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 15182728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87cb35f2801d4586a56fefa8e4d06b73ee39b878090164472570fc76e26aef30
|
3 |
size 15182728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8075796
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27455fc081a929f79575809baa0887a8d2711eb590c8dc631080da396f996afd
|
3 |
size 8075796
|
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 sha256:5c1af7ea30e9f011a819d820433d75f698f846808436042fe9ed21f92292b7c3
|
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 sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -37,6 +37,35 @@
|
|
37 |
"eval_samples_per_second": 28.066,
|
38 |
"eval_steps_per_second": 14.033,
|
39 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 5,
|
@@ -56,7 +85,7 @@
|
|
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": 0.34551495016611294,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 26,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
37 |
"eval_samples_per_second": 28.066,
|
38 |
"eval_steps_per_second": 14.033,
|
39 |
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.19933554817275748,
|
43 |
+
"grad_norm": 3.3211214542388916,
|
44 |
+
"learning_rate": 9.619397662556435e-05,
|
45 |
+
"loss": 2.4196,
|
46 |
+
"step": 15
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.26578073089701,
|
50 |
+
"grad_norm": 3.485300302505493,
|
51 |
+
"learning_rate": 8.535533905932738e-05,
|
52 |
+
"loss": 2.1031,
|
53 |
+
"step": 20
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.26578073089701,
|
57 |
+
"eval_loss": 2.3668720722198486,
|
58 |
+
"eval_runtime": 1.2122,
|
59 |
+
"eval_samples_per_second": 26.399,
|
60 |
+
"eval_steps_per_second": 13.2,
|
61 |
+
"step": 20
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.33222591362126247,
|
65 |
+
"grad_norm": 2.3391213417053223,
|
66 |
+
"learning_rate": 6.91341716182545e-05,
|
67 |
+
"loss": 2.0734,
|
68 |
+
"step": 25
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
+
"total_flos": 199481886769152.0,
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|