Training in progress, step 7770, 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 sha256:1ff46b4cb7e36db0f6b467765e4658cc8f5b1ae740e2a7ca36a2d147e4ee7fde
|
| 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 sha256:9e52933a297f68bd0933de8f8daf83985a85a0458bff5cdfafa94538a15a4c7b
|
| 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 sha256:564d9c7721aa5aed5ab1d73353afa153984f603115a6b2ef499ae19d8423858b
|
| 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": 59.
|
| 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,
|
|
@@ -13976,6 +13976,24 @@
|
|
| 13976 |
"mean_token_accuracy": 0.6434663653373718,
|
| 13977 |
"num_tokens": 28301500.0,
|
| 13978 |
"step": 7760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13979 |
}
|
| 13980 |
],
|
| 13981 |
"logging_steps": 5,
|
|
@@ -13995,7 +14013,7 @@
|
|
| 13995 |
"attributes": {}
|
| 13996 |
}
|
| 13997 |
},
|
| 13998 |
-
"total_flos": 1.
|
| 13999 |
"train_batch_size": 4,
|
| 14000 |
"trial_name": null,
|
| 14001 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13976 |
"mean_token_accuracy": 0.6434663653373718,
|
| 13977 |
"num_tokens": 28301500.0,
|
| 13978 |
"step": 7760
|
| 13979 |
+
},
|
| 13980 |
+
{
|
| 13981 |
+
"epoch": 59.73076923076923,
|
| 13982 |
+
"grad_norm": 0.0,
|
| 13983 |
+
"learning_rate": 1.118e-05,
|
| 13984 |
+
"loss": 1.7526,
|
| 13985 |
+
"mean_token_accuracy": 0.6484665781259537,
|
| 13986 |
+
"num_tokens": 28320482.0,
|
| 13987 |
+
"step": 7765
|
| 13988 |
+
},
|
| 13989 |
+
{
|
| 13990 |
+
"epoch": 59.76923076923077,
|
| 13991 |
+
"grad_norm": 0.0,
|
| 13992 |
+
"learning_rate": 1.1155e-05,
|
| 13993 |
+
"loss": 1.7621,
|
| 13994 |
+
"mean_token_accuracy": 0.6493111461400985,
|
| 13995 |
+
"num_tokens": 28338521.0,
|
| 13996 |
+
"step": 7770
|
| 13997 |
}
|
| 13998 |
],
|
| 13999 |
"logging_steps": 5,
|
|
|
|
| 14013 |
"attributes": {}
|
| 14014 |
}
|
| 14015 |
},
|
| 14016 |
+
"total_flos": 1.4369277741583565e+18,
|
| 14017 |
"train_batch_size": 4,
|
| 14018 |
"trial_name": null,
|
| 14019 |
"trial_params": null
|