Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_bsz2048

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
bda460d
·
verified ·
1 Parent(s): 68a9e21

Training in progress, epoch 2

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 +11 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a19048511cfc8094ee97239aa94d6bf4d1c73893b8d9d7249f593fb39a980f0d
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afd093b6cb8dae3dd6277bb1e391ea54388cc2760a10191eaeb1abc0b4ae939
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e708d86037ac3682c8661142e608aa704247fff2b7cce09d58f6f00ca57de2a2
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0598917375d66d1ca22b93d0f0c1817f657206229c3be97a428c43e9518006
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56f12b389ac17e2b46b21806dcfffb0ae33d6d4c08acd9c64098007f3a67ae3f
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a29952d8ba51d17ebc30375de1278693bf9b0b0de28f0286391ac3019f27bba
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be80823a29f5edbb90db81ce4fc1832afcc66fe68d565ec76c21beb1f7624597
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f927a1ea58e609c1c14427d1678c622d90a144f3b85b70ca400cead8a994fcf
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -22,3 +22,14 @@
22
  {"current_steps": 210, "total_steps": 330, "loss": 0.5699, "lr": 5e-06, "epoch": 1.8996051889452905, "percentage": 63.64, "elapsed_time": "5:26:32", "remaining_time": "3:06:35"}
23
  {"current_steps": 220, "total_steps": 330, "loss": 0.567, "lr": 5e-06, "epoch": 1.9898477157360406, "percentage": 66.67, "elapsed_time": "5:41:54", "remaining_time": "2:50:57"}
24
  {"current_steps": 220, "total_steps": 330, "eval_loss": 0.5897566080093384, "epoch": 1.9898477157360406, "percentage": 66.67, "elapsed_time": "5:45:52", "remaining_time": "2:52:56"}
 
 
 
 
 
 
 
 
 
 
 
 
22
  {"current_steps": 210, "total_steps": 330, "loss": 0.5699, "lr": 5e-06, "epoch": 1.8996051889452905, "percentage": 63.64, "elapsed_time": "5:26:32", "remaining_time": "3:06:35"}
23
  {"current_steps": 220, "total_steps": 330, "loss": 0.567, "lr": 5e-06, "epoch": 1.9898477157360406, "percentage": 66.67, "elapsed_time": "5:41:54", "remaining_time": "2:50:57"}
24
  {"current_steps": 220, "total_steps": 330, "eval_loss": 0.5897566080093384, "epoch": 1.9898477157360406, "percentage": 66.67, "elapsed_time": "5:45:52", "remaining_time": "2:52:56"}
25
+ {"current_steps": 230, "total_steps": 330, "loss": 0.5744, "lr": 5e-06, "epoch": 2.0846023688663284, "percentage": 69.7, "elapsed_time": "6:01:19", "remaining_time": "2:37:06"}
26
+ {"current_steps": 240, "total_steps": 330, "loss": 0.5402, "lr": 5e-06, "epoch": 2.1748448956570785, "percentage": 72.73, "elapsed_time": "6:16:40", "remaining_time": "2:21:15"}
27
+ {"current_steps": 250, "total_steps": 330, "loss": 0.5316, "lr": 5e-06, "epoch": 2.2650874224478286, "percentage": 75.76, "elapsed_time": "6:32:03", "remaining_time": "2:05:27"}
28
+ {"current_steps": 260, "total_steps": 330, "loss": 0.54, "lr": 5e-06, "epoch": 2.3553299492385786, "percentage": 78.79, "elapsed_time": "6:47:25", "remaining_time": "1:49:41"}
29
+ {"current_steps": 270, "total_steps": 330, "loss": 0.5365, "lr": 5e-06, "epoch": 2.4455724760293287, "percentage": 81.82, "elapsed_time": "7:02:46", "remaining_time": "1:33:57"}
30
+ {"current_steps": 280, "total_steps": 330, "loss": 0.5379, "lr": 5e-06, "epoch": 2.5358150028200788, "percentage": 84.85, "elapsed_time": "7:18:08", "remaining_time": "1:18:14"}
31
+ {"current_steps": 290, "total_steps": 330, "loss": 0.5372, "lr": 5e-06, "epoch": 2.6260575296108293, "percentage": 87.88, "elapsed_time": "7:33:29", "remaining_time": "1:02:33"}
32
+ {"current_steps": 300, "total_steps": 330, "loss": 0.5385, "lr": 5e-06, "epoch": 2.7163000564015793, "percentage": 90.91, "elapsed_time": "7:48:50", "remaining_time": "0:46:53"}
33
+ {"current_steps": 310, "total_steps": 330, "loss": 0.5411, "lr": 5e-06, "epoch": 2.8065425831923294, "percentage": 93.94, "elapsed_time": "8:04:11", "remaining_time": "0:31:14"}
34
+ {"current_steps": 320, "total_steps": 330, "loss": 0.5393, "lr": 5e-06, "epoch": 2.8967851099830795, "percentage": 96.97, "elapsed_time": "8:19:35", "remaining_time": "0:15:36"}
35
+ {"current_steps": 330, "total_steps": 330, "loss": 0.5383, "lr": 5e-06, "epoch": 2.9870276367738295, "percentage": 100.0, "elapsed_time": "8:34:57", "remaining_time": "0:00:00"}