Upload folder using huggingface_hub
Browse files- adapter_model.bin +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +17 -3
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4994175
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c9efca0a41b1fa0a7d2c73a7c0668d7fdd266dbc38b22073b3785ec1a03d107
|
3 |
size 4994175
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2506975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e7334e269ed3f118133b4e9a64cbdd8962344cc1a926a089fc1f3a3aaa49ce
|
3 |
size 2506975
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb21a3129c20b585a208f88d463aa0b3f24c0c1cd36c5d747317950a557c052
|
3 |
size 14575
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37b925d914a427f9d777adc61a9630c02045830538343e941aba5fd083fe36b9
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -49,13 +49,27 @@
|
|
49 |
"eval_samples_per_second": 2.635,
|
50 |
"eval_steps_per_second": 1.318,
|
51 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 20,
|
55 |
"max_steps": 500,
|
56 |
"num_train_epochs": 2,
|
57 |
"save_steps": 20,
|
58 |
-
"total_flos":
|
59 |
"trial_name": null,
|
60 |
"trial_params": null
|
61 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.21447721179624665,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 80,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
49 |
"eval_samples_per_second": 2.635,
|
50 |
"eval_steps_per_second": 1.318,
|
51 |
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.21,
|
55 |
+
"learning_rate": 1.6969696969696972e-05,
|
56 |
+
"loss": 2.0875,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.21,
|
61 |
+
"eval_loss": 2.063451051712036,
|
62 |
+
"eval_runtime": 124.438,
|
63 |
+
"eval_samples_per_second": 2.636,
|
64 |
+
"eval_steps_per_second": 1.318,
|
65 |
+
"step": 80
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 20,
|
69 |
"max_steps": 500,
|
70 |
"num_train_epochs": 2,
|
71 |
"save_steps": 20,
|
72 |
+
"total_flos": 3.037389329006592e+16,
|
73 |
"trial_name": null,
|
74 |
"trial_params": null
|
75 |
}
|