Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_epoch3

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
02af0cc
·
verified ·
1 Parent(s): 93e2466

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:eec643d245058fa9d0ee011f2192f5b0df0235c89e1d4421ad03fa56055a7051
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9e6a4ebd34705b6a20e1ec65f00a977bfb774630fa0ff6a9b52ed70f9b548f
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:910b4205f8e2bd74ca5f007ff3beb2932456f220ba6da92aa0cdb5969b70a028
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c60b68c16be2eda0fc274839c1a270524eb9928b296aa5897dd8a64844339f5
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:bf5f5f1384e301b3ce68f06772bfb607994c5a4e39d4db3371eec522f7f09af3
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1239068a8483d6206e6aaac9c517f1fe049327a0cc774be888b3e263e9a35f78
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:d8e7fb6a427a5e851e707f22f4f374ce6179961252d3ce4f5b13a442e6dce775
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f913dde7f121d7e067815841a0d8841f1ae94c5a0bbe079fc80e3f51cbde2a8
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -43,3 +43,48 @@
43
  {"current_steps": 430, "total_steps": 1329, "loss": 0.5887, "lr": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "5:28:13", "remaining_time": "11:26:13"}
44
  {"current_steps": 440, "total_steps": 1329, "loss": 0.5935, "lr": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "5:35:51", "remaining_time": "11:18:35"}
45
  {"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5913009643554688, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "5:44:15", "remaining_time": "11:28:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1329, "loss": 0.5887, "lr": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "5:28:13", "remaining_time": "11:26:13"}
44
  {"current_steps": 440, "total_steps": 1329, "loss": 0.5935, "lr": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "5:35:51", "remaining_time": "11:18:35"}
45
  {"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5913009643554688, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "5:44:15", "remaining_time": "11:28:31"}
46
+ {"current_steps": 450, "total_steps": 1329, "loss": 0.6021, "lr": 5e-06, "epoch": 1.0155148095909732, "percentage": 33.86, "elapsed_time": "5:50:34", "remaining_time": "11:24:46"}
47
+ {"current_steps": 460, "total_steps": 1329, "loss": 0.528, "lr": 5e-06, "epoch": 1.0380818053596614, "percentage": 34.61, "elapsed_time": "5:58:12", "remaining_time": "11:16:41"}
48
+ {"current_steps": 470, "total_steps": 1329, "loss": 0.543, "lr": 5e-06, "epoch": 1.0606488011283497, "percentage": 35.36, "elapsed_time": "6:05:50", "remaining_time": "11:08:38"}
49
+ {"current_steps": 480, "total_steps": 1329, "loss": 0.5306, "lr": 5e-06, "epoch": 1.0832157968970382, "percentage": 36.12, "elapsed_time": "6:13:29", "remaining_time": "11:00:35"}
50
+ {"current_steps": 490, "total_steps": 1329, "loss": 0.541, "lr": 5e-06, "epoch": 1.1057827926657264, "percentage": 36.87, "elapsed_time": "6:21:07", "remaining_time": "10:52:34"}
51
+ {"current_steps": 500, "total_steps": 1329, "loss": 0.5393, "lr": 5e-06, "epoch": 1.1283497884344147, "percentage": 37.62, "elapsed_time": "6:28:45", "remaining_time": "10:44:34"}
52
+ {"current_steps": 510, "total_steps": 1329, "loss": 0.5409, "lr": 5e-06, "epoch": 1.150916784203103, "percentage": 38.37, "elapsed_time": "6:36:24", "remaining_time": "10:36:34"}
