Hugging Face's logo

mlfoundations-dev
/
s1K_32b

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
d58a304
·
verified ·
1 Parent(s): 49bae1e

Training in progress, epoch 5

Browse files
Files changed (15) hide show
  1. model-00001-of-00014.safetensors +1 -1
  2. model-00002-of-00014.safetensors +1 -1
  3. model-00003-of-00014.safetensors +1 -1
  4. model-00004-of-00014.safetensors +1 -1
  5. model-00005-of-00014.safetensors +1 -1
  6. model-00006-of-00014.safetensors +1 -1
  7. model-00007-of-00014.safetensors +1 -1
  8. model-00008-of-00014.safetensors +1 -1
  9. model-00009-of-00014.safetensors +1 -1
  10. model-00010-of-00014.safetensors +1 -1
  11. model-00011-of-00014.safetensors +1 -1
  12. model-00012-of-00014.safetensors +1 -1
  13. model-00013-of-00014.safetensors +1 -1
  14. model-00014-of-00014.safetensors +1 -1
  15. trainer_log.jsonl +24 -0
model-00001-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35d193c3b9db208711cda75647166c9cc6c8a0a5cf63ae1e5736449f399315d4
3
  size 4891730992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30ca9c98cf9695747e3b73f653fdd87657cb27c049bd4a6f4c5650ed6ac7ad2
3
  size 4891730992
model-00002-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:686e2ac636b14a8f74c627532fb1c6ab7aa7d693b1a03434438d8a1e7a04fba2
3
  size 4876059352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5963473774e10659000e1c825dad215c55a8225e3872f9771e3344e2469d43
3
  size 4876059352
model-00003-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df6a4e206e5ee46a3f87aad6333e8edb0d1149c86c083d164327373b69c7b70c
3
  size 4876059384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f71db433453518b5c8e80ad5ace0cf557675ccb50e85a8901aa53fc80ee9b8
3
  size 4876059384
model-00004-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c498c419cf69f648b818c64265ef630d778158154dfbd0df4babf6276364bd7a
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe53e7b8f4a00dc1541b70c0a1b5ce54db565e68ce1ed149235bdbd70f955472
3
  size 4876059416
model-00005-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f62b64fd3d915847af98809fc286d11a6cf57e00d515930405ed941534e7df
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb6acfec45a8375d23db8e00215c5becadfa0ee876f11ae25b87c4791f59de3
3
  size 4876059416
model-00006-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c37811b272b4c7287948b9d557397e86a3d2acb2a3e567b15df61796e4d732c9
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a971d0a5ddf20e711ca37c0bb737e5d1a192b50d2debf6b13936773163e2ca
3
  size 4876059416
model-00007-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0b4c4f9aa6ad2d3085ec7c73da509383eaf06d75bf67aeb007439564bd3b7c1
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76e490e018d41946c753303310e8ce4cc865f74acca51dd95d8f743e889c2c4
3
  size 4876059416
model-00008-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4824381e946e92fa4d323b3caf4215459dd741e234ca048d68da9f0a89663bf
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245e8cab5650f4d432811643e90f0e8eb1aa9ad03893ed7d59687d4c4029eb46
3
  size 4876059416
model-00009-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2d852aa959a7a5d8598662c3bf13dbb59649ad7581d295c61492e1706f8997a
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35950008a849cf3ac0d892f6f808faac9ce116abda92e4fda08a8bb4133b589f
3
  size 4876059416
model-00010-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d892c73f96f855bb8e0bf0d22dea06d7daa73b5423be39a4017b1c3acb91093f
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd94493473c9ee75b98fc0e628199a44e0f56eaaf37cc00f0ccc78d95bd3ae9a
