Training in progress, step 540, 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 sha256:0f5ee6c2770596bacb9ce0d74db2ac26e807046b841be3701c7620f97aaf96e7
|
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:d6132468edad037891ff42a5b7df7168aa7a52ede9007dd578443a04fb7f85a2
|
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:da0376d0c2c8d9893ef28b6acbf650807626b4017e98a7675bfde05e30f086f7
|
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 sha256:9c3bdda5816887e8bec9ed0343f3e3500a6daf7fc061f720f9e8b837e510c8be
|
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": 1.
|
5 |
"eval_steps": 60,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -111,13 +111,26 @@
|
|
111 |
"eval_samples_per_second": 1.915,
|
112 |
"eval_steps_per_second": 0.239,
|
113 |
"step": 480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 60,
|
117 |
"max_steps": 1011,
|
118 |
"num_train_epochs": 3,
|
119 |
"save_steps": 60,
|
120 |
-
"total_flos":
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 540,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
111 |
"eval_samples_per_second": 1.915,
|
112 |
"eval_steps_per_second": 0.239,
|
113 |
"step": 480
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.6,
|
117 |
+
"learning_rate": 0.0002,
|
118 |
+
"loss": 0.569,
|
119 |
+
"step": 540
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.6,
|
123 |
+
"eval_runtime": 313.3538,
|
124 |
+
"eval_samples_per_second": 1.915,
|
125 |
+
"eval_steps_per_second": 0.239,
|
126 |
+
"step": 540
|
127 |
}
|
128 |
],
|
129 |
"logging_steps": 60,
|
130 |
"max_steps": 1011,
|
131 |
"num_train_epochs": 3,
|
132 |
"save_steps": 60,
|
133 |
+
"total_flos": 8.969458437586944e+16,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|