Training in progress, step 4, 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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c02b9f37302900e66e1552c2677161fa62a8a14a5382f52a383b70887e0c30b
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64219860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaf276fdacd0db3e8907c333704f8d26a21f43a0c86a763be6b03f849cd304a0
|
3 |
size 64219860
|
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 sha256:41ae54b5e63e82884cc8216afa89f8f2561c547f1fa2982921ac363ebc4b962f
|
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:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -37,6 +37,28 @@
|
|
37 |
"eval_samples_per_second": 17.356,
|
38 |
"eval_steps_per_second": 8.678,
|
39 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 1,
|
@@ -56,7 +78,7 @@
|
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
-
"total_flos":
|
60 |
"train_batch_size": 2,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0002451149359254238,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
37 |
"eval_samples_per_second": 17.356,
|
38 |
"eval_steps_per_second": 8.678,
|
39 |
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.00018383620194406782,
|
43 |
+
"grad_norm": 8.999253273010254,
|
44 |
+
"learning_rate": 3e-05,
|
45 |
+
"loss": 33.9703,
|
46 |
+
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.0002451149359254238,
|
50 |
+
"grad_norm": 9.006853103637695,
|
51 |
+
"learning_rate": 4e-05,
|
52 |
+
"loss": 31.5724,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.0002451149359254238,
|
57 |
+
"eval_loss": 1.9366836547851562,
|
58 |
+
"eval_runtime": 1569.4882,
|
59 |
+
"eval_samples_per_second": 17.512,
|
60 |
+
"eval_steps_per_second": 8.756,
|
61 |
+
"step": 4
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 1,
|
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
+
"total_flos": 5699167510855680.0,
|
82 |
"train_batch_size": 2,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|