Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_epoch2_dcftv1.2

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
20fd969
·
verified ·
1 Parent(s): 5d5462e

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 +33 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e508b491bb3150f937d3cc7a1cf696bd194dbd370adcf82e73df88c2ae0d5995
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72eca94cf1d9f925e281716a0aa87656ab776315b6c03c66e4ad0f07c5c763f3
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3547fddcda08949b8cd9ce8b530069bd29739e1bca82e1d4050a5a2d2b4202aa
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15f451ef20769509557b0ae57de316a0af33038f760ae61029765d381d78e29
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:e09ae6139e440c2f02cdbb145f76ff43ab31cd698ba1053a5b433713cfe200d5
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238f58db0e11b801d9680103bb10ebd766544e68a71e9e1c3ba5fae53b569271
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c59d89e28ce3a2ef50a83ca935bfefef81260d28983f0f47d2b4700d303ad40
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317fa2f126d52b1bbf265c9cc78f953f2ee0d16f1bfeb2268abebf4d925738a4
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -32,3 +32,36 @@
32
  {"current_steps": 320, "total_steps": 668, "loss": 0.6152, "lr": 5e-06, "epoch": 0.9579045837231057, "percentage": 47.9, "elapsed_time": "7:53:53", "remaining_time": "8:35:20"}
33
  {"current_steps": 330, "total_steps": 668, "loss": 0.6082, "lr": 5e-06, "epoch": 0.9878391019644528, "percentage": 49.4, "elapsed_time": "8:08:42", "remaining_time": "8:20:33"}
34
  {"current_steps": 334, "total_steps": 668, "eval_loss": 0.619162917137146, "epoch": 0.9998129092609915, "percentage": 50.0, "elapsed_time": "8:23:18", "remaining_time": "8:23:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  {"current_steps": 320, "total_steps": 668, "loss": 0.6152, "lr": 5e-06, "epoch": 0.9579045837231057, "percentage": 47.9, "elapsed_time": "7:53:53", "remaining_time": "8:35:20"}
33
  {"current_steps": 330, "total_steps": 668, "loss": 0.6082, "lr": 5e-06, "epoch": 0.9878391019644528, "percentage": 49.4, "elapsed_time": "8:08:42", "remaining_time": "8:20:33"}
34
  {"current_steps": 334, "total_steps": 668, "eval_loss": 0.619162917137146, "epoch": 0.9998129092609915, "percentage": 50.0, "elapsed_time": "8:23:18", "remaining_time": "8:23:18"}
35
+ {"current_steps": 340, "total_steps": 668, "loss": 0.6383, "lr": 5e-06, "epoch": 1.0177736202057999, "percentage": 50.9, "elapsed_time": "8:33:23", "remaining_time": "8:15:16"}
36
+ {"current_steps": 350, "total_steps": 668, "loss": 0.5523, "lr": 5e-06, "epoch": 1.047708138447147, "percentage": 52.4, "elapsed_time": "8:48:10", "remaining_time": "7:59:53"}
37
+ {"current_steps": 360, "total_steps": 668, "loss": 0.5478, "lr": 5e-06, "epoch": 1.077642656688494, "percentage": 53.89, "elapsed_time": "9:02:57", "remaining_time": "7:44:32"}
38
+ {"current_steps": 370, "total_steps": 668, "loss": 0.5481, "lr": 5e-06, "epoch": 1.1075771749298409, "percentage": 55.39, "elapsed_time": "9:17:45", "remaining_time": "7:29:13"}
39
+ {"current_steps": 380, "total_steps": 668, "loss": 0.5484, "lr": 5e-06, "epoch": 1.137511693171188, "percentage": 56.89, "elapsed_time": "9:32:32", "remaining_time": "7:13:55"}
40
+ {"current_steps": 390, "total_steps": 668, "loss": 0.5501, "lr": 5e-06, "epoch": 1.167446211412535, "percentage": 58.38, "elapsed_time": "9:47:21", "remaining_time": "6:58:41"}
41
+ {"current_steps": 400, "total_steps": 668, "loss": 0.5501, "lr": 5e-06, "epoch": 1.197380729653882, "percentage": 59.88, "elapsed_time": "10:02:08", "remaining_time": "6:43:26"}
42
+ {"current_steps": 410, "total_steps": 668, "loss": 0.5524, "lr": 5e-06, "epoch": 1.2273152478952292, "percentage": 61.38, "elapsed_time": "10:16:58", "remaining_time": "6:28:14"}
43
+ {"current_steps": 420, "total_steps": 668, "loss": 0.5567, "lr": 5e-06, "epoch": 1.2572497661365762, "percentage": 62.87, "elapsed_time": "10:31:45", "remaining_time": "6:13:02"}
44
+ {"current_steps": 430, "total_steps": 668, "loss": 0.5514, "lr": 5e-06, "epoch": 1.2871842843779233, "percentage": 64.37, "elapsed_time": "10:46:32", "remaining_time": "5:57:51"}
45
