tuanna08go
commited on
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 6804608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f54e84880456bd810f698865f527b85e934e8a7d66bf4351e0a33a4dc31f032
|
3 |
size 6804608
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3633530
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3a693b11b0e42472ec02909ca0a95eb4d582b10a939398de162b7fe17734924
|
3 |
size 3633530
|
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 sha256:9eda220ee3a708217e3360f735df149c9943b926da8f17d7f7ca9a33ad2afc6b
|
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 sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
|
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,
|
@@ -30,6 +30,21 @@
|
|
30 |
"eval_samples_per_second": 172.013,
|
31 |
"eval_steps_per_second": 21.514,
|
32 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 10,
|
@@ -49,7 +64,7 @@
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
-
"total_flos":
|
53 |
"train_batch_size": 8,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.019736217857481735,
|
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,
|
|
|
30 |
"eval_samples_per_second": 172.013,
|
31 |
"eval_steps_per_second": 21.514,
|
32 |
"step": 10
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.015181706044216719,
|
36 |
+
"grad_norm": 0.32615259289741516,
|
37 |
+
"learning_rate": 6.91341716182545e-05,
|
38 |
+
"loss": 2.7322,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.015181706044216719,
|
43 |
+
"eval_loss": 2.9421498775482178,
|
44 |
+
"eval_runtime": 52.2462,
|
45 |
+
"eval_samples_per_second": 169.869,
|
46 |
+
"eval_steps_per_second": 21.246,
|
47 |
+
"step": 20
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
+
"total_flos": 1995832257675264.0,
|
68 |
"train_batch_size": 8,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|