Training in progress, step 289, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:121295b2b22ccacbb358f407723b1ecbe5fc47272371aae6c4ebe1121aa8e6c5
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37431220
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07b1cfc78181126f7ff856497c9c819f03a388066e7f612ef97f28acc940ea43
|
3 |
size 37431220
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a413486fbe876b5d13f54e47216896bd97b3e8e9188c7f5c0091ef8570249ad4
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -2016,6 +2016,20 @@
|
|
2016 |
"learning_rate": 5.833333333333334e-05,
|
2017 |
"loss": 1.1807,
|
2018 |
"step": 287
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2019 |
}
|
2020 |
],
|
2021 |
"logging_steps": 1,
|
@@ -2035,7 +2049,7 @@
|
|
2035 |
"attributes": {}
|
2036 |
}
|
2037 |
},
|
2038 |
-
"total_flos": 3.
|
2039 |
"train_batch_size": 4,
|
2040 |
"trial_name": null,
|
2041 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7928669410150891,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 289,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2016 |
"learning_rate": 5.833333333333334e-05,
|
2017 |
"loss": 1.1807,
|
2018 |
"step": 287
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.7901234567901234,
|
2022 |
+
"grad_norm": 0.15906862914562225,
|
2023 |
+
"learning_rate": 5.757575757575758e-05,
|
2024 |
+
"loss": 1.1282,
|
2025 |
+
"step": 288
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.7928669410150891,
|
2029 |
+
"grad_norm": 0.16204234957695007,
|
2030 |
+
"learning_rate": 5.6818181818181825e-05,
|
2031 |
+
"loss": 1.1278,
|
2032 |
+
"step": 289
|
2033 |
}
|
2034 |
],
|
2035 |
"logging_steps": 1,
|
|
|
2049 |
"attributes": {}
|
2050 |
}
|
2051 |
},
|
2052 |
+
"total_flos": 3.575919377014456e+17,
|
2053 |
"train_batch_size": 4,
|
2054 |
"trial_name": null,
|
2055 |
"trial_params": null
|