Training in progress, step 7410, 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 sha256:5a7f9238760f03c87d71cb1ced78357d2253bc97e328d0a43e8779229da1ee11
|
| 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:b51cbb6305a08e1cb7998759efda3e79356722770ea962b8ad5a3eef38a1b445
|
| 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:c09ff2fda5bcdcac6be6a90bfa74fff9865a294c74058f9f20d9388f6c232ccf
|
| 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,
|
|
@@ -13328,6 +13328,24 @@
|
|
| 13328 |
"mean_token_accuracy": 0.661999249458313,
|
| 13329 |
"num_tokens": 26987507.0,
|
| 13330 |
"step": 7400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13331 |
}
|
| 13332 |
],
|
| 13333 |
"logging_steps": 5,
|
|
@@ -13347,7 +13365,7 @@
|
|
| 13347 |
"attributes": {}
|
| 13348 |
}
|
| 13349 |
},
|
| 13350 |
-
"total_flos": 1.
|
| 13351 |
"train_batch_size": 4,
|
| 13352 |
"trial_name": null,
|
| 13353 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13328 |
"mean_token_accuracy": 0.661999249458313,
|
| 13329 |
"num_tokens": 26987507.0,
|
| 13330 |
"step": 7400
|
| 13331 |
+
},
|
| 13332 |
+
{
|
| 13333 |
+
"epoch": 56.96153846153846,
|
| 13334 |
+
"grad_norm": 0.0,
|
| 13335 |
+
"learning_rate": 1.2980000000000001e-05,
|
| 13336 |
+
"loss": 1.6936,
|
| 13337 |
+
"mean_token_accuracy": 0.6539974421262741,
|
| 13338 |
+
"num_tokens": 27005866.0,
|
| 13339 |
+
"step": 7405
|
| 13340 |
+
},
|
| 13341 |
+
{
|
| 13342 |
+
"epoch": 57.0,
|
| 13343 |
+
"grad_norm": 0.0,
|
| 13344 |
+
"learning_rate": 1.2955e-05,
|
| 13345 |
+
"loss": 1.7419,
|
| 13346 |
+
"mean_token_accuracy": 0.6442842125892639,
|
| 13347 |
+
"num_tokens": 27023985.0,
|
| 13348 |
+
"step": 7410
|
| 13349 |
}
|
| 13350 |
],
|
| 13351 |
"logging_steps": 5,
|
|
|
|
| 13365 |
"attributes": {}
|
| 13366 |
}
|
| 13367 |
},
|
| 13368 |
+
"total_flos": 1.3701530454279782e+18,
|
| 13369 |
"train_batch_size": 4,
|
| 13370 |
"trial_name": null,
|
| 13371 |
"trial_params": null
|