Training in progress, step 1300, 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 sha256:549bf19da0b8d53caf80966577c1e664032b73282221e93e9426bfe495c4e2f0
|
| 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 sha256:7f35f441e7d5d50f01405b245baee043bc9c54d4fc204530d6837cf3c5d70fb7
|
| 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 sha256:3ef4ea08799334f13d9fbc4a646b9e08c2a1ffed8918582e90e9b8baafa40ba7
|
| 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":
|
| 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,
|
|
@@ -2330,6 +2330,24 @@
|
|
| 2330 |
"mean_token_accuracy": 0.6531021893024445,
|
| 2331 |
"num_tokens": 4705563.0,
|
| 2332 |
"step": 1290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2333 |
}
|
| 2334 |
],
|
| 2335 |
"logging_steps": 5,
|
|
@@ -2349,7 +2367,7 @@
|
|
| 2349 |
"attributes": {}
|
| 2350 |
}
|
| 2351 |
},
|
| 2352 |
-
"total_flos": 2.
|
| 2353 |
"train_batch_size": 4,
|
| 2354 |
"trial_name": null,
|
| 2355 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2330 |
"mean_token_accuracy": 0.6531021893024445,
|
| 2331 |
"num_tokens": 4705563.0,
|
| 2332 |
"step": 1290
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 9.961538461538462,
|
| 2336 |
+
"grad_norm": 0.0,
|
| 2337 |
+
"learning_rate": 4.3530000000000005e-05,
|
| 2338 |
+
"loss": 1.7758,
|
| 2339 |
+
"mean_token_accuracy": 0.6376697093248367,
|
| 2340 |
+
"num_tokens": 4723178.0,
|
| 2341 |
+
"step": 1295
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 10.0,
|
| 2345 |
+
"grad_norm": 0.0,
|
| 2346 |
+
"learning_rate": 4.3505000000000004e-05,
|
| 2347 |
+
"loss": 1.7658,
|
| 2348 |
+
"mean_token_accuracy": 0.6424418658018112,
|
| 2349 |
+
"num_tokens": 4741050.0,
|
| 2350 |
+
"step": 1300
|
| 2351 |
}
|
| 2352 |
],
|
| 2353 |
"logging_steps": 5,
|
|
|
|
| 2367 |
"attributes": {}
|
| 2368 |
}
|
| 2369 |
},
|
| 2370 |
+
"total_flos": 2.4024046966013952e+17,
|
| 2371 |
"train_batch_size": 4,
|
| 2372 |
"trial_name": null,
|
| 2373 |
"trial_params": null
|