Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_scheduler_cosine_warmup0.05_minlr1e-7_dcftv1.2

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
28d11c6
·
verified ·
1 Parent(s): 241f7b7

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 +35 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b8bf292615feb3cb10d829c4560c8d5e613f1158500e52d646bdb3dc4ae23c
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9891e893251e1b4acc20c833dba56b2198433410706b6c01fb36d91a75e4711
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:b700b7da95657db1b01966d96bf408b3dcb0060cee561e9c196209a31800f90e
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed5fbf9f16ec3c8d6b3df9142c8c47fa6650847b433577bd1cac5bb9b895328
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e904fb4c842213dd2a1b131a57b47297a6cc7bf4dc5947b7e985a3dec094c5
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6260983daa5b823e665a7cdda6ef746470bc897d850835938c1be79cee5dc71f
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03abf2c40712caebb6f53e7cf7624d0bf7ec0bd2a924788342d7cf1445fdaa9a
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc688b990c84e80bf60ffee2c4ec7f12b1d7cdcd93bc85d6d91617d20cf1b520
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -32,3 +32,38 @@
32
  {"current_steps": 320, "total_steps": 1002, "loss": 0.6156, "learning_rate": 4.094663671224683e-06, "epoch": 0.9579045837231057, "percentage": 31.94, "elapsed_time": "7:53:18", "remaining_time": "16:48:44"}
33
  {"current_steps": 330, "total_steps": 1002, "loss": 0.6083, "learning_rate": 4.031009950438763e-06, "epoch": 0.9878391019644528, "percentage": 32.93, "elapsed_time": "8:08:06", "remaining_time": "16:33:58"}
34
  {"current_steps": 334, "total_steps": 1002, "eval_loss": 0.6193081736564636, "epoch": 0.9998129092609915, "percentage": 33.33, "elapsed_time": "8:22:43", "remaining_time": "16:45:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  {"current_steps": 320, "total_steps": 1002, "loss": 0.6156, "learning_rate": 4.094663671224683e-06, "epoch": 0.9579045837231057, "percentage": 31.94, "elapsed_time": "7:53:18", "remaining_time": "16:48:44"}
33
  {"current_steps": 330, "total_steps": 1002, "loss": 0.6083, "learning_rate": 4.031009950438763e-06, "epoch": 0.9878391019644528, "percentage": 32.93, "elapsed_time": "8:08:06", "remaining_time": "16:33:58"}
34
  {"current_steps": 334, "total_steps": 1002, "eval_loss": 0.6193081736564636, "epoch": 0.9998129092609915, "percentage": 33.33, "elapsed_time": "8:22:43", "remaining_time": "16:45:27"}
35
+ {"current_steps": 340, "total_steps": 1002, "loss": 0.6447, "learning_rate": 3.965740170725753e-06, "epoch": 1.0177736202057999, "percentage": 33.93, "elapsed_time": "8:32:45", "remaining_time": "16:38:22"}
36
+ {"current_steps": 350, "total_steps": 1002, "loss": 0.5583, "learning_rate": 3.89892555362616e-06, "epoch": 1.047708138447147, "percentage": 34.93, "elapsed_time": "8:47:34", "remaining_time": "16:22:48"}
37
+ {"current_steps": 360, "total_steps": 1002, "loss": 0.554, "learning_rate": 3.830639006387089e-06, "epoch": 1.077642656688494, "percentage": 35.93, "elapsed_time": "9:02:23", "remaining_time": "16:07:15"}
38
+ {"current_steps": 370, "total_steps": 1002, "loss": 0.5537, "learning_rate": 3.7609550424068e-06, "epoch": 1.1075771749298409, "percentage": 36.93, "elapsed_time": "9:17:11", "remaining_time": "15:51:44"}
