Hugging Face's logo

WhirlwindAI
/
Translate-25T

Translation
Transformers
Safetensors
mt5
text2text-generation
machine-translation
whirlwindai
Model card Files
xet
 Community
QuantaSparkLabs commited on
Commit
f7e7f75
·
verified ·
1 Parent(s): d2e0f6c

checkpoint-4000

Browse files
Files changed (6) hide show
  1. model.safetensors +1 -1
  2. optimizer.pt +1 -1
  3. rng_state.pth +1 -1
  4. scaler.pt +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +89 -3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f64733363c4ab84fc7a91b7e6056521940e864fa3dde9cefae41d6441176bcb
3
  size 2225188480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421b1c3566897b50359cc94a1212bb9f4a46e09806ff05c974a4d25863395330
3
  size 2225188480
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9dbcf3c45dd8f88e56068b62bc6a894b03559b0f6580ed774fcd76a18a432c2
3
  size 4450498267
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010fd42cc33bfa044c7c52d0b6996c0334b0b753ff77599a9987f1177a2ca3ec
3
  size 4450498267
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbd26160ab842c822518103cb963d5530d3a1db9d1f97a9b0b60e08b0a504981
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d12912a41eb6d74668aa9acfb4ff7cd99f55b1aa02423c599a95b3ebc3006011
3
  size 14645
scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
3
  size 1383
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b23d2336a6dedfd0ec92ca5bf7a3a04e0f8095e554e3b126d5fdaf26a4e1028
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf6a257871b46c5a112aa215608ac0c00c2d1cd54b28ecf333a6131a03c71f6
3
  size 1465
trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 2.0202020202020203,
6
  "eval_steps": 500,
7
- "global_step": 3000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -266,6 +266,92 @@
266
  "eval_samples_per_second": 13.617,
267
  "eval_steps_per_second": 3.404,
268
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
269
  }
270
  ],
271
  "logging_steps": 100,
@@ -285,7 +371,7 @@
285
  "attributes": {}
286
  }
287
  },
288
- "total_flos": 1.154443985240064e+16,
289
  "train_batch_size": 8,
290
  "trial_name": null,
291
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 2.6936026936026938,
6
  "eval_steps": 500,
7
+ "global_step": 4000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
266
  "eval_samples_per_second": 13.617,
267
  "eval_steps_per_second": 3.404,
268
  "step": 3000
269
+ },
270
+ {
271
+ "epoch": 2.0875420875420874,
272
+ "grad_norm": 19.735408782958984,
273
+ "learning_rate": 9.560517038777907e-05,
274
+ "loss": 51.3095654296875,
275
+ "step": 3100
276
+ },
277
+ {
278
+ "epoch": 2.154882154882155,
279
+ "grad_norm": 23.40346336364746,
280
+ "learning_rate": 8.855464159811985e-05,
281
+ "loss": 51.257080078125,
282
+ "step": 3200
283
+ },
284
+ {
285
+ "epoch": 2.2222222222222223,
286
+ "grad_norm": 19.5986385345459,
287
+ "learning_rate": 8.150411280846062e-05,
288
+ "loss": 50.9421484375,
289
+ "step": 3300
290
+ },
291
+ {
292
+ "epoch": 2.28956228956229,
293
+ "grad_norm": 22.559755325317383,
294
+ "learning_rate": 7.44535840188014e-05,
295
+ "loss": 50.7065576171875,
296
+ "step": 3400
297
+ },
298
+ {
299
+ "epoch": 2.356902356902357,
300
+ "grad_norm": 21.577171325683594,
301
+ "learning_rate": 6.740305522914217e-05,
302
+ "loss": 51.1507177734375,
303
+ "step": 3500
304
+ },
305
+ {
306
+ "epoch": 2.356902356902357,
307
+ "eval_loss": 5.395638942718506,
308
+ "eval_runtime": 73.4284,
309
+ "eval_samples_per_second": 13.074,
310
+ "eval_steps_per_second": 3.268,
311
+ "step": 3500
312
+ },
313
+ {
314
+ "epoch": 2.4242424242424243,
315
+ "grad_norm": 29.17755889892578,
316
+ "learning_rate": 6.0352526439482956e-05,
317
+ "loss": 50.8910009765625,
318
+ "step": 3600
319
+ },
320
+ {
321
+ "epoch": 2.4915824915824913,
322
+ "grad_norm": 20.923023223876953,
323
+ "learning_rate": 5.330199764982373e-05,
324
+ "loss": 50.6894189453125,
325
+ "step": 3700
326
+ },
327
+ {
328
+ "epoch": 2.558922558922559,
329
+ "grad_norm": 18.506322860717773,
330
+ "learning_rate": 4.625146886016451e-05,
331
+ "loss": 51.0062451171875,
332
+ "step": 3800
333
+ },
334
+ {
335
+ "epoch": 2.6262626262626263,
336
+ "grad_norm": 22.548017501831055,
337
+ "learning_rate": 3.920094007050528e-05,
338
+ "loss": 50.7424365234375,
339
+ "step": 3900
340
+ },
341
+ {
342
+ "epoch": 2.6936026936026938,
343
+ "grad_norm": 22.250715255737305,
344
+ "learning_rate": 3.2150411280846066e-05,
345
+ "loss": 50.8699951171875,
346
+ "step": 4000
347
+ },
348
+ {
349
+ "epoch": 2.6936026936026938,
350
+ "eval_loss": 5.3642354011535645,
351
+ "eval_runtime": 71.4784,
352
+ "eval_samples_per_second": 13.431,
353
+ "eval_steps_per_second": 3.358,
354
+ "step": 4000
355
  }
356
  ],
357
  "logging_steps": 100,
 
371
  "attributes": {}
372
  }
373
  },
374
+ "total_flos": 1.541159116578816e+16,
375
  "train_batch_size": 8,
376
  "trial_name": null,
377
  "trial_params": null