Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz2048_lr5e-6_scheduler-cosine-warmup0.15

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
d44228b
•
1 Parent(s): 2dcb519

Training in progress, epoch 3

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +17 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b39f750f80884d8c0560597a9994715815199cdca596a7c2de6bb1132a1c12
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ea6043cebfee3301f84b0329d5b6008cee00e17a2118c245f297796a01f362
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea9064e2a3883c2f7d2810b05257c94043e0d41973bbafc26cf0edbc7a19d49f
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821ebfbe647374371a089bc87008cf9f065d4e66cf63d76466fcc037b4687c01
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5be67176a93b9e0ddf50eeb55211983838c11749e6ef4153298500995475984
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156a99fdce4affcf667c8a879a2d04e3f199b3b4c5e15cfdd6617349ed401725
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -33,3 +33,20 @@
33
  {"current_steps": 320, "total_steps": 504, "loss": 0.4338, "lr": 1.9539255805556346e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "5:11:56", "remaining_time": "2:59:22"}
34
  {"current_steps": 330, "total_steps": 504, "loss": 0.4333, "lr": 1.7764836446824835e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "5:21:34", "remaining_time": "2:49:33"}
35
  {"current_steps": 336, "total_steps": 504, "eval_loss": 0.05795557424426079, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "5:30:16", "remaining_time": "2:45:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 320, "total_steps": 504, "loss": 0.4338, "lr": 1.9539255805556346e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "5:11:56", "remaining_time": "2:59:22"}
34
  {"current_steps": 330, "total_steps": 504, "loss": 0.4333, "lr": 1.7764836446824835e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "5:21:34", "remaining_time": "2:49:33"}
35
  {"current_steps": 336, "total_steps": 504, "eval_loss": 0.05795557424426079, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "5:30:16", "remaining_time": "2:45:08"}
36
+ {"current_steps": 340, "total_steps": 504, "loss": 0.414, "lr": 1.6029381269821607e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "5:34:54", "remaining_time": "2:41:32"}
37
+ {"current_steps": 350, "total_steps": 504, "loss": 0.3888, "lr": 1.4342236378529106e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "5:44:32", "remaining_time": "2:31:35"}
38
+ {"current_steps": 360, "total_steps": 504, "loss": 0.3841, "lr": 1.2712487707171645e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "5:54:10", "remaining_time": "2:21:40"}
39
+ {"current_steps": 370, "total_steps": 504, "loss": 0.3837, "lr": 1.1148912088910687e-06, "epoch": 2.2023809523809526, "percentage": 73.41, "elapsed_time": "6:03:47", "remaining_time": "2:11:45"}
40
+ {"current_steps": 380, "total_steps": 504, "loss": 0.3863, "lr": 9.659929989170156e-07, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "6:13:25", "remaining_time": "2:01:51"}
41
+ {"current_steps": 390, "total_steps": 504, "loss": 0.3825, "lr": 8.253560158141111e-07, "epoch": 2.3214285714285716, "percentage": 77.38, "elapsed_time": "6:23:02", "remaining_time": "1:51:58"}
42
+ {"current_steps": 400, "total_steps": 504, "loss": 0.3817, "lr": 6.93737644667995e-07, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "6:32:40", "remaining_time": "1:42:05"}
43
+ {"current_steps": 410, "total_steps": 504, "loss": 0.3816, "lr": 5.718467018163243e-07, "epoch": 2.4404761904761907, "percentage": 81.35, "elapsed_time": "6:42:18", "remaining_time": "1:32:14"}
44
+ {"current_steps": 420, "total_steps": 504, "loss": 0.3815, "lr": 4.6033961759594045e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "6:51:56", "remaining_time": "1:22:23"}
45
+ {"current_steps": 430, "total_steps": 504, "loss": 0.3829, "lr": 3.598169012091049e-07, "epoch": 2.5595238095238093, "percentage": 85.32, "elapsed_time": "7:01:34", "remaining_time": "1:12:32"}
46
+ {"current_steps": 440, "total_steps": 504, "loss": 0.3837, "lr": 2.708199067468939e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "7:11:12", "remaining_time": "1:02:43"}
47
+ {"current_steps": 450, "total_steps": 504, "loss": 0.3818, "lr": 1.9382791778596864e-07, "epoch": 2.678571428571429, "percentage": 89.29, "elapsed_time": "7:20:50", "remaining_time": "0:52:54"}
48
+ {"current_steps": 460, "total_steps": 504, "loss": 0.3828, "lr": 1.2925556625931174e-07, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "7:30:28", "remaining_time": "0:43:05"}
49
+ {"current_steps": 470, "total_steps": 504, "loss": 0.3819, "lr": 7.7450599501315e-08, "epoch": 2.7976190476190474, "percentage": 93.25, "elapsed_time": "7:40:06", "remaining_time": "0:33:17"}
50
+ {"current_steps": 480, "total_steps": 504, "loss": 0.3815, "lr": 3.869200749255703e-08, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "7:49:43", "remaining_time": "0:23:29"}
51
+ {"current_steps": 490, "total_steps": 504, "loss": 0.3791, "lr": 1.3188520389787462e-08, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "7:59:21", "remaining_time": "0:13:41"}
52
+ {"current_steps": 500, "total_steps": 504, "loss": 0.3811, "lr": 1.0774844325039946e-09, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "8:08:59", "remaining_time": "0:03:54"}