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 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21f1cb12ec6dd2d4aa8d26fe10259535f69d064ac22b2d8e516c172b54477e73
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:457e51e4f200eb4aa3921a5a160def2ae1569e11b5f85b55ff33066bd68a0d5c
|
3 |
size 640009682
|
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 sha256:39acb5a2530dc832149c5d18e7a15da6846a800c716036ccf187a7e397862da3
|
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:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
|
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": 5.92,
|
74 |
"eval_steps_per_second": 2.96,
|
75 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 3,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.318232044198895,
|
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": 5.92,
|
74 |
"eval_steps_per_second": 2.96,
|
75 |
"step": 18
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.24751381215469614,
|
79 |
+
"grad_norm": 37.68834686279297,
|
80 |
+
"learning_rate": 0.00014994217771805422,
|
81 |
+
"loss": 78.5547,
|
82 |
+
"step": 21
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.2828729281767956,
|
86 |
+
"grad_norm": 36.297088623046875,
|
87 |
+
"learning_rate": 0.00014907662554463532,
|
88 |
+
"loss": 71.8931,
|
89 |
+
"step": 24
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.318232044198895,
|
93 |
+
"grad_norm": 40.15138244628906,
|
94 |
+
"learning_rate": 0.0001471841427340235,
|
95 |
+
"loss": 68.7287,
|
96 |
+
"step": 27
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.318232044198895,
|
100 |
+
"eval_loss": 2.1229209899902344,
|
101 |
+
"eval_runtime": 48.3187,
|
102 |
+
"eval_samples_per_second": 5.919,
|
103 |
+
"eval_steps_per_second": 2.96,
|
104 |
+
"step": 27
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 1.419972205168558e+17,
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|