Training in progress, step 4330, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d783fd131ac4d246f39470fde6dfaaaaa140a95661ab424b12450e7fecfb80de
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89c3bfc03e66b507ba63c4621f08509d221d1d0f5a70e7be9d8ed97fa19e5a65
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26fa79148bb3f2ed4cc710bdcff469ba6aeec3ceab1ec596990700f4ea27c1c9
|
| 3 |
size 14645
|
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 sha256:610f155e20460be233b63e851ca501465c44f781bed5601edf88e458e04a8b85
|
| 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": 0.
|
| 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,
|
|
@@ -4338,6 +4338,16 @@
|
|
| 4338 |
"mean_token_accuracy": 0.763984477519989,
|
| 4339 |
"num_tokens": 20116649.0,
|
| 4340 |
"step": 4320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4341 |
}
|
| 4342 |
],
|
| 4343 |
"logging_steps": 10,
|
|
@@ -4357,7 +4367,7 @@
|
|
| 4357 |
"attributes": {}
|
| 4358 |
}
|
| 4359 |
},
|
| 4360 |
-
"total_flos": 9.
|
| 4361 |
"train_batch_size": 4,
|
| 4362 |
"trial_name": null,
|
| 4363 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9237333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4338 |
"mean_token_accuracy": 0.763984477519989,
|
| 4339 |
"num_tokens": 20116649.0,
|
| 4340 |
"step": 4320
|
| 4341 |
+
},
|
| 4342 |
+
{
|
| 4343 |
+
"entropy": 0.95065303966403,
|
| 4344 |
+
"epoch": 0.9237333333333333,
|
| 4345 |
+
"grad_norm": 0.26842495799064636,
|
| 4346 |
+
"learning_rate": 5.8763830415477674e-05,
|
| 4347 |
+
"loss": 1.0108171463012696,
|
| 4348 |
+
"mean_token_accuracy": 0.7639551430940628,
|
| 4349 |
+
"num_tokens": 20161155.0,
|
| 4350 |
+
"step": 4330
|
| 4351 |
}
|
| 4352 |
],
|
| 4353 |
"logging_steps": 10,
|
|
|
|
| 4367 |
"attributes": {}
|
| 4368 |
}
|
| 4369 |
},
|
| 4370 |
+
"total_flos": 9.545480340993331e+16,
|
| 4371 |
"train_batch_size": 4,
|
| 4372 |
"trial_name": null,
|
| 4373 |
"trial_params": null
|