Training in progress, step 4430, 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 sha256:04b6269f76c91e59b90d552b1c2e8a0c634341643d3a397c74a322e26056126a
|
| 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 sha256:0fa03d89809e2ac5a61d9b697f72857b57ac6148155461ebd216f8d7e1afc68d
|
| 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:cd5edd827bb57f3e0b14791aae04b4b801f7d05e0e0ed2d7fb5dcd946cec80a0
|
| 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": 34.
|
| 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,
|
|
@@ -7964,6 +7964,24 @@
|
|
| 7964 |
"mean_token_accuracy": 0.644026267528534,
|
| 7965 |
"num_tokens": 16119570.0,
|
| 7966 |
"step": 4420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7967 |
}
|
| 7968 |
],
|
| 7969 |
"logging_steps": 5,
|
|
@@ -7983,7 +8001,7 @@
|
|
| 7983 |
"attributes": {}
|
| 7984 |
}
|
| 7985 |
},
|
| 7986 |
-
"total_flos": 8.
|
| 7987 |
"train_batch_size": 4,
|
| 7988 |
"trial_name": null,
|
| 7989 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7964 |
"mean_token_accuracy": 0.644026267528534,
|
| 7965 |
"num_tokens": 16119570.0,
|
| 7966 |
"step": 4420
|
| 7967 |
+
},
|
| 7968 |
+
{
|
| 7969 |
+
"epoch": 34.03846153846154,
|
| 7970 |
+
"grad_norm": 0.0,
|
| 7971 |
+
"learning_rate": 2.788e-05,
|
| 7972 |
+
"loss": 1.7598,
|
| 7973 |
+
"mean_token_accuracy": 0.6437584400177002,
|
| 7974 |
+
"num_tokens": 16137834.0,
|
| 7975 |
+
"step": 4425
|
| 7976 |
+
},
|
| 7977 |
+
{
|
| 7978 |
+
"epoch": 34.07692307692308,
|
| 7979 |
+
"grad_norm": 0.0,
|
| 7980 |
+
"learning_rate": 2.7855000000000004e-05,
|
| 7981 |
+
"loss": 1.6805,
|
| 7982 |
+
"mean_token_accuracy": 0.6666524916887283,
|
| 7983 |
+
"num_tokens": 16156663.0,
|
| 7984 |
+
"step": 4430
|
| 7985 |
}
|
| 7986 |
],
|
| 7987 |
"logging_steps": 5,
|
|
|
|
| 8001 |
"attributes": {}
|
| 8002 |
}
|
| 8003 |
},
|
| 8004 |
+
"total_flos": 8.187926188887245e+17,
|
| 8005 |
"train_batch_size": 4,
|
| 8006 |
"trial_name": null,
|
| 8007 |
"trial_params": null
|