Training in progress, step 15, 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 2373352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a55ff1f0f00824c859bc14e5aaf1073d5dc73090c93ca88ebf50d38591c854e
|
3 |
size 2373352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4830714
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a883ca51a5f160905741ffb34ccda858e11d9f05fdf4244fa056538f9508d5f
|
3 |
size 4830714
|
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:e1ec70e5c25cb47fe3815029290a7edc4d0b592e520ac9a83fe282041e1d4d4f
|
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:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -52,6 +52,28 @@
|
|
52 |
"eval_samples_per_second": 135.047,
|
53 |
"eval_steps_per_second": 16.922,
|
54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
@@ -71,7 +93,7 @@
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
-
"total_flos":
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008843036109064112,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"eval_samples_per_second": 135.047,
|
53 |
"eval_steps_per_second": 16.922,
|
54 |
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.00707442888725129,
|
58 |
+
"grad_norm": 0.4747415781021118,
|
59 |
+
"learning_rate": 9.938441702975689e-05,
|
60 |
+
"loss": 11.9255,
|
61 |
+
"step": 12
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.008843036109064112,
|
65 |
+
"grad_norm": 0.5072726607322693,
|
66 |
+
"learning_rate": 9.619397662556435e-05,
|
67 |
+
"loss": 11.9161,
|
68 |
+
"step": 15
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.008843036109064112,
|
72 |
+
"eval_loss": 11.908404350280762,
|
73 |
+
"eval_runtime": 21.5643,
|
74 |
+
"eval_samples_per_second": 132.488,
|
75 |
+
"eval_steps_per_second": 16.602,
|
76 |
+
"step": 15
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 3,
|
|
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 16526868480000.0,
|
97 |
"train_batch_size": 8,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|