Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.95

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
4fea40b
·
verified ·
1 Parent(s): 528bced

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 +45 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2eeecffa37dffc624ba05cf4a5566f425e115dc00cb2a265e5f44340653dd3f
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2858bdf0313445d0c64c98fa6cfa71dd1c9724dcd6f072b94ea247654a077279
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:f3180115dde6011921a61c19739ae555198a6fde2eb0c5d56b13423ff7723067
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be4acbd177d4252e5f3a492fb61f0387090bbe332fe8bc8ac5cf2eb11eeaa984
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:fc60f7ce4bdfcde6d7482a234cfb2db1c2acaacf3f95e414e00e04464b01c40c
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2524cc26e222252c24c43b8cbd30731135b17905e0c4d448ee74ecb3fa45231a
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:f3b4dc80b2cf004d2333e8aa75620291e329ddafa41abe0895bff02cf460d1c9
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbeed37582edf11b0ee5eea36ebacaa3540dbc33d4bb807c4a42f99dcf3159d
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -43,3 +43,48 @@
43
  {"current_steps": 430, "total_steps": 1329, "loss": 0.5888, "learning_rate": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "10:44:14", "remaining_time": "22:26:53"}
44
  {"current_steps": 440, "total_steps": 1329, "loss": 0.5936, "learning_rate": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "10:59:12", "remaining_time": "22:11:54"}
45
  {"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5913681387901306, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "11:15:31", "remaining_time": "22:31:02"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1329, "loss": 0.5888, "learning_rate": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "10:44:14", "remaining_time": "22:26:53"}
44
  {"current_steps": 440, "total_steps": 1329, "loss": 0.5936, "learning_rate": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "10:59:12", "remaining_time": "22:11:54"}
45
  {"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5913681387901306, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "11:15:31", "remaining_time": "22:31:02"}
46
+ {"current_steps": 450, "total_steps": 1329, "loss": 0.6006, "learning_rate": 5e-06, "epoch": 1.0155148095909732, "percentage": 33.86, "elapsed_time": "11:27:05", "remaining_time": "22:22:07"}
47
+ {"current_steps": 460, "total_steps": 1329, "loss": 0.5274, "learning_rate": 5e-06, "epoch": 1.0380818053596614, "percentage": 34.61, "elapsed_time": "11:42:03", "remaining_time": "22:06:17"}
48
+ {"current_steps": 470, "total_steps": 1329, "loss": 0.5421, "learning_rate": 5e-06, "epoch": 1.0606488011283497, "percentage": 35.36, "elapsed_time": "11:57:01", "remaining_time": "21:50:29"}
49
+ {"current_steps": 480, "total_steps": 1329, "loss": 0.53, "learning_rate": 5e-06, "epoch": 1.0832157968970382, "percentage": 36.12, "elapsed_time": "12:12:00", "remaining_time": "21:34:44"}
50
+ {"current_steps": 490, "total_steps": 1329, "loss": 0.5401, "learning_rate": 5e-06, "epoch": 1.1057827926657264, "percentage": 36.87, "elapsed_time": "12:26:59", "remaining_time": "21:19:02"}
51
+ {"current_steps": 500, "total_steps": 1329, "loss": 0.5387, "learning_rate": 5e-06, "epoch": 1.1283497884344147, "percentage": 37.62, "elapsed_time": "12:41:58", "remaining_time": "21:03:21"}
52
+ {"current_steps": 510, "total_steps": 1329, "loss": 0.5399, "learning_rate": 5e-06, "epoch": 1.150916784203103, "percentage": 38.37, "elapsed_time": "12:56:56", "remaining_time": "20:47:41"}
53
