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
68a9e21
·
verified ·
1 Parent(s): 6a0efc8

Training in progress, epoch 1

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 +12 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ee7536bd9c15a19c1358963af37f7bc6ea493925da1d3b6898627d79d329f2b
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a19048511cfc8094ee97239aa94d6bf4d1c73893b8d9d7249f593fb39a980f0d
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:f3e9c4fadf2f30bd479ccec8af90f2344824f3d3dfa79f6596fef03aef592d81
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e708d86037ac3682c8661142e608aa704247fff2b7cce09d58f6f00ca57de2a2
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:fb2e4fff8645f5bcdb5c56cdb431771fc71dcfcb6d57b375380f2fabd4388e7a
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f12b389ac17e2b46b21806dcfffb0ae33d6d4c08acd9c64098007f3a67ae3f
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:cc58e608ef2eaac0a96ff8be58e6dc345d6a9c65991d7e350041a265ffe7c780
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be80823a29f5edbb90db81ce4fc1832afcc66fe68d565ec76c21beb1f7624597
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -10,3 +10,15 @@
10
  {"current_steps": 100, "total_steps": 330, "loss": 0.6088, "lr": 5e-06, "epoch": 0.9024252679075014, "percentage": 30.3, "elapsed_time": "2:33:35", "remaining_time": "5:53:16"}
11
  {"current_steps": 110, "total_steps": 330, "loss": 0.6031, "lr": 5e-06, "epoch": 0.9926677946982515, "percentage": 33.33, "elapsed_time": "2:48:56", "remaining_time": "5:37:53"}
12
  {"current_steps": 110, "total_steps": 330, "eval_loss": 0.601691484451294, "epoch": 0.9926677946982515, "percentage": 33.33, "elapsed_time": "2:52:27", "remaining_time": "5:44:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  {"current_steps": 100, "total_steps": 330, "loss": 0.6088, "lr": 5e-06, "epoch": 0.9024252679075014, "percentage": 30.3, "elapsed_time": "2:33:35", "remaining_time": "5:53:16"}
11
  {"current_steps": 110, "total_steps": 330, "loss": 0.6031, "lr": 5e-06, "epoch": 0.9926677946982515, "percentage": 33.33, "elapsed_time": "2:48:56", "remaining_time": "5:37:53"}
12
  {"current_steps": 110, "total_steps": 330, "eval_loss": 0.601691484451294, "epoch": 0.9926677946982515, "percentage": 33.33, "elapsed_time": "2:52:27", "remaining_time": "5:44:55"}
13
+ {"current_steps": 120, "total_steps": 330, "loss": 0.6161, "lr": 5e-06, "epoch": 1.0874224478285393, "percentage": 36.36, "elapsed_time": "3:08:13", "remaining_time": "5:29:24"}
14
+ {"current_steps": 130, "total_steps": 330, "loss": 0.5733, "lr": 5e-06, "epoch": 1.1776649746192893, "percentage": 39.39, "elapsed_time": "3:23:36", "remaining_time": "5:13:14"}
15
+ {"current_steps": 140, "total_steps": 330, "loss": 0.5743, "lr": 5e-06, "epoch": 1.2679075014100394, "percentage": 42.42, "elapsed_time": "3:38:58", "remaining_time": "4:57:10"}
16
+ {"current_steps": 150, "total_steps": 330, "loss": 0.5749, "lr": 5e-06, "epoch": 1.3581500282007897, "percentage": 45.45, "elapsed_time": "3:54:20", "remaining_time": "4:41:12"}
17
+ {"current_steps": 160, "total_steps": 330, "loss": 0.5699, "lr": 5e-06, "epoch": 1.4483925549915397, "percentage": 48.48, "elapsed_time": "4:09:41", "remaining_time": "4:25:17"}
18
+ {"current_steps": 170, "total_steps": 330, "loss": 0.5713, "lr": 5e-06, "epoch": 1.53863508178229, "percentage": 51.52, "elapsed_time": "4:25:03", "remaining_time": "4:09:28"}
19
+ {"current_steps": 180, "total_steps": 330, "loss": 0.5726, "lr": 5e-06, "epoch": 1.62887760857304, "percentage": 54.55, "elapsed_time": "4:40:24", "remaining_time": "3:53:40"}
20
+ {"current_steps": 190, "total_steps": 330, "loss": 0.571, "lr": 5e-06, "epoch": 1.7191201353637902, "percentage": 57.58, "elapsed_time": "4:55:47", "remaining_time": "3:37:57"}
21
+ {"current_steps": 200, "total_steps": 330, "loss": 0.5663, "lr": 5e-06, "epoch": 1.8093626621545402, "percentage": 60.61, "elapsed_time": "5:11:09", "remaining_time": "3:22:15"}
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"}