Training in progress, step 35, 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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdae13e8231a3a0b22a1a0f44d1c39bb4e8cd5a86ba21fd05280221f08f687b6
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 341314196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b43d2e450a76e4a908689c1a1e50d6c551af925d8ca406764b869f85ad183679
|
3 |
size 341314196
|
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:f2b703739f5454d2894fcbb8e649647ab136cbeb65534f344ebd4100fb9a50e7
|
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 sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
|
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,
|
@@ -133,6 +133,21 @@
|
|
133 |
"eval_samples_per_second": 6.321,
|
134 |
"eval_steps_per_second": 0.817,
|
135 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 3,
|
@@ -152,7 +167,7 @@
|
|
152 |
"attributes": {}
|
153 |
}
|
154 |
},
|
155 |
-
"total_flos":
|
156 |
"train_batch_size": 8,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.28169014084507044,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 35,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"eval_samples_per_second": 6.321,
|
134 |
"eval_steps_per_second": 0.817,
|
135 |
"step": 30
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.2655935613682093,
|
139 |
+
"grad_norm": 0.037129033356904984,
|
140 |
+
"learning_rate": 3.832773180720475e-05,
|
141 |
+
"loss": 0.0068,
|
142 |
+
"step": 33
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.28169014084507044,
|
146 |
+
"eval_loss": 0.007025540340691805,
|
147 |
+
"eval_runtime": 33.0263,
|
148 |
+
"eval_samples_per_second": 6.328,
|
149 |
+
"eval_steps_per_second": 0.818,
|
150 |
+
"step": 35
|
151 |
}
|
152 |
],
|
153 |
"logging_steps": 3,
|
|
|
167 |
"attributes": {}
|
168 |
}
|
169 |
},
|
170 |
+
"total_flos": 1.04841693722837e+17,
|
171 |
"train_batch_size": 8,
|
172 |
"trial_name": null,
|
173 |
"trial_params": null
|