Training in progress, step 40, 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 619632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38799347f65a7ed1a2cbacce2d9144aa3c914d18ccb1e3fdd4251542125db97d
|
3 |
size 619632
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1324026
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab235c3bd36826b1a9f64b02b346ee5a6d20e57442da515f05163e4e5379acd
|
3 |
size 1324026
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90021be0ad63cbcd6db2577a307ccc4130b2c06ca765264bfa98daa67579ad94
|
3 |
size 14512
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a402bfbd22dfb93faf811296f0988585bea76884af7cafd9bcf1eec8614fa602
|
3 |
size 14512
|
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 sha256:9a2759c51def6f12ecf076b0cf2571dc6049a636d579f7f0a8bd8ae37daff96c
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -249,6 +249,84 @@
|
|
249 |
"eval_samples_per_second": 92.045,
|
250 |
"eval_steps_per_second": 23.011,
|
251 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
252 |
}
|
253 |
],
|
254 |
"logging_steps": 1,
|
@@ -263,12 +341,12 @@
|
|
263 |
"should_evaluate": false,
|
264 |
"should_log": false,
|
265 |
"should_save": true,
|
266 |
-
"should_training_stop":
|
267 |
},
|
268 |
"attributes": {}
|
269 |
}
|
270 |
},
|
271 |
-
"total_flos":
|
272 |
"train_batch_size": 2,
|
273 |
"trial_name": null,
|
274 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0110323089046493,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
249 |
"eval_samples_per_second": 92.045,
|
250 |
"eval_steps_per_second": 23.011,
|
251 |
"step": 30
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.7817178881008668,
|
255 |
+
"grad_norm": 0.25170794129371643,
|
256 |
+
"learning_rate": 1.3213804466343421e-05,
|
257 |
+
"loss": 11.9165,
|
258 |
+
"step": 31
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 0.8069345941686368,
|
262 |
+
"grad_norm": 0.2574658989906311,
|
263 |
+
"learning_rate": 1.0542974530180327e-05,
|
264 |
+
"loss": 11.9158,
|
265 |
+
"step": 32
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.8321513002364066,
|
269 |
+
"grad_norm": 0.2503858506679535,
|
270 |
+
"learning_rate": 8.141676086873572e-06,
|
271 |
+
"loss": 11.9152,
|
272 |
+
"step": 33
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.8573680063041765,
|
276 |
+
"grad_norm": 0.27511805295944214,
|
277 |
+
"learning_rate": 6.026312439675552e-06,
|
278 |
+
"loss": 11.9153,
|
279 |
+
"step": 34
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.8825847123719465,
|
283 |
+
"grad_norm": 0.2627543807029724,
|
284 |
+
"learning_rate": 4.2113336672471245e-06,
|
285 |
+
"loss": 11.9171,
|
286 |
+
"step": 35
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.9078014184397163,
|
290 |
+
"grad_norm": 0.22878780961036682,
|
291 |
+
"learning_rate": 2.7091379149682685e-06,
|
292 |
+
"loss": 11.9206,
|
293 |
+
"step": 36
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.9330181245074862,
|
297 |
+
"grad_norm": 0.26924818754196167,
|
298 |
+
"learning_rate": 1.5299867030334814e-06,
|
299 |
+
"loss": 11.9155,
|
300 |
+
"step": 37
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.9582348305752562,
|
304 |
+
"grad_norm": 0.25205621123313904,
|
305 |
+
"learning_rate": 6.819348298638839e-07,
|
306 |
+
"loss": 11.916,
|
307 |
+
"step": 38
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.983451536643026,
|
311 |
+
"grad_norm": 0.25344499945640564,
|
312 |
+
"learning_rate": 1.7077534966650766e-07,
|
313 |
+
"loss": 11.9166,
|
314 |
+
"step": 39
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.0110323089046493,
|
318 |
+
"grad_norm": 0.42802441120147705,
|
319 |
+
"learning_rate": 0.0,
|
320 |
+
"loss": 17.6584,
|
321 |
+
"step": 40
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.0110323089046493,
|
325 |
+
"eval_loss": 11.915095329284668,
|
326 |
+
"eval_runtime": 2.9117,
|
327 |
+
"eval_samples_per_second": 92.042,
|
328 |
+
"eval_steps_per_second": 23.011,
|
329 |
+
"step": 40
|
330 |
}
|
331 |
],
|
332 |
"logging_steps": 1,
|
|
|
341 |
"should_evaluate": false,
|
342 |
"should_log": false,
|
343 |
"should_save": true,
|
344 |
+
"should_training_stop": true
|
345 |
},
|
346 |
"attributes": {}
|
347 |
}
|
348 |
},
|
349 |
+
"total_flos": 649990955335680.0,
|
350 |
"train_batch_size": 2,
|
351 |
"trial_name": null,
|
352 |
"trial_params": null
|