3
  size 4876059416
model-00011-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a602a147616fe8a4c4a0665e0affd1d39639dd3d90f8100730b995177115ad
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b226d049d1fe738822c9dc9d5959fe010f0323906f50ebd1c28907a4b792e6d
3
  size 4876059416
model-00012-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2f957fa10e3a011d9e64cb56e23a08e2a2349dc7b5c91a62d45a8e0507c2012
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d18eaae685410b5691a3fbe94babb34443589dfb198c1aa463542d7b0521ce
3
  size 4876059416
model-00013-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f09b78ccb4b4830ec3dfc68bdade8d0e1699ffac4f8de3f135ab28619ff69b
3
  size 4876059416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10e20c4f585604d88875f155b648874590bee20186df1ed5f25961c730668cb
3
  size 4876059416
model-00014-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3168b44df4a5652648169b22b2ed25d6a5781c1d825c0620933ae2ea79e29528
3
  size 2123397800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934c9f67c704d2e0301a048e839632f499061a2350154ed0527578b000df1bb0
3
  size 2123397800
trainer_log.jsonl CHANGED
@@ -290,3 +290,27 @@
290
  {"current_steps": 290, "total_steps": 315, "loss": 0.0041, "lr": 1.7150580780396385e-07, "epoch": 4.603174603174603, "percentage": 92.06, "elapsed_time": "1:16:01", "remaining_time": "0:06:33"}
291
  {"current_steps": 291, "total_steps": 315, "loss": 0.0022, "lr": 1.5813109883537792e-07, "epoch": 4.619047619047619, "percentage": 92.38, "elapsed_time": "1:16:13", "remaining_time": "0:06:17"}
292
  {"current_steps": 292, "total_steps": 315, "loss": 0.0029, "lr": 1.4529091286973994e-07, "epoch": 4.634920634920634, "percentage": 92.7, "elapsed_time": "1:16:25", "remaining_time": "0:06:01"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
  {"current_steps": 290, "total_steps": 315, "loss": 0.0041, "lr": 1.7150580780396385e-07, "epoch": 4.603174603174603, "percentage": 92.06, "elapsed_time": "1:16:01", "remaining_time": "0:06:33"}
291
  {"current_steps": 291, "total_steps": 315, "loss": 0.0022, "lr": 1.5813109883537792e-07, "epoch": 4.619047619047619, "percentage": 92.38, "elapsed_time": "1:16:13", "remaining_time": "0:06:17"}
292
  {"current_steps": 292, "total_steps": 315, "loss": 0.0029, "lr": 1.4529091286973994e-07, "epoch": 4.634920634920634, "percentage": 92.7, "elapsed_time": "1:16:25", "remaining_time": "0:06:01"}
293
+ {"current_steps": 293, "total_steps": 315, "loss": 0.0047, "lr": 1.3298666741233424e-07, "epoch": 4.650793650793651, "percentage": 93.02, "elapsed_time": "1:16:37", "remaining_time": "0:05:45"}
294
+ {"current_steps": 294, "total_steps": 315, "loss": 0.0041, "lr": 1.2121972080275378e-07, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "1:16:49", "remaining_time": "0:05:29"}
295
+ {"current_steps": 295, "total_steps": 315, "loss": 0.0045, "lr": 1.0999137206494315e-07, "epoch": 4.682539682539683, "percentage": 93.65, "elapsed_time": "1:17:01", "remaining_time": "0:05:13"}
296
+ {"current_steps": 296, "total_steps": 315, "loss": 0.0067, "lr": 9.93028607637908e-08, "epoch": 4.698412698412699, "percentage": 93.97, "elapsed_time": "1:17:14", "remaining_time": "0:04:57"}
297
+ {"current_steps": 297, "total_steps": 315, "loss": 0.0085, "lr": 8.915536686828764e-08, "epoch": 4.714285714285714, "percentage": 94.29, "elapsed_time": "1:17:27", "remaining_time": "0:04:41"}
298
+ {"current_steps": 298, "total_steps": 315, "loss": 0.0036, "lr": 7.955001062125989e-08, "epoch": 4.73015873015873, "percentage": 94.6, "elapsed_time": "1:17:39", "remaining_time": "0:04:25"}
