Training in progress, step 600, 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:d8e0f9fcdf48f487a1c9001825e5051f82f66679b2a25912d3b21503f2d4a1c4
|
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 sha256:347cd973f6654ee2258a2954d44bb5fc9959a63600a404728a5f3d3feda03a7d
|
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 sha256:3775aa2a57ceedad86a9060869357a0158ad85ec662a59802338adbc33ed6fc5
|
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:f6f4ffe4ed9bff96a333b247dd3c9b5dfaf8c2768b6a1ee83b674ec988b0833c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch":
|
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,
|
@@ -282,6 +282,21 @@
|
|
282 |
"eval_samples_per_second": 28.425,
|
283 |
"eval_steps_per_second": 0.91,
|
284 |
"step": 580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
285 |
}
|
286 |
],
|
287 |
"logging_steps": 100,
|
@@ -310,7 +325,7 @@
|
|
310 |
"attributes": {}
|
311 |
}
|
312 |
},
|
313 |
-
"total_flos": 2.
|
314 |
"train_batch_size": 8,
|
315 |
"trial_name": null,
|
316 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.6435236577526666e-07,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-600",
|
4 |
+
"epoch": 4.040404040404041,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
282 |
"eval_samples_per_second": 28.425,
|
283 |
"eval_steps_per_second": 0.91,
|
284 |
"step": 580
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 4.040404040404041,
|
288 |
+
"grad_norm": 6.343952009046916e-06,
|
289 |
+
"learning_rate": 2.6341528967837533e-05,
|
290 |
+
"loss": 0.0,
|
291 |
+
"step": 600
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 4.040404040404041,
|
295 |
+
"eval_loss": 2.6435236577526666e-07,
|
296 |
+
"eval_runtime": 4.4258,
|
297 |
+
"eval_samples_per_second": 28.244,
|
298 |
+
"eval_steps_per_second": 0.904,
|
299 |
+
"step": 600
|
300 |
}
|
301 |
],
|
302 |
"logging_steps": 100,
|
|
|
325 |
"attributes": {}
|
326 |
}
|
327 |
},
|
328 |
+
"total_flos": 2.5335631580233728e+17,
|
329 |
"train_batch_size": 8,
|
330 |
"trial_name": null,
|
331 |
"trial_params": null
|