Training in progress, step 1290, 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:b25b22e3bafe63e6cf2422f1b7acd52713b5da6f03bfc2d5ca7c0f62a27e3dcc
|
| 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 sha256:3d1924d3ca3123badd935b4eefd192e15fb62d1fb78b6d77b04c8de2f3414a8c
|
| 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 sha256:543ee5f90d7c86df1a19e3c55554c8f0041076bb65afced323a58e780f37111a
|
| 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,
|
|
@@ -2312,6 +2312,24 @@
|
|
| 2312 |
"mean_token_accuracy": 0.658900797367096,
|
| 2313 |
"num_tokens": 4669522.0,
|
| 2314 |
"step": 1280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2315 |
}
|
| 2316 |
],
|
| 2317 |
"logging_steps": 5,
|
|
@@ -2331,7 +2349,7 @@
|
|
| 2331 |
"attributes": {}
|
| 2332 |
}
|
| 2333 |
},
|
| 2334 |
-
"total_flos": 2.
|
| 2335 |
"train_batch_size": 4,
|
| 2336 |
"trial_name": null,
|
| 2337 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2312 |
"mean_token_accuracy": 0.658900797367096,
|
| 2313 |
"num_tokens": 4669522.0,
|
| 2314 |
"step": 1280
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 9.884615384615385,
|
| 2318 |
+
"grad_norm": 0.0,
|
| 2319 |
+
"learning_rate": 4.3580000000000006e-05,
|
| 2320 |
+
"loss": 1.778,
|
| 2321 |
+
"mean_token_accuracy": 0.6451369762420655,
|
| 2322 |
+
"num_tokens": 4687769.0,
|
| 2323 |
+
"step": 1285
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 9.923076923076923,
|
| 2327 |
+
"grad_norm": 0.0,
|
| 2328 |
+
"learning_rate": 4.3555e-05,
|
| 2329 |
+
"loss": 1.733,
|
| 2330 |
+
"mean_token_accuracy": 0.6531021893024445,
|
| 2331 |
+
"num_tokens": 4705563.0,
|
| 2332 |
+
"step": 1290
|
| 2333 |
}
|
| 2334 |
],
|
| 2335 |
"logging_steps": 5,
|
|
|
|
| 2349 |
"attributes": {}
|
| 2350 |
}
|
| 2351 |
},
|
| 2352 |
+
"total_flos": 2.384513462403072e+17,
|
| 2353 |
"train_batch_size": 4,
|
| 2354 |
"trial_name": null,
|
| 2355 |
"trial_params": null
|