Training in progress, step 12, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4d2970ab1d6ad891bf59a3818940f5d85d33b1b9b914ec8493eab147e39fbae
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 127788180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c746814e5a3aadcbcdf9e929ce14d6cfd555742510c0f5a64ee967a6372434
|
3 |
size 127788180
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a16e0cbf69d1d7bff64db471cb64149f07c4facf42e6acec78fcc9dc0cc66894
|
3 |
size 14244
|
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 sha256:5c3f3d5c4a86eb24d6104ecbafd33bca7426420d96c84e1b2c30df274293a5af
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -39,6 +39,21 @@
|
|
39 |
"eval_samples_per_second": 9.76,
|
40 |
"eval_steps_per_second": 6.507,
|
41 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 10,
|
@@ -53,12 +68,12 @@
|
|
53 |
"should_evaluate": false,
|
54 |
"should_log": false,
|
55 |
"should_save": true,
|
56 |
-
"should_training_stop":
|
57 |
},
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
-
"total_flos":
|
62 |
"train_batch_size": 2,
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 12,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
39 |
"eval_samples_per_second": 9.76,
|
40 |
"eval_steps_per_second": 6.507,
|
41 |
"step": 9
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.8333333333333334,
|
45 |
+
"grad_norm": 1.1259316205978394,
|
46 |
+
"learning_rate": 0.0002,
|
47 |
+
"loss": 1.6216,
|
48 |
+
"step": 10
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.0,
|
52 |
+
"eval_loss": 0.41837990283966064,
|
53 |
+
"eval_runtime": 0.3135,
|
54 |
+
"eval_samples_per_second": 9.568,
|
55 |
+
"eval_steps_per_second": 6.379,
|
56 |
+
"step": 12
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 10,
|
|
|
68 |
"should_evaluate": false,
|
69 |
"should_log": false,
|
70 |
"should_save": true,
|
71 |
+
"should_training_stop": true
|
72 |
},
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
+
"total_flos": 3015219232112640.0,
|
77 |
"train_batch_size": 2,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|