning_rate": 3.7855e-05,
|
| 4381 |
+
"loss": 1.7309,
|
| 4382 |
+
"mean_token_accuracy": 0.6484656900167465,
|
| 4383 |
+
"num_tokens": 8860614.0,
|
| 4384 |
+
"step": 2430
|
| 4385 |
}
|
| 4386 |
],
|
| 4387 |
"logging_steps": 5,
|
|
|
|
| 4401 |
"attributes": {}
|
| 4402 |
}
|
| 4403 |
},
|
| 4404 |
+
"total_flos": 4.490071018360013e+17,
|
| 4405 |
"train_batch_size": 4,
|
| 4406 |
"trial_name": null,
|
| 4407 |
"trial_params": null
|