+ {"current_steps": 440, "total_steps": 668, "loss": 0.5534, "lr": 5e-06, "epoch": 1.3171188026192704, "percentage": 65.87, "elapsed_time": "11:01:21", "remaining_time": "5:42:42"}
46
+ {"current_steps": 450, "total_steps": 668, "loss": 0.5475, "lr": 5e-06, "epoch": 1.3470533208606175, "percentage": 67.37, "elapsed_time": "11:16:09", "remaining_time": "5:27:33"}
47
+ {"current_steps": 460, "total_steps": 668, "loss": 0.5581, "lr": 5e-06, "epoch": 1.3769878391019645, "percentage": 68.86, "elapsed_time": "11:30:59", "remaining_time": "5:12:26"}
48
+ {"current_steps": 470, "total_steps": 668, "loss": 0.5573, "lr": 5e-06, "epoch": 1.4069223573433116, "percentage": 70.36, "elapsed_time": "11:45:48", "remaining_time": "4:57:20"}
49
+ {"current_steps": 480, "total_steps": 668, "loss": 0.5592, "lr": 5e-06, "epoch": 1.4368568755846587, "percentage": 71.86, "elapsed_time": "12:00:38", "remaining_time": "4:42:15"}
50
+ {"current_steps": 490, "total_steps": 668, "loss": 0.5587, "lr": 5e-06, "epoch": 1.4667913938260055, "percentage": 73.35, "elapsed_time": "12:15:29", "remaining_time": "4:27:10"}
51
+ {"current_steps": 500, "total_steps": 668, "loss": 0.5549, "lr": 5e-06, "epoch": 1.4967259120673526, "percentage": 74.85, "elapsed_time": "12:30:19", "remaining_time": "4:12:06"}
52
+ {"current_steps": 510, "total_steps": 668, "loss": 0.5577, "lr": 5e-06, "epoch": 1.5266604303086997, "percentage": 76.35, "elapsed_time": "12:45:09", "remaining_time": "3:57:02"}
53
+ {"current_steps": 520, "total_steps": 668, "loss": 0.5557, "lr": 5e-06, "epoch": 1.5565949485500468, "percentage": 77.84, "elapsed_time": "12:59:59", "remaining_time": "3:41:59"}
54
+ {"current_steps": 530, "total_steps": 668, "loss": 0.5563, "lr": 5e-06, "epoch": 1.5865294667913938, "percentage": 79.34, "elapsed_time": "13:14:49", "remaining_time": "3:26:57"}
55
+ {"current_steps": 540, "total_steps": 668, "loss": 0.5599, "lr": 5e-06, "epoch": 1.616463985032741, "percentage": 80.84, "elapsed_time": "13:29:38", "remaining_time": "3:11:54"}
56
+ {"current_steps": 550, "total_steps": 668, "loss": 0.5593, "lr": 5e-06, "epoch": 1.646398503274088, "percentage": 82.34, "elapsed_time": "13:44:28", "remaining_time": "2:56:53"}
57
+ {"current_steps": 560, "total_steps": 668, "loss": 0.5499, "lr": 5e-06, "epoch": 1.6763330215154348, "percentage": 83.83, "elapsed_time": "13:59:17", "remaining_time": "2:41:51"}
58
+ {"current_steps": 570, "total_steps": 668, "loss": 0.5517, "lr": 5e-06, "epoch": 1.706267539756782, "percentage": 85.33, "elapsed_time": "14:14:04", "remaining_time": "2:26:50"}
59
+ {"current_steps": 580, "total_steps": 668, "loss": 0.5529, "lr": 5e-06, "epoch": 1.736202057998129, "percentage": 86.83, "elapsed_time": "14:28:54", "remaining_time": "2:11:50"}
60
+ {"current_steps": 590, "total_steps": 668, "loss": 0.5558, "lr": 5e-06, "epoch": 1.766136576239476, "percentage": 88.32, "elapsed_time": "14:43:44", "remaining_time": "1:56:50"}
61
+ {"current_steps": 600, "total_steps": 668, "loss": 0.5565, "lr": 5e-06, "epoch": 1.7960710944808231, "percentage": 89.82, "elapsed_time": "14:58:32", "remaining_time": "1:41:50"}
62
+ {"current_steps": 610, "total_steps": 668, "loss": 0.5542, "lr": 5e-06, "epoch": 1.8260056127221702, "percentage": 91.32, "elapsed_time": "15:13:21", "remaining_time": "1:26:50"}
63
+ {"current_steps": 620, "total_steps": 668, "loss": 0.5524, "lr": 5e-06, "epoch": 1.8559401309635173, "percentage": 92.81, "elapsed_time": "15:28:09", "remaining_time": "1:11:51"}
64
+ {"current_steps": 630, "total_steps": 668, "loss": 0.5542, "lr": 5e-06, "epoch": 1.8858746492048644, "percentage": 94.31, "elapsed_time": "15:42:59", "remaining_time": "0:56:52"}
65
+ {"current_steps": 640, "total_steps": 668, "loss": 0.5557, "lr": 5e-06, "epoch": 1.9158091674462114, "percentage": 95.81, "elapsed_time": "15:57:47", "remaining_time": "0:41:54"}
66
+ {"current_steps": 650, "total_steps": 668, "loss": 0.5539, "lr": 5e-06, "epoch": 1.9457436856875585, "percentage": 97.31, "elapsed_time": "16:12:34", "remaining_time": "0:26:55"}
67
+ {"current_steps": 660, "total_steps": 668, "loss": 0.5587, "lr": 5e-06, "epoch": 1.9756782039289056, "percentage": 98.8, "elapsed_time": "16:27:21", "remaining_time": "0:11:58"}