299
+ {"current_steps": 299, "total_steps": 315, "loss": 0.0028, "lr": 7.048785241570321e-08, "epoch": 4.746031746031746, "percentage": 94.92, "elapsed_time": "1:17:51", "remaining_time": "0:04:09"}
300
+ {"current_steps": 300, "total_steps": 315, "loss": 0.0033, "lr": 6.19698926777168e-08, "epoch": 4.761904761904762, "percentage": 95.24, "elapsed_time": "1:18:03", "remaining_time": "0:03:54"}
301
+ {"current_steps": 301, "total_steps": 315, "loss": 0.0016, "lr": 5.399707175606117e-08, "epoch": 4.777777777777778, "percentage": 95.56, "elapsed_time": "1:18:15", "remaining_time": "0:03:38"}
302
+ {"current_steps": 302, "total_steps": 315, "loss": 0.002, "lr": 4.657026981834623e-08, "epoch": 4.7936507936507935, "percentage": 95.87, "elapsed_time": "1:18:27", "remaining_time": "0:03:22"}
303
+ {"current_steps": 303, "total_steps": 315, "loss": 0.0029, "lr": 3.9690306753866204e-08, "epoch": 4.809523809523809, "percentage": 96.19, "elapsed_time": "1:18:39", "remaining_time": "0:03:06"}
304
+ {"current_steps": 304, "total_steps": 315, "loss": 0.0016, "lr": 3.3357942083085404e-08, "epoch": 4.825396825396825, "percentage": 96.51, "elapsed_time": "1:18:51", "remaining_time": "0:02:51"}
305
+ {"current_steps": 305, "total_steps": 315, "loss": 0.0043, "lr": 2.7573874873791372e-08, "epoch": 4.841269841269841, "percentage": 96.83, "elapsed_time": "1:19:03", "remaining_time": "0:02:35"}
306
+ {"current_steps": 306, "total_steps": 315, "loss": 0.001, "lr": 2.233874366391997e-08, "epoch": 4.857142857142857, "percentage": 97.14, "elapsed_time": "1:19:15", "remaining_time": "0:02:19"}
307
+ {"current_steps": 307, "total_steps": 315, "loss": 0.005, "lr": 1.7653126391063425e-08, "epoch": 4.8730158730158735, "percentage": 97.46, "elapsed_time": "1:19:27", "remaining_time": "0:02:04"}
308
+ {"current_steps": 308, "total_steps": 315, "loss": 0.0025, "lr": 1.3517540328669143e-08, "epoch": 4.888888888888889, "percentage": 97.78, "elapsed_time": "1:19:39", "remaining_time": "0:01:48"}
309
+ {"current_steps": 309, "total_steps": 315, "loss": 0.0023, "lr": 9.93244202893262e-09, "epoch": 4.904761904761905, "percentage": 98.1, "elapsed_time": "1:19:51", "remaining_time": "0:01:33"}
310
+ {"current_steps": 310, "total_steps": 315, "loss": 0.0065, "lr": 6.898227272398306e-09, "epoch": 4.920634920634921, "percentage": 98.41, "elapsed_time": "1:20:03", "remaining_time": "0:01:17"}
311
+ {"current_steps": 311, "total_steps": 315, "loss": 0.0108, "lr": 4.415231024265665e-09, "epoch": 4.936507936507937, "percentage": 98.73, "elapsed_time": "1:20:15", "remaining_time": "0:01:01"}
312
+ {"current_steps": 312, "total_steps": 315, "loss": 0.0026, "lr": 2.4837273974115393e-09, "epoch": 4.9523809523809526, "percentage": 99.05, "elapsed_time": "1:20:27", "remaining_time": "0:00:46"}
313
+ {"current_steps": 313, "total_steps": 315, "loss": 0.0116, "lr": 1.1039296221276863e-09, "epoch": 4.968253968253968, "percentage": 99.37, "elapsed_time": "1:20:39", "remaining_time": "0:00:30"}
314
+ {"current_steps": 314, "total_steps": 315, "loss": 0.0022, "lr": 2.7599002258127395e-10, "epoch": 4.984126984126984, "percentage": 99.68, "elapsed_time": "1:20:51", "remaining_time": "0:00:15"}
315
+ {"current_steps": 315, "total_steps": 315, "loss": 0.0015, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:21:03", "remaining_time": "0:00:00"}
316
+ {"current_steps": 315, "total_steps": 315, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:29:14", "remaining_time": "0:00:00"}