Training in progress, step 4980, 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 sha256:28f9319b614402d2481a5c42aaefeee70a02aec65ce02e153bf3ef9b0d16b671
|
| 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 sha256:1618e0ab745d3cdd857df9a941055964bbd4ac22fd94f2ab6a968b3ec8d2dcb2
|
| 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 sha256:8629903c2626622a640134243516bd089afc4db0ed4e110064cb5e7bb6a00d19
|
| 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": 38.
|
| 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,
|
|
@@ -8954,6 +8954,24 @@
|
|
| 8954 |
"mean_token_accuracy": 0.6630479246377945,
|
| 8955 |
"num_tokens": 18126899.0,
|
| 8956 |
"step": 4970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8957 |
}
|
| 8958 |
],
|
| 8959 |
"logging_steps": 5,
|
|
@@ -8973,7 +8991,7 @@
|
|
| 8973 |
"attributes": {}
|
| 8974 |
}
|
| 8975 |
},
|
| 8976 |
-
"total_flos": 9.
|
| 8977 |
"train_batch_size": 4,
|
| 8978 |
"trial_name": null,
|
| 8979 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4980,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8954 |
"mean_token_accuracy": 0.6630479246377945,
|
| 8955 |
"num_tokens": 18126899.0,
|
| 8956 |
"step": 4970
|
| 8957 |
+
},
|
| 8958 |
+
{
|
| 8959 |
+
"epoch": 38.26923076923077,
|
| 8960 |
+
"grad_norm": 0.0,
|
| 8961 |
+
"learning_rate": 2.5130000000000005e-05,
|
| 8962 |
+
"loss": 1.6931,
|
| 8963 |
+
"mean_token_accuracy": 0.6576372981071472,
|
| 8964 |
+
"num_tokens": 18145576.0,
|
| 8965 |
+
"step": 4975
|
| 8966 |
+
},
|
| 8967 |
+
{
|
| 8968 |
+
"epoch": 38.30769230769231,
|
| 8969 |
+
"grad_norm": 0.0,
|
| 8970 |
+
"learning_rate": 2.5105e-05,
|
| 8971 |
+
"loss": 1.7881,
|
| 8972 |
+
"mean_token_accuracy": 0.6391725331544876,
|
| 8973 |
+
"num_tokens": 18162910.0,
|
| 8974 |
+
"step": 4980
|
| 8975 |
}
|
| 8976 |
],
|
| 8977 |
"logging_steps": 5,
|
|
|
|
| 8991 |
"attributes": {}
|
| 8992 |
}
|
| 8993 |
},
|
| 8994 |
+
"total_flos": 9.204709734413107e+17,
|
| 8995 |
"train_batch_size": 4,
|
| 8996 |
"trial_name": null,
|
| 8997 |
"trial_params": null
|