39
+ {"current_steps": 380, "total_steps": 1002, "loss": 0.5536, "learning_rate": 3.6899496999266545e-06, "epoch": 1.137511693171188, "percentage": 37.92, "elapsed_time": "9:31:57", "remaining_time": "15:36:12"}
40
+ {"current_steps": 390, "total_steps": 1002, "loss": 0.5551, "learning_rate": 3.617700459059159e-06, "epoch": 1.167446211412535, "percentage": 38.92, "elapsed_time": "9:46:43", "remaining_time": "15:20:41"}
41
+ {"current_steps": 400, "total_steps": 1002, "loss": 0.5552, "learning_rate": 3.5442861572426747e-06, "epoch": 1.197380729653882, "percentage": 39.92, "elapsed_time": "10:01:30", "remaining_time": "15:05:15"}
42
+ {"current_steps": 410, "total_steps": 1002, "loss": 0.5572, "learning_rate": 3.4697869032150196e-06, "epoch": 1.2273152478952292, "percentage": 40.92, "elapsed_time": "10:16:16", "remaining_time": "14:49:50"}
43
+ {"current_steps": 420, "total_steps": 1002, "loss": 0.5612, "learning_rate": 3.3942839895998515e-06, "epoch": 1.2572497661365762, "percentage": 41.92, "elapsed_time": "10:31:05", "remaining_time": "14:34:31"}
44
+ {"current_steps": 430, "total_steps": 1002, "loss": 0.5551, "learning_rate": 3.317859804201203e-06, "epoch": 1.2871842843779233, "percentage": 42.91, "elapsed_time": "10:45:53", "remaining_time": "14:19:11"}
45
+ {"current_steps": 440, "total_steps": 1002, "loss": 0.5567, "learning_rate": 3.240597740102979e-06, "epoch": 1.3171188026192704, "percentage": 43.91, "elapsed_time": "11:00:42", "remaining_time": "14:03:54"}
46
+ {"current_steps": 450, "total_steps": 1002, "loss": 0.5506, "learning_rate": 3.162582104671497e-06, "epoch": 1.3470533208606175, "percentage": 44.91, "elapsed_time": "11:15:32", "remaining_time": "13:48:39"}
47
+ {"current_steps": 460, "total_steps": 1002, "loss": 0.561, "learning_rate": 3.083898027560378e-06, "epoch": 1.3769878391019645, "percentage": 45.91, "elapsed_time": "11:30:20", "remaining_time": "13:33:23"}
48
+ {"current_steps": 470, "total_steps": 1002, "loss": 0.5594, "learning_rate": 3.0046313678181703e-06, "epoch": 1.4069223573433116, "percentage": 46.91, "elapsed_time": "11:45:07", "remaining_time": "13:18:08"}
49
+ {"current_steps": 480, "total_steps": 1002, "loss": 0.5614, "learning_rate": 2.9248686202000648e-06, "epoch": 1.4368568755846587, "percentage": 47.9, "elapsed_time": "11:59:54", "remaining_time": "13:02:53"}
50
+ {"current_steps": 490, "total_steps": 1002, "loss": 0.56, "learning_rate": 2.844696820785932e-06, "epoch": 1.4667913938260055, "percentage": 48.9, "elapsed_time": "12:14:41", "remaining_time": "12:47:40"}
51
+ {"current_steps": 500, "total_steps": 1002, "loss": 0.5561, "learning_rate": 2.7642034520076817e-06, "epoch": 1.4967259120673526, "percentage": 49.9, "elapsed_time": "12:29:25", "remaining_time": "12:32:24"}
52
+ {"current_steps": 510, "total_steps": 1002, "loss": 0.5588, "learning_rate": 2.683476347189556e-06, "epoch": 1.5266604303086997, "percentage": 50.9, "elapsed_time": "12:44:10", "remaining_time": "12:17:12"}
53
+ {"current_steps": 520, "total_steps": 1002, "loss": 0.5565, "learning_rate": 2.602603594705548e-06, "epoch": 1.5565949485500468, "percentage": 51.9, "elapsed_time": "12:58:56", "remaining_time": "12:02:01"}
54
