Training in progress, step 27, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cfb84e66e6d7e6ac9cb1fba4e7fe0194263d9a4f3624128ea2c3e7b48ca92a2
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 85723284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:807363c14a34f42629792a1dcd97052ae3445965d99cfce3b7ced0835245fa04
|
3 |
size 85723284
|
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:cc3af19de247348acb313345a43a4aa9e3e74629a4910adb275427735ab53b92
|
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 sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -73,6 +73,35 @@
|
|
73 |
"eval_samples_per_second": 12.085,
|
74 |
"eval_steps_per_second": 1.549,
|
75 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 3,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 8,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.19424460431654678,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 27,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"eval_samples_per_second": 12.085,
|
74 |
"eval_steps_per_second": 1.549,
|
75 |
"step": 18
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.1510791366906475,
|
79 |
+
"grad_norm": 2.4984405040740967,
|
80 |
+
"learning_rate": 4.817959636416969e-05,
|
81 |
+
"loss": 4.4278,
|
82 |
+
"step": 21
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.17266187050359713,
|
86 |
+
"grad_norm": 2.3186981678009033,
|
87 |
+
"learning_rate": 4.707368982147318e-05,
|
88 |
+
"loss": 4.4248,
|
89 |
+
"step": 24
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.19424460431654678,
|
93 |
+
"grad_norm": 2.286144733428955,
|
94 |
+
"learning_rate": 4.572593931387604e-05,
|
95 |
+
"loss": 4.4557,
|
96 |
+
"step": 27
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.19424460431654678,
|
100 |
+
"eval_loss": 1.0573580265045166,
|
101 |
+
"eval_runtime": 19.3833,
|
102 |
+
"eval_samples_per_second": 12.072,
|
103 |
+
"eval_steps_per_second": 1.548,
|
104 |
+
"step": 27
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 4.605498216362803e+16,
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|