Training in progress, step 900, 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 sha256:7928893400b46dcb29642a403c24b8f22b024fddc25b60538a31c85c1ad8865b
|
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 21689885
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1086fe9363f82aec5d220614e79a6fc2421d31fe34ca1c9fa9612a1c28fc43ba
|
3 |
size 21689885
|
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 sha256:9c31fdd7bc052e2da00f42fa4208407109642b65360d36af47981ba37b94fb7b
|
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 sha256:41ec64ba9e76742780de858ce14668285049f1680bae66c1352aa2d20d3be491
|
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": 100,
|
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": 1.779,
|
112 |
"eval_steps_per_second": 0.223,
|
113 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 100,
|
117 |
"max_steps": 1686,
|
118 |
"num_train_epochs": 3,
|
119 |
"save_steps": 100,
|
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": 100,
|
6 |
+
"global_step": 900,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
111 |
"eval_samples_per_second": 1.779,
|
112 |
"eval_steps_per_second": 0.223,
|
113 |
"step": 800
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.6,
|
117 |
+
"learning_rate": 0.0001,
|
118 |
+
"loss": 0.5724,
|
119 |
+
"step": 900
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.6,
|
123 |
+
"eval_runtime": 1402.9928,
|
124 |
+
"eval_samples_per_second": 1.782,
|
125 |
+
"eval_steps_per_second": 0.223,
|
126 |
+
"step": 900
|
127 |
}
|
128 |
],
|
129 |
"logging_steps": 100,
|
130 |
"max_steps": 1686,
|
131 |
"num_train_epochs": 3,
|
132 |
"save_steps": 100,
|
133 |
+
"total_flos": 3.259733737734144e+17,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|