+ {"current_steps": 530, "total_steps": 1002, "loss": 0.5569, "learning_rate": 2.5216734418584993e-06, "epoch": 1.5865294667913938, "percentage": 52.89, "elapsed_time": "13:13:41", "remaining_time": "11:46:50"}
55
+ {"current_steps": 540, "total_steps": 1002, "loss": 0.56, "learning_rate": 2.4407741985857883e-06, "epoch": 1.616463985032741, "percentage": 53.89, "elapsed_time": "13:28:28", "remaining_time": "11:31:41"}
56
+ {"current_steps": 550, "total_steps": 1002, "loss": 0.5591, "learning_rate": 2.359994141096666e-06, "epoch": 1.646398503274088, "percentage": 54.89, "elapsed_time": "13:43:16", "remaining_time": "11:16:35"}
57
+ {"current_steps": 560, "total_steps": 1002, "loss": 0.5495, "learning_rate": 2.279421415546392e-06, "epoch": 1.6763330215154348, "percentage": 55.89, "elapsed_time": "13:58:04", "remaining_time": "11:01:28"}
58
+ {"current_steps": 570, "total_steps": 1002, "loss": 0.5512, "learning_rate": 2.1991439418522963e-06, "epoch": 1.706267539756782, "percentage": 56.89, "elapsed_time": "14:12:53", "remaining_time": "10:46:23"}
59
+ {"current_steps": 580, "total_steps": 1002, "loss": 0.5515, "learning_rate": 2.119249317756697e-06, "epoch": 1.736202057998129, "percentage": 57.88, "elapsed_time": "14:27:40", "remaining_time": "10:31:18"}
60
+ {"current_steps": 590, "total_steps": 1002, "loss": 0.5547, "learning_rate": 2.039824723241373e-06, "epoch": 1.766136576239476, "percentage": 58.88, "elapsed_time": "14:42:26", "remaining_time": "10:16:12"}
61
+ {"current_steps": 600, "total_steps": 1002, "loss": 0.555, "learning_rate": 1.9609568253978996e-06, "epoch": 1.7960710944808231, "percentage": 59.88, "elapsed_time": "14:57:13", "remaining_time": "10:01:08"}
62
+ {"current_steps": 610, "total_steps": 1002, "loss": 0.5527, "learning_rate": 1.8827316838576325e-06, "epoch": 1.8260056127221702, "percentage": 60.88, "elapsed_time": "15:12:01", "remaining_time": "9:46:05"}
63
+ {"current_steps": 620, "total_steps": 1002, "loss": 0.5504, "learning_rate": 1.8052346568845544e-06, "epoch": 1.8559401309635173, "percentage": 61.88, "elapsed_time": "15:26:49", "remaining_time": "9:31:02"}
64
+ {"current_steps": 630, "total_steps": 1002, "loss": 0.552, "learning_rate": 1.7285503082334374e-06, "epoch": 1.8858746492048644, "percentage": 62.87, "elapsed_time": "15:41:37", "remaining_time": "9:16:00"}
65
+ {"current_steps": 640, "total_steps": 1002, "loss": 0.5536, "learning_rate": 1.6527623148749634e-06, "epoch": 1.9158091674462114, "percentage": 63.87, "elapsed_time": "15:56:26", "remaining_time": "9:00:59"}
66
+ {"current_steps": 650, "total_steps": 1002, "loss": 0.5512, "learning_rate": 1.5779533756885018e-06, "epoch": 1.9457436856875585, "percentage": 64.87, "elapsed_time": "16:11:15", "remaining_time": "8:45:58"}
67
+ {"current_steps": 660, "total_steps": 1002, "loss": 0.556, "learning_rate": 1.5042051212221528e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:26:03", "remaining_time": "8:30:57"}
68
+ {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6115813851356506, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:46:44", "remaining_time": "8:23:22"}
69
+ {"current_steps": 670, "total_steps": 1002, "loss": 0.6015, "learning_rate": 1.4315980246185532e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:50:52", "remaining_time": "8:20:54"}