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 sha256:7928cc861b0c29b902b3401ba6bd3ef6b7d27d267766af35ee45f1dd7ed291cb
|
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:e7bcbbffafdf73d3d2f9ebb1b88eca4f3b57af07cab98759686b5340aa2b2ae8
|
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 sha256:6988304369cf1930141352fe7025e91f20bdfbba03640e6a295c2917f2efb5d3
|
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": 13.353,
|
38 |
"eval_steps_per_second": 6.677,
|
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": 0.06237816764132553,
|
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": 13.353,
|
38 |
"eval_steps_per_second": 6.677,
|
39 |
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04678362573099415,
|
43 |
+
"grad_norm": 2.17221999168396,
|
44 |
+
"learning_rate": 3e-05,
|
45 |
+
"loss": 15.2007,
|
46 |
+
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.06237816764132553,
|
50 |
+
"grad_norm": 2.0967655181884766,
|
51 |
+
"learning_rate": 4e-05,
|
52 |
+
"loss": 14.3259,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.06237816764132553,
|
57 |
+
"eval_loss": 0.9278036952018738,
|
58 |
+
"eval_runtime": 13.6763,
|
59 |
+
"eval_samples_per_second": 7.897,
|
60 |
+
"eval_steps_per_second": 3.948,
|
61 |
+
"step": 4
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 1,
|
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
+
"total_flos": 1.005269824831488e+16,
|
82 |
"train_batch_size": 2,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|