Training in progress, step 500, 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 12609416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a484c67a7b85e5b5d8597ba20eb01fac01ceeb14985bd4c60caa3ee28a4fad1
|
3 |
size 12609416
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6615226
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a722bbae0d2ef3f7353b097bd1a45aff136a61bb588ae1cc739d062c715df5d0
|
3 |
size 6615226
|
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:d456150d273def7b6aef58ff01646b7bb689c6c947da8898e5d6caf60a79b2a4
|
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 sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
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": 59.639,
|
151 |
"eval_steps_per_second": 14.94,
|
152 |
"step": 450
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 50,
|
@@ -173,12 +188,12 @@
|
|
173 |
"should_evaluate": false,
|
174 |
"should_log": false,
|
175 |
"should_save": true,
|
176 |
-
"should_training_stop":
|
177 |
},
|
178 |
"attributes": {}
|
179 |
}
|
180 |
},
|
181 |
-
"total_flos":
|
182 |
"train_batch_size": 4,
|
183 |
"trial_name": null,
|
184 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4820817708969116,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-500",
|
4 |
+
"epoch": 0.212630236019562,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_samples_per_second": 59.639,
|
151 |
"eval_steps_per_second": 14.94,
|
152 |
"step": 450
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.212630236019562,
|
156 |
+
"grad_norm": 3.2577598094940186,
|
157 |
+
"learning_rate": 0.0,
|
158 |
+
"loss": 2.9982,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.212630236019562,
|
163 |
+
"eval_loss": 1.4820817708969116,
|
164 |
+
"eval_runtime": 16.6053,
|
165 |
+
"eval_samples_per_second": 59.62,
|
166 |
+
"eval_steps_per_second": 14.935,
|
167 |
+
"step": 500
|
168 |
}
|
169 |
],
|
170 |
"logging_steps": 50,
|
|
|
188 |
"should_evaluate": false,
|
189 |
"should_log": false,
|
190 |
"should_save": true,
|
191 |
+
"should_training_stop": true
|
192 |
},
|
193 |
"attributes": {}
|
194 |
}
|
195 |
},
|
196 |
+
"total_flos": 6613636428595200.0,
|
197 |
"train_batch_size": 4,
|
198 |
"trial_name": null,
|
199 |
"trial_params": null
|