tuanna08go
commited on
Training in progress, step 15, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0198d4ed2d7b975559a2d084adaabd271b412fc21c2249c2597fb4bfcc3e92a2
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46cbaeb13a38c0123abe9c140dfcda94d2d33755b07fd5c42fe42af324caacaf
|
3 |
size 43122580
|
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:b542fbd0a9224550cadec27dc6708567a414ecfe90e076df0634e488bd0b9dcc
|
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:a72cb13506d816c905eeab58110179a6a089148e55e5ed8b6d7eca1563ab5a6e
|
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": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -38,6 +38,14 @@
|
|
38 |
"learning_rate": 5.868240888334653e-05,
|
39 |
"loss": 2.1898,
|
40 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"logging_steps": 10,
|
@@ -57,7 +65,7 @@
|
|
57 |
"attributes": {}
|
58 |
}
|
59 |
},
|
60 |
-
"total_flos":
|
61 |
"train_batch_size": 8,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7547169811320755,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
38 |
"learning_rate": 5.868240888334653e-05,
|
39 |
"loss": 2.1898,
|
40 |
"step": 10
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.6037735849056604,
|
44 |
+
"eval_loss": 0.010044231079518795,
|
45 |
+
"eval_runtime": 7.259,
|
46 |
+
"eval_samples_per_second": 18.46,
|
47 |
+
"eval_steps_per_second": 2.342,
|
48 |
+
"step": 12
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 10,
|
|
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
+
"total_flos": 4.438954195550208e+16,
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|