Training in progress, step 7760, 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 sha256:4e8d7edd845d22992c4d13e6dc06d81c205d11eb83aafbe7beb4025567846514
|
| 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 sha256:5d4c26e1eaee8a50e335098fa46ef1e4a02aaf8abf3b11c044dcc8a33bb9b64e
|
| 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 sha256:039bdd5589437ed84e3b07bc7d050fbd6c2cfbaeccd46bc57531efd3323caac9
|
| 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,
|
|
@@ -13958,6 +13958,24 @@
|
|
| 13958 |
"mean_token_accuracy": 0.6731823951005935,
|
| 13959 |
"num_tokens": 28265694.0,
|
| 13960 |
"step": 7750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13961 |
}
|
| 13962 |
],
|
| 13963 |
"logging_steps": 5,
|
|
@@ -13977,7 +13995,7 @@
|
|
| 13977 |
"attributes": {}
|
| 13978 |
}
|
| 13979 |
},
|
| 13980 |
-
"total_flos": 1.
|
| 13981 |
"train_batch_size": 4,
|
| 13982 |
"trial_name": null,
|
| 13983 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13958 |
"mean_token_accuracy": 0.6731823951005935,
|
| 13959 |
"num_tokens": 28265694.0,
|
| 13960 |
"step": 7750
|
| 13961 |
+
},
|
| 13962 |
+
{
|
| 13963 |
+
"epoch": 59.65384615384615,
|
| 13964 |
+
"grad_norm": 0.0,
|
| 13965 |
+
"learning_rate": 1.1230000000000001e-05,
|
| 13966 |
+
"loss": 1.7091,
|
| 13967 |
+
"mean_token_accuracy": 0.6587099075317383,
|
| 13968 |
+
"num_tokens": 28283812.0,
|
| 13969 |
+
"step": 7755
|
| 13970 |
+
},
|
| 13971 |
+
{
|
| 13972 |
+
"epoch": 59.69230769230769,
|
| 13973 |
+
"grad_norm": 0.0,
|
| 13974 |
+
"learning_rate": 1.1205e-05,
|
| 13975 |
+
"loss": 1.775,
|
| 13976 |
+
"mean_token_accuracy": 0.6434663653373718,
|
| 13977 |
+
"num_tokens": 28301500.0,
|
| 13978 |
+
"step": 7760
|
| 13979 |
}
|
| 13980 |
],
|
| 13981 |
"logging_steps": 5,
|
|
|
|
| 13995 |
"attributes": {}
|
| 13996 |
}
|
| 13997 |
},
|
| 13998 |
+
"total_flos": 1.4350100396300698e+18,
|
| 13999 |
"train_batch_size": 4,
|
| 14000 |
"trial_name": null,
|
| 14001 |
"trial_params": null
|