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 41581360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8d70b39222fd2831e5d3f77d49e254021c1ce7043156dc26419dd9cf88065f
|
3 |
size 41581360
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21505540
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c168fc04afea9dc48670a6fc5c2f0373b360bbae819d6c15203845a3782715d
|
3 |
size 21505540
|
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:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
|
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": 75.032,
|
38 |
"eval_steps_per_second": 37.848,
|
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": 0.05998125585754452,
|
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": 75.032,
|
38 |
"eval_steps_per_second": 37.848,
|
39 |
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04498594189315839,
|
43 |
+
"grad_norm": 9.607409477233887,
|
44 |
+
"learning_rate": 3e-05,
|
45 |
+
"loss": 3.4362,
|
46 |
+
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.05998125585754452,
|
50 |
+
"grad_norm": 10.251847267150879,
|
51 |
+
"learning_rate": 4e-05,
|
52 |
+
"loss": 3.2573,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.05998125585754452,
|
57 |
+
"eval_loss": 2.9723637104034424,
|
58 |
+
"eval_runtime": 1.5083,
|
59 |
+
"eval_samples_per_second": 74.918,
|
60 |
+
"eval_steps_per_second": 37.79,
|
61 |
+
"step": 4
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 1,
|
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
+
"total_flos": 800155729133568.0,
|
82 |
"train_batch_size": 2,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|