Training in progress, step 4420, 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:e63e064851a0ccb8347711a57130da48526e6dc833f2b3b937c846ac4c71251c
|
| 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 sha256:1e85170decd009a55c9f4546f9ff81bf133e3d7d09635d49c15d6b9dd758de35
|
| 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:e050b2d24740ad8a3ebee3c408c31c987593e16f2eb75622d4230053ecdf33bf
|
| 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,
|
|
@@ -7946,6 +7946,24 @@
|
|
| 7946 |
"mean_token_accuracy": 0.652796396613121,
|
| 7947 |
"num_tokens": 16083292.0,
|
| 7948 |
"step": 4410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7949 |
}
|
| 7950 |
],
|
| 7951 |
"logging_steps": 5,
|
|
@@ -7965,7 +7983,7 @@
|
|
| 7965 |
"attributes": {}
|
| 7966 |
}
|
| 7967 |
},
|
| 7968 |
-
"total_flos": 8.
|
| 7969 |
"train_batch_size": 4,
|
| 7970 |
"trial_name": null,
|
| 7971 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7946 |
"mean_token_accuracy": 0.652796396613121,
|
| 7947 |
"num_tokens": 16083292.0,
|
| 7948 |
"step": 4410
|
| 7949 |
+
},
|
| 7950 |
+
{
|
| 7951 |
+
"epoch": 33.96153846153846,
|
| 7952 |
+
"grad_norm": 0.0,
|
| 7953 |
+
"learning_rate": 2.7930000000000002e-05,
|
| 7954 |
+
"loss": 1.7136,
|
| 7955 |
+
"mean_token_accuracy": 0.654367059469223,
|
| 7956 |
+
"num_tokens": 16101807.0,
|
| 7957 |
+
"step": 4415
|
| 7958 |
+
},
|
| 7959 |
+
{
|
| 7960 |
+
"epoch": 34.0,
|
| 7961 |
+
"grad_norm": 0.0,
|
| 7962 |
+
"learning_rate": 2.7905000000000005e-05,
|
| 7963 |
+
"loss": 1.7799,
|
| 7964 |
+
"mean_token_accuracy": 0.644026267528534,
|
| 7965 |
+
"num_tokens": 16119570.0,
|
| 7966 |
+
"step": 4420
|
| 7967 |
}
|
| 7968 |
],
|
| 7969 |
"logging_steps": 5,
|
|
|
|
| 7983 |
"attributes": {}
|
| 7984 |
}
|
| 7985 |
},
|
| 7986 |
+
"total_flos": 8.168666278448333e+17,
|
| 7987 |
"train_batch_size": 4,
|
| 7988 |
"trial_name": null,
|
| 7989 |
"trial_params": null
|