+ {"current_steps": 520, "total_steps": 1329, "loss": 0.5324, "learning_rate": 5e-06, "epoch": 1.1734837799717912, "percentage": 39.13, "elapsed_time": "13:11:56", "remaining_time": "20:32:04"}
54
+ {"current_steps": 530, "total_steps": 1329, "loss": 0.5387, "learning_rate": 5e-06, "epoch": 1.1960507757404795, "percentage": 39.88, "elapsed_time": "13:26:54", "remaining_time": "20:16:26"}
55
+ {"current_steps": 540, "total_steps": 1329, "loss": 0.536, "learning_rate": 5e-06, "epoch": 1.2186177715091677, "percentage": 40.63, "elapsed_time": "13:41:52", "remaining_time": "20:00:50"}
56
+ {"current_steps": 550, "total_steps": 1329, "loss": 0.5408, "learning_rate": 5e-06, "epoch": 1.2411847672778562, "percentage": 41.38, "elapsed_time": "13:56:50", "remaining_time": "19:45:15"}
57
+ {"current_steps": 560, "total_steps": 1329, "loss": 0.5427, "learning_rate": 5e-06, "epoch": 1.2637517630465445, "percentage": 42.14, "elapsed_time": "14:11:48", "remaining_time": "19:29:42"}
58
+ {"current_steps": 570, "total_steps": 1329, "loss": 0.54, "learning_rate": 5e-06, "epoch": 1.2863187588152327, "percentage": 42.89, "elapsed_time": "14:26:46", "remaining_time": "19:14:10"}
59
+ {"current_steps": 580, "total_steps": 1329, "loss": 0.5398, "learning_rate": 5e-06, "epoch": 1.308885754583921, "percentage": 43.64, "elapsed_time": "14:41:44", "remaining_time": "18:58:39"}
60
+ {"current_steps": 590, "total_steps": 1329, "loss": 0.54, "learning_rate": 5e-06, "epoch": 1.3314527503526092, "percentage": 44.39, "elapsed_time": "14:56:42", "remaining_time": "18:43:10"}
61
+ {"current_steps": 600, "total_steps": 1329, "loss": 0.5453, "learning_rate": 5e-06, "epoch": 1.3540197461212977, "percentage": 45.15, "elapsed_time": "15:11:40", "remaining_time": "18:27:41"}
62
+ {"current_steps": 610, "total_steps": 1329, "loss": 0.538, "learning_rate": 5e-06, "epoch": 1.376586741889986, "percentage": 45.9, "elapsed_time": "15:26:39", "remaining_time": "18:12:14"}
63
+ {"current_steps": 620, "total_steps": 1329, "loss": 0.5422, "learning_rate": 5e-06, "epoch": 1.3991537376586742, "percentage": 46.65, "elapsed_time": "15:41:36", "remaining_time": "17:56:46"}
64
+ {"current_steps": 630, "total_steps": 1329, "loss": 0.5404, "learning_rate": 5e-06, "epoch": 1.4217207334273625, "percentage": 47.4, "elapsed_time": "15:56:34", "remaining_time": "17:41:20"}
65
+ {"current_steps": 640, "total_steps": 1329, "loss": 0.54, "learning_rate": 5e-06, "epoch": 1.4442877291960508, "percentage": 48.16, "elapsed_time": "16:11:33", "remaining_time": "17:25:56"}
66
+ {"current_steps": 650, "total_steps": 1329, "loss": 0.5409, "learning_rate": 5e-06, "epoch": 1.466854724964739, "percentage": 48.91, "elapsed_time": "16:26:29", "remaining_time": "17:10:30"}
67
+ {"current_steps": 660, "total_steps": 1329, "loss": 0.5447, "learning_rate": 5e-06, "epoch": 1.4894217207334273, "percentage": 49.66, "elapsed_time": "16:41:28", "remaining_time": "16:55:08"}
68
+ {"current_steps": 670, "total_steps": 1329, "loss": 0.5393, "learning_rate": 5e-06, "epoch": 1.5119887165021155, "percentage": 50.41, "elapsed_time": "16:56:28", "remaining_time": "16:39:47"}
69
+ {"current_steps": 680, "total_steps": 1329, "loss": 0.5336, "learning_rate": 5e-06, "epoch": 1.5345557122708038, "percentage": 51.17, "elapsed_time": "17:11:26", "remaining_time": "16:24:25"}
70
+ {"current_steps": 690, "total_steps": 1329, "loss": 0.5357, "learning_rate": 5e-06, "epoch": 1.5571227080394923, "percentage": 51.92, "elapsed_time": "17:26:26", "remaining_time": "16:09:05"}
71
+ {"current_steps": 700, "total_steps": 1329, "loss": 0.5399, "learning_rate": 5e-06, "epoch": 1.5796897038081805, "percentage": 52.67, "elapsed_time": "17:41:23", "remaining_time": "15:53:44"}
