Training in progress, step 400, 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 109009752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41af589fcd24d3adeda28e1ae5886906584a02a3a05bfde402c85a9fadce6ff0
|
3 |
size 109009752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56088788
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b6b52de6d3987e0a962c190d63aee104d4913f3e39498d11de3519fbb4f0be2
|
3 |
size 56088788
|
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:a2c51bbb10d1e68a840b29522c94a0963bf01dea0c64b55bbee990ed70cdab65
|
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 sha256:6f70998b817472e026736459d4df0f6f43763ba4dd4e65ff61ee56b907e34fba
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 3.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -188,6 +188,21 @@
|
|
188 |
"eval_samples_per_second": 27.478,
|
189 |
"eval_steps_per_second": 0.879,
|
190 |
"step": 380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
191 |
}
|
192 |
],
|
193 |
"logging_steps": 100,
|
@@ -216,7 +231,7 @@
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
-
"total_flos": 1.
|
220 |
"train_batch_size": 8,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 3.222342002118239e-07,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
4 |
+
"epoch": 2.6936026936026938,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
188 |
"eval_samples_per_second": 27.478,
|
189 |
"eval_steps_per_second": 0.879,
|
190 |
"step": 380
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 2.6936026936026938,
|
194 |
+
"grad_norm": 7.30554893380031e-06,
|
195 |
+
"learning_rate": 0.00013359431874331886,
|
196 |
+
"loss": 0.0,
|
197 |
+
"step": 400
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 2.6936026936026938,
|
201 |
+
"eval_loss": 3.222342002118239e-07,
|
202 |
+
"eval_runtime": 4.5438,
|
203 |
+
"eval_samples_per_second": 27.51,
|
204 |
+
"eval_steps_per_second": 0.88,
|
205 |
+
"step": 400
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 100,
|
|
|
231 |
"attributes": {}
|
232 |
}
|
233 |
},
|
234 |
+
"total_flos": 1.6892181205745664e+17,
|
235 |
"train_batch_size": 8,
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|