Hugging Face's logo

mlfoundations-dev
/
oh_scale_x.125_compute_equal

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
4fff630
·
verified ·
1 Parent(s): 2610d96

Training in progress, epoch 72

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +6 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b89607510c3af7463df59e60a8bec4fc179f7eb03b42fa6bdcfbe9269e052d2
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c463a2d47933c2d02c05d27fefffd284d8e78c15c49b9ec8ecf5625d10ecc476
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0ac0ff38ceeb4fa713743c15cc0ca63b837820fa465eb9df14df683651be689
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd7649d40813f0a58f5637b4779763211086772403b8329f88b0a778b8d9374
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67e7193ea5280ce344c8371993023be24a6f97a05b09ccedda4cd8fa2386a908
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defd0ae956c4adee4c3aa8f4f5b6784c43dfa87a79d59af425cb11678e684ada
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52021737827121d3c8e99b48d6ca00dd46496175c5b56493d5a6d2a27d763174
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2348c6a3b35c1843a72d64805db8d40a1451442a7d3d5a75c6ba048ed16fb543
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -409,3 +409,9 @@
409
  {"current_steps": 3380, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.72413793103448, "percentage": 80.8, "elapsed_time": "1 day, 8:29:02", "remaining_time": "7:43:02"}
410
  {"current_steps": 3390, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.93633952254642, "percentage": 81.04, "elapsed_time": "1 day, 8:34:21", "remaining_time": "7:37:10"}
411
  {"current_steps": 3393, "total_steps": 4183, "eval_loss": 2.136025905609131, "epoch": 72.0, "percentage": 81.11, "elapsed_time": "1 day, 8:36:22", "remaining_time": "7:35:30"}
 
 
 
 
 
 
 
409
  {"current_steps": 3380, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.72413793103448, "percentage": 80.8, "elapsed_time": "1 day, 8:29:02", "remaining_time": "7:43:02"}
410
  {"current_steps": 3390, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 71.93633952254642, "percentage": 81.04, "elapsed_time": "1 day, 8:34:21", "remaining_time": "7:37:10"}
411
  {"current_steps": 3393, "total_steps": 4183, "eval_loss": 2.136025905609131, "epoch": 72.0, "percentage": 81.11, "elapsed_time": "1 day, 8:36:22", "remaining_time": "7:35:30"}
412
+ {"current_steps": 3400, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 72.14854111405836, "percentage": 81.28, "elapsed_time": "1 day, 8:41:24", "remaining_time": "7:31:42"}
413
+ {"current_steps": 3410, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 72.36074270557029, "percentage": 81.52, "elapsed_time": "1 day, 8:46:41", "remaining_time": "7:25:49"}
414
+ {"current_steps": 3420, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 72.57294429708223, "percentage": 81.76, "elapsed_time": "1 day, 8:51:59", "remaining_time": "7:19:57"}
415
+ {"current_steps": 3430, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 72.78514588859416, "percentage": 82.0, "elapsed_time": "1 day, 8:57:18", "remaining_time": "7:14:05"}
416
+ {"current_steps": 3440, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 72.9973474801061, "percentage": 82.24, "elapsed_time": "1 day, 9:02:37", "remaining_time": "7:08:13"}
417
+ {"current_steps": 3440, "total_steps": 4183, "eval_loss": 2.140444278717041, "epoch": 72.9973474801061, "percentage": 82.24, "elapsed_time": "1 day, 9:03:12", "remaining_time": "7:08:20"}