72
+ {"current_steps": 710, "total_steps": 1329, "loss": 0.5427, "learning_rate": 5e-06, "epoch": 1.6022566995768688, "percentage": 53.42, "elapsed_time": "17:56:20", "remaining_time": "15:38:23"}
73
+ {"current_steps": 720, "total_steps": 1329, "loss": 0.5507, "learning_rate": 5e-06, "epoch": 1.6248236953455573, "percentage": 54.18, "elapsed_time": "18:11:18", "remaining_time": "15:23:03"}
74
+ {"current_steps": 730, "total_steps": 1329, "loss": 0.5339, "learning_rate": 5e-06, "epoch": 1.6473906911142455, "percentage": 54.93, "elapsed_time": "18:26:15", "remaining_time": "15:07:43"}
75
+ {"current_steps": 740, "total_steps": 1329, "loss": 0.5498, "learning_rate": 5e-06, "epoch": 1.6699576868829338, "percentage": 55.68, "elapsed_time": "18:41:13", "remaining_time": "14:52:26"}
76
+ {"current_steps": 750, "total_steps": 1329, "loss": 0.5412, "learning_rate": 5e-06, "epoch": 1.692524682651622, "percentage": 56.43, "elapsed_time": "18:56:12", "remaining_time": "14:37:09"}
77
+ {"current_steps": 760, "total_steps": 1329, "loss": 0.5402, "learning_rate": 5e-06, "epoch": 1.7150916784203103, "percentage": 57.19, "elapsed_time": "19:11:10", "remaining_time": "14:21:52"}
78
+ {"current_steps": 770, "total_steps": 1329, "loss": 0.5414, "learning_rate": 5e-06, "epoch": 1.7376586741889986, "percentage": 57.94, "elapsed_time": "19:26:09", "remaining_time": "14:06:36"}
79
+ {"current_steps": 780, "total_steps": 1329, "loss": 0.5367, "learning_rate": 5e-06, "epoch": 1.7602256699576868, "percentage": 58.69, "elapsed_time": "19:41:07", "remaining_time": "13:51:20"}
80
+ {"current_steps": 790, "total_steps": 1329, "loss": 0.54, "learning_rate": 5e-06, "epoch": 1.782792665726375, "percentage": 59.44, "elapsed_time": "19:56:06", "remaining_time": "13:36:04"}
81
+ {"current_steps": 800, "total_steps": 1329, "loss": 0.5351, "learning_rate": 5e-06, "epoch": 1.8053596614950633, "percentage": 60.2, "elapsed_time": "20:11:05", "remaining_time": "13:20:49"}
82
+ {"current_steps": 810, "total_steps": 1329, "loss": 0.5458, "learning_rate": 5e-06, "epoch": 1.8279266572637518, "percentage": 60.95, "elapsed_time": "20:26:04", "remaining_time": "13:05:35"}
83
+ {"current_steps": 820, "total_steps": 1329, "loss": 0.5332, "learning_rate": 5e-06, "epoch": 1.85049365303244, "percentage": 61.7, "elapsed_time": "20:41:03", "remaining_time": "12:50:21"}
84
+ {"current_steps": 830, "total_steps": 1329, "loss": 0.5453, "learning_rate": 5e-06, "epoch": 1.8730606488011283, "percentage": 62.45, "elapsed_time": "20:56:02", "remaining_time": "12:35:08"}
85
+ {"current_steps": 840, "total_steps": 1329, "loss": 0.5454, "learning_rate": 5e-06, "epoch": 1.8956276445698168, "percentage": 63.21, "elapsed_time": "21:11:01", "remaining_time": "12:19:55"}
86
+ {"current_steps": 850, "total_steps": 1329, "loss": 0.5334, "learning_rate": 5e-06, "epoch": 1.918194640338505, "percentage": 63.96, "elapsed_time": "21:25:59", "remaining_time": "12:04:41"}
87
+ {"current_steps": 860, "total_steps": 1329, "loss": 0.5384, "learning_rate": 5e-06, "epoch": 1.9407616361071933, "percentage": 64.71, "elapsed_time": "21:40:56", "remaining_time": "11:49:28"}
88
+ {"current_steps": 870, "total_steps": 1329, "loss": 0.5449, "learning_rate": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:55:55", "remaining_time": "11:34:15"}
89
+ {"current_steps": 880, "total_steps": 1329, "loss": 0.5431, "learning_rate": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:10:54", "remaining_time": "11:19:03"}
90
+ {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.587314784526825, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:31:50", "remaining_time": "11:15:55"}