Training in progress, step 6280, 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:bb05c1dac61c701fbd5b72d20aeae5888b2dc0f18f21cd1d5190ce32eb6917c7
|
| 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 sha256:9947ddcf396199702dc4fe7f497981df1e7c15e369bcfce95eb9a83bc575b187
|
| 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 sha256:2a34f9a6707c3a6e6fbef560da830a8892f32645ffc688475b0c06a17853a46d
|
| 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": 48.
|
| 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,
|
|
@@ -11294,6 +11294,24 @@
|
|
| 11294 |
"mean_token_accuracy": 0.6651150584220886,
|
| 11295 |
"num_tokens": 22866785.0,
|
| 11296 |
"step": 6270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11297 |
}
|
| 11298 |
],
|
| 11299 |
"logging_steps": 5,
|
|
@@ -11313,7 +11331,7 @@
|
|
| 11313 |
"attributes": {}
|
| 11314 |
}
|
| 11315 |
},
|
| 11316 |
-
"total_flos": 1.
|
| 11317 |
"train_batch_size": 4,
|
| 11318 |
"trial_name": null,
|
| 11319 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11294 |
"mean_token_accuracy": 0.6651150584220886,
|
| 11295 |
"num_tokens": 22866785.0,
|
| 11296 |
"step": 6270
|
| 11297 |
+
},
|
| 11298 |
+
{
|
| 11299 |
+
"epoch": 48.26923076923077,
|
| 11300 |
+
"grad_norm": 0.0,
|
| 11301 |
+
"learning_rate": 1.863e-05,
|
| 11302 |
+
"loss": 1.7495,
|
| 11303 |
+
"mean_token_accuracy": 0.6475239574909211,
|
| 11304 |
+
"num_tokens": 22884516.0,
|
| 11305 |
+
"step": 6275
|
| 11306 |
+
},
|
| 11307 |
+
{
|
| 11308 |
+
"epoch": 48.30769230769231,
|
| 11309 |
+
"grad_norm": 0.0,
|
| 11310 |
+
"learning_rate": 1.8605e-05,
|
| 11311 |
+
"loss": 1.7714,
|
| 11312 |
+
"mean_token_accuracy": 0.6414877325296402,
|
| 11313 |
+
"num_tokens": 22902483.0,
|
| 11314 |
+
"step": 6280
|
| 11315 |
}
|
| 11316 |
],
|
| 11317 |
"logging_steps": 5,
|
|
|
|
| 11331 |
"attributes": {}
|
| 11332 |
}
|
| 11333 |
},
|
| 11334 |
+
"total_flos": 1.1609502469373952e+18,
|
| 11335 |
"train_batch_size": 4,
|
| 11336 |
"trial_name": null,
|
| 11337 |
"trial_params": null
|