Training in progress, step 16, 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 604317736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36fc67ee49a94db964b47494913a07681852f57d17b0b3d9c6c2c46001e3bddf
|
3 |
size 604317736
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:240ceb61e571c1b271acebdf3e88758ba65f8c49891cba28e2e9f0a9afbefeab
|
3 |
size 41119636
|
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:dc7c3dcfd2fbfcccbf5177669f5b109776dfbae391c64a8d0d5e2326b72c5b68
|
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:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
|
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": 6,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -30,6 +30,28 @@
|
|
30 |
"eval_samples_per_second": 13.984,
|
31 |
"eval_steps_per_second": 7.53,
|
32 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 5,
|
@@ -49,7 +71,7 @@
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
-
"total_flos":
|
53 |
"train_batch_size": 2,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5378151260504201,
|
5 |
"eval_steps": 6,
|
6 |
+
"global_step": 16,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_samples_per_second": 13.984,
|
31 |
"eval_steps_per_second": 7.53,
|
32 |
"step": 6
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.33613445378151263,
|
36 |
+
"grad_norm": 0.6221334934234619,
|
37 |
+
"learning_rate": 0.0001,
|
38 |
+
"loss": 0.2676,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.40336134453781514,
|
43 |
+
"eval_loss": 0.019643442705273628,
|
44 |
+
"eval_runtime": 0.9567,
|
45 |
+
"eval_samples_per_second": 13.589,
|
46 |
+
"eval_steps_per_second": 7.317,
|
47 |
+
"step": 12
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.5042016806722689,
|
51 |
+
"grad_norm": 0.08144775032997131,
|
52 |
+
"learning_rate": 8.535533905932738e-05,
|
53 |
+
"loss": 0.0289,
|
54 |
+
"step": 15
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 5,
|
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
+
"total_flos": 2605974628073472.0,
|
75 |
"train_batch_size": 2,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|