Training in progress, step 30, 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 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56459a07aad686fc5859320202935b852d51f92e6d7c2e0097cb341aacea546
|
3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:976bf27ed037770fa88bc6e0bbed3489162a0bf617afa80bea7687abfe620417
|
3 |
size 328468404
|
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 sha256:8572479df9e638b99d9607eeea0c39cc7d3f7fd2dc1ba67aa8a69c89b73c8d81
|
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:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
|
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":
|
5 |
"eval_steps": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -150,6 +150,21 @@
|
|
150 |
"eval_samples_per_second": 13.902,
|
151 |
"eval_steps_per_second": 2.453,
|
152 |
"step": 27
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 3,
|
@@ -164,12 +179,12 @@
|
|
164 |
"should_evaluate": false,
|
165 |
"should_log": false,
|
166 |
"should_save": true,
|
167 |
-
"should_training_stop":
|
168 |
},
|
169 |
"attributes": {}
|
170 |
}
|
171 |
},
|
172 |
-
"total_flos":
|
173 |
"train_batch_size": 8,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_samples_per_second": 13.902,
|
151 |
"eval_steps_per_second": 2.453,
|
152 |
"step": 27
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 3.0,
|
156 |
+
"grad_norm": 0.9758431315422058,
|
157 |
+
"learning_rate": 0.0,
|
158 |
+
"loss": 0.5685,
|
159 |
+
"step": 30
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 3.0,
|
163 |
+
"eval_loss": 1.1300764083862305,
|
164 |
+
"eval_runtime": 1.2206,
|
165 |
+
"eval_samples_per_second": 13.928,
|
166 |
+
"eval_steps_per_second": 2.458,
|
167 |
+
"step": 30
|
168 |
}
|
169 |
],
|
170 |
"logging_steps": 3,
|
|
|
179 |
"should_evaluate": false,
|
180 |
"should_log": false,
|
181 |
"should_save": true,
|
182 |
+
"should_training_stop": true
|
183 |
},
|
184 |
"attributes": {}
|
185 |
}
|
186 |
},
|
187 |
+
"total_flos": 4.19901502390272e+16,
|
188 |
"train_batch_size": 8,
|
189 |
"trial_name": null,
|
190 |
"trial_params": null
|