Training in progress, step 2030, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b905651374eb2e59d0098ec78dfa8fd628bebad699c69be6259081f8ca6eed83
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00f2dda045580becfc005e53e68449b8bb0898dc88d89856d32ed14d13b1d111
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69278b4a3681b01d8f701e80b23385d7d42b83b4d66e68ecd0a5a2973bcf8f5b
|
| 3 |
size 14645
|
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 sha256:6d5461865fd39a6a349b4cd5c7ceb6252061309c8a68ee111d9578fa57092966
|
| 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": 0.
|
| 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,
|
|
@@ -2038,6 +2038,16 @@
|
|
| 2038 |
"mean_token_accuracy": 0.7832586973905563,
|
| 2039 |
"num_tokens": 9360075.0,
|
| 2040 |
"step": 2020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2041 |
}
|
| 2042 |
],
|
| 2043 |
"logging_steps": 10,
|
|
@@ -2057,7 +2067,7 @@
|
|
| 2057 |
"attributes": {}
|
| 2058 |
}
|
| 2059 |
},
|
| 2060 |
-
"total_flos": 4.
|
| 2061 |
"train_batch_size": 4,
|
| 2062 |
"trial_name": null,
|
| 2063 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.43306666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2038 |
"mean_token_accuracy": 0.7832586973905563,
|
| 2039 |
"num_tokens": 9360075.0,
|
| 2040 |
"step": 2020
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"entropy": 0.9146695531904697,
|
| 2044 |
+
"epoch": 0.43306666666666666,
|
| 2045 |
+
"grad_norm": 0.33491751551628113,
|
| 2046 |
+
"learning_rate": 9.13096172752704e-05,
|
| 2047 |
+
"loss": 0.9856008529663086,
|
| 2048 |
+
"mean_token_accuracy": 0.7726532012224198,
|
| 2049 |
+
"num_tokens": 9396928.0,
|
| 2050 |
+
"step": 2030
|
| 2051 |
}
|
| 2052 |
],
|
| 2053 |
"logging_steps": 10,
|
|
|
|
| 2067 |
"attributes": {}
|
| 2068 |
}
|
| 2069 |
},
|
| 2070 |
+
"total_flos": 4.459659291556147e+16,
|
| 2071 |
"train_batch_size": 4,
|
| 2072 |
"trial_name": null,
|
| 2073 |
"trial_params": null
|