Training in progress, step 800, 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 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dc0dec55c3008c4e06b05c2c6399fd0b2087d83a1959d6bd37c0b30ab55397c
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20524127
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:406f0543a6da379c3a07397e363fea8776e66421d39ca05d9149e520a54e989a
|
3 |
size 20524127
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ed6b2ccb6b511d4a5b0a951ff64fe81b3f72732119d339d43b6ec843aa012e1
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fa67daeb64419974086372ba8aca20c65ba993b273167e2568257f8e5992653
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -98,13 +98,26 @@
|
|
98 |
"eval_samples_per_second": 1.756,
|
99 |
"eval_steps_per_second": 0.221,
|
100 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 100,
|
104 |
"max_steps": 957,
|
105 |
"num_train_epochs": 3,
|
106 |
"save_steps": 100,
|
107 |
-
"total_flos": 1.
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.507836990595611,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"eval_samples_per_second": 1.756,
|
99 |
"eval_steps_per_second": 0.221,
|
100 |
"step": 700
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.51,
|
104 |
+
"learning_rate": 0.0002,
|
105 |
+
"loss": 0.4752,
|
106 |
+
"step": 800
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 2.51,
|
110 |
+
"eval_runtime": 513.4451,
|
111 |
+
"eval_samples_per_second": 1.753,
|
112 |
+
"eval_steps_per_second": 0.22,
|
113 |
+
"step": 800
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 100,
|
117 |
"max_steps": 957,
|
118 |
"num_train_epochs": 3,
|
119 |
"save_steps": 100,
|
120 |
+
"total_flos": 1.3279781520094003e+17,
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|