Training in progress, step 25, 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 201892112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be9d2efb9e317fc6772e56f800552745bbfa573be0e138980248abdf7ea0344d
|
3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102864548
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f63d6b848cf583a4f54b6c39c1c464c5378f12e7d597e5e1eaa34406776367f
|
3 |
size 102864548
|
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 sha256:584f9af47faa33f58e366891684daa24bbcfd0788a48868de15ac3d036b8b6b0
|
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 sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -89,6 +89,28 @@
|
|
89 |
"eval_samples_per_second": 49.28,
|
90 |
"eval_steps_per_second": 6.163,
|
91 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
}
|
93 |
],
|
94 |
"logging_steps": 3,
|
@@ -108,7 +130,7 @@
|
|
108 |
"attributes": {}
|
109 |
}
|
110 |
},
|
111 |
-
"total_flos":
|
112 |
"train_batch_size": 8,
|
113 |
"trial_name": null,
|
114 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.011756407241946862,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
89 |
"eval_samples_per_second": 49.28,
|
90 |
"eval_steps_per_second": 6.163,
|
91 |
"step": 20
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.009875382083235363,
|
95 |
+
"grad_norm": 0.5509119033813477,
|
96 |
+
"learning_rate": 8.247240241650918e-05,
|
97 |
+
"loss": 1.1259,
|
98 |
+
"step": 21
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.011286150952268986,
|
102 |
+
"grad_norm": 0.48853400349617004,
|
103 |
+
"learning_rate": 7.269952498697734e-05,
|
104 |
+
"loss": 1.1989,
|
105 |
+
"step": 24
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.011756407241946862,
|
109 |
+
"eval_loss": 1.1405397653579712,
|
110 |
+
"eval_runtime": 72.6738,
|
111 |
+
"eval_samples_per_second": 49.289,
|
112 |
+
"eval_steps_per_second": 6.165,
|
113 |
+
"step": 25
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 3,
|
|
|
130 |
"attributes": {}
|
131 |
}
|
132 |
},
|
133 |
+
"total_flos": 5332869631180800.0,
|
134 |
"train_batch_size": 8,
|
135 |
"trial_name": null,
|
136 |
"trial_params": null
|