Upload folder using huggingface_hub
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +10 -3
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 406933384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e25a93fb675087db31f46d3ab515e7cf06d50ded08db134fdedc7e79838bae3
|
3 |
size 406933384
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 814251306
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62a6c487c535db775dd9e1a7771e745d299dae076213ae39dfe2c8274d56fdfd
|
3 |
size 814251306
|
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 sha256:36514a89f2dd91a64cc1a12407b38606392cc7a71127c82ec2d39843cbe15703
|
3 |
size 1064
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
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,
|
@@ -56,6 +56,13 @@
|
|
56 |
"learning_rate": 2.0156046814044216e-06,
|
57 |
"loss": 0.8124,
|
58 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
}
|
60 |
],
|
61 |
"logging_steps": 100,
|
@@ -75,7 +82,7 @@
|
|
75 |
"attributes": {}
|
76 |
}
|
77 |
},
|
78 |
-
"total_flos":
|
79 |
"train_batch_size": 16,
|
80 |
"trial_name": null,
|
81 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.807017543859649,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
56 |
"learning_rate": 2.0156046814044216e-06,
|
57 |
"loss": 0.8124,
|
58 |
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 2.807017543859649,
|
62 |
+
"grad_norm": 1.4423238039016724,
|
63 |
+
"learning_rate": 7.15214564369311e-07,
|
64 |
+
"loss": 0.7947,
|
65 |
+
"step": 800
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 100,
|
|
|
82 |
"attributes": {}
|
83 |
}
|
84 |
},
|
85 |
+
"total_flos": 5.13850968947841e+17,
|
86 |
"train_batch_size": 16,
|
87 |
"trial_name": null,
|
88 |
"trial_params": null
|