Training in progress, step 26, 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 109009752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56a7143eb127d2a8c89687af5d55981cb801945ec29a1e7c68370da5884a1e19
|
3 |
size 109009752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56088148
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70c44a4a5f4f7a5325baa9bc5602044187d7ba256cd06840336c01ff0fb773b
|
3 |
size 56088148
|
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:d44674e2e3b9f7554311b4e60eca4d2c20155a8871289e702a9e642015db6204
|
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 sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -30,6 +30,21 @@
|
|
30 |
"eval_samples_per_second": 15.636,
|
31 |
"eval_steps_per_second": 7.818,
|
32 |
"step": 13
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 10,
|
@@ -49,7 +64,7 @@
|
|
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": 0.0007303114356939714,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 26,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_samples_per_second": 15.636,
|
31 |
"eval_steps_per_second": 7.818,
|
32 |
"step": 13
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.0005617780274569011,
|
36 |
+
"grad_norm": 0.3594229519367218,
|
37 |
+
"learning_rate": 0.00015000000000000001,
|
38 |
+
"loss": 0.3801,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0007303114356939714,
|
43 |
+
"eval_loss": 0.38734641671180725,
|
44 |
+
"eval_runtime": 957.8246,
|
45 |
+
"eval_samples_per_second": 15.65,
|
46 |
+
"eval_steps_per_second": 7.825,
|
47 |
+
"step": 26
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
+
"total_flos": 9135190211297280.0,
|
68 |
"train_batch_size": 2,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|