Training in progress, step 1280, 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 sha256:482ce46804d7e62db9620bb04d8ed18160c6a68f73054b5d8788f2adf922e97f
|
| 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 sha256:5d73c14f98c2f6d70ff9a86d198ac5e63df60cc524adea8d49d5c3af0549437c
|
| 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 sha256:4d40f0aa25a10bde694c43f01d47806ab674a4d6baa7d7a473242b7a531ffabf
|
| 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": 9.
|
| 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,
|
|
@@ -2294,6 +2294,24 @@
|
|
| 2294 |
"mean_token_accuracy": 0.6545175701379776,
|
| 2295 |
"num_tokens": 4633258.0,
|
| 2296 |
"step": 1270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2297 |
}
|
| 2298 |
],
|
| 2299 |
"logging_steps": 5,
|
|
@@ -2313,7 +2331,7 @@
|
|
| 2313 |
"attributes": {}
|
| 2314 |
}
|
| 2315 |
},
|
| 2316 |
-
"total_flos": 2.
|
| 2317 |
"train_batch_size": 4,
|
| 2318 |
"trial_name": null,
|
| 2319 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2294 |
"mean_token_accuracy": 0.6545175701379776,
|
| 2295 |
"num_tokens": 4633258.0,
|
| 2296 |
"step": 1270
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 9.807692307692308,
|
| 2300 |
+
"grad_norm": 0.0,
|
| 2301 |
+
"learning_rate": 4.363000000000001e-05,
|
| 2302 |
+
"loss": 1.7886,
|
| 2303 |
+
"mean_token_accuracy": 0.6439413070678711,
|
| 2304 |
+
"num_tokens": 4650771.0,
|
| 2305 |
+
"step": 1275
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 9.846153846153847,
|
| 2309 |
+
"grad_norm": 0.0,
|
| 2310 |
+
"learning_rate": 4.3605e-05,
|
| 2311 |
+
"loss": 1.6981,
|
| 2312 |
+
"mean_token_accuracy": 0.658900797367096,
|
| 2313 |
+
"num_tokens": 4669522.0,
|
| 2314 |
+
"step": 1280
|
| 2315 |
}
|
| 2316 |
],
|
| 2317 |
"logging_steps": 5,
|
|
|
|
| 2331 |
"attributes": {}
|
| 2332 |
}
|
| 2333 |
},
|
| 2334 |
+
"total_flos": 2.366428517646336e+17,
|
| 2335 |
"train_batch_size": 4,
|
| 2336 |
"trial_name": null,
|
| 2337 |
"trial_params": null
|