Training in progress, step 8530, 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 sha256:82c7d01b1b6595e5ad606e8fd0ef9c1248cbb348f3b90c63db0680f4a60451a3
|
| 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 sha256:9c964306b696699757b1c0f5c3f2e87fbdd0acea3eb465ba20230d0dac922cb0
|
| 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 sha256:06ae67057c7da5d59c50b1b4522b722ef8920302e77154188e2429de26bc8428
|
| 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": 65.
|
| 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,
|
|
@@ -15344,6 +15344,24 @@
|
|
| 15344 |
"mean_token_accuracy": 0.6601694732904434,
|
| 15345 |
"num_tokens": 31073830.0,
|
| 15346 |
"step": 8520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15347 |
}
|
| 15348 |
],
|
| 15349 |
"logging_steps": 5,
|
|
@@ -15363,7 +15381,7 @@
|
|
| 15363 |
"attributes": {}
|
| 15364 |
}
|
| 15365 |
},
|
| 15366 |
-
"total_flos": 1.
|
| 15367 |
"train_batch_size": 4,
|
| 15368 |
"trial_name": null,
|
| 15369 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15344 |
"mean_token_accuracy": 0.6601694732904434,
|
| 15345 |
"num_tokens": 31073830.0,
|
| 15346 |
"step": 8520
|
| 15347 |
+
},
|
| 15348 |
+
{
|
| 15349 |
+
"epoch": 65.57692307692308,
|
| 15350 |
+
"grad_norm": 0.0,
|
| 15351 |
+
"learning_rate": 7.3800000000000005e-06,
|
| 15352 |
+
"loss": 1.6752,
|
| 15353 |
+
"mean_token_accuracy": 0.6580190539360047,
|
| 15354 |
+
"num_tokens": 31092611.0,
|
| 15355 |
+
"step": 8525
|
| 15356 |
+
},
|
| 15357 |
+
{
|
| 15358 |
+
"epoch": 65.61538461538461,
|
| 15359 |
+
"grad_norm": 0.0,
|
| 15360 |
+
"learning_rate": 7.355000000000001e-06,
|
| 15361 |
+
"loss": 1.8009,
|
| 15362 |
+
"mean_token_accuracy": 0.6394985377788543,
|
| 15363 |
+
"num_tokens": 31110126.0,
|
| 15364 |
+
"step": 8530
|
| 15365 |
}
|
| 15366 |
],
|
| 15367 |
"logging_steps": 5,
|
|
|
|
| 15381 |
"attributes": {}
|
| 15382 |
}
|
| 15383 |
},
|
| 15384 |
+
"total_flos": 1.577440967414907e+18,
|
| 15385 |
"train_batch_size": 4,
|
| 15386 |
"trial_name": null,
|
| 15387 |
"trial_params": null
|