53
+ {"current_steps": 520, "total_steps": 1329, "loss": 0.5336, "lr": 5e-06, "epoch": 1.1734837799717912, "percentage": 39.13, "elapsed_time": "6:44:02", "remaining_time": "10:28:35"}
54
+ {"current_steps": 530, "total_steps": 1329, "loss": 0.5393, "lr": 5e-06, "epoch": 1.1960507757404795, "percentage": 39.88, "elapsed_time": "6:51:41", "remaining_time": "10:20:38"}
55
+ {"current_steps": 540, "total_steps": 1329, "loss": 0.5371, "lr": 5e-06, "epoch": 1.2186177715091677, "percentage": 40.63, "elapsed_time": "6:59:18", "remaining_time": "10:12:40"}
56
+ {"current_steps": 550, "total_steps": 1329, "loss": 0.5422, "lr": 5e-06, "epoch": 1.2411847672778562, "percentage": 41.38, "elapsed_time": "7:06:57", "remaining_time": "10:04:43"}
57
+ {"current_steps": 560, "total_steps": 1329, "loss": 0.5438, "lr": 5e-06, "epoch": 1.2637517630465445, "percentage": 42.14, "elapsed_time": "7:14:35", "remaining_time": "9:56:46"}
58
+ {"current_steps": 570, "total_steps": 1329, "loss": 0.5415, "lr": 5e-06, "epoch": 1.2863187588152327, "percentage": 42.89, "elapsed_time": "7:22:13", "remaining_time": "9:48:51"}
59
+ {"current_steps": 580, "total_steps": 1329, "loss": 0.5409, "lr": 5e-06, "epoch": 1.308885754583921, "percentage": 43.64, "elapsed_time": "7:29:51", "remaining_time": "9:40:56"}
60
+ {"current_steps": 590, "total_steps": 1329, "loss": 0.5409, "lr": 5e-06, "epoch": 1.3314527503526092, "percentage": 44.39, "elapsed_time": "7:37:29", "remaining_time": "9:33:02"}
61
+ {"current_steps": 600, "total_steps": 1329, "loss": 0.5463, "lr": 5e-06, "epoch": 1.3540197461212977, "percentage": 45.15, "elapsed_time": "7:45:08", "remaining_time": "9:25:08"}
62
+ {"current_steps": 610, "total_steps": 1329, "loss": 0.539, "lr": 5e-06, "epoch": 1.376586741889986, "percentage": 45.9, "elapsed_time": "7:52:46", "remaining_time": "9:17:15"}
63
+ {"current_steps": 620, "total_steps": 1329, "loss": 0.543, "lr": 5e-06, "epoch": 1.3991537376586742, "percentage": 46.65, "elapsed_time": "8:00:24", "remaining_time": "9:09:22"}
64
+ {"current_steps": 630, "total_steps": 1329, "loss": 0.5411, "lr": 5e-06, "epoch": 1.4217207334273625, "percentage": 47.4, "elapsed_time": "8:08:03", "remaining_time": "9:01:30"}
65
+ {"current_steps": 640, "total_steps": 1329, "loss": 0.5407, "lr": 5e-06, "epoch": 1.4442877291960508, "percentage": 48.16, "elapsed_time": "8:15:42", "remaining_time": "8:53:39"}
66
+ {"current_steps": 650, "total_steps": 1329, "loss": 0.5418, "lr": 5e-06, "epoch": 1.466854724964739, "percentage": 48.91, "elapsed_time": "8:23:20", "remaining_time": "8:45:47"}
67
+ {"current_steps": 660, "total_steps": 1329, "loss": 0.5456, "lr": 5e-06, "epoch": 1.4894217207334273, "percentage": 49.66, "elapsed_time": "8:30:59", "remaining_time": "8:37:57"}
68
+ {"current_steps": 670, "total_steps": 1329, "loss": 0.5405, "lr": 5e-06, "epoch": 1.5119887165021155, "percentage": 50.41, "elapsed_time": "8:38:37", "remaining_time": "8:30:06"}
69
+ {"current_steps": 680, "total_steps": 1329, "loss": 0.5345, "lr": 5e-06, "epoch": 1.5345557122708038, "percentage": 51.17, "elapsed_time": "8:46:16", "remaining_time": "8:22:16"}
70
+ {"current_steps": 690, "total_steps": 1329, "loss": 0.537, "lr": 5e-06, "epoch": 1.5571227080394923, "percentage": 51.92, "elapsed_time": "8:53:54", "remaining_time": "8:14:26"}
71
+ {"current_steps": 700, "total_steps": 1329, "loss": 0.5407, "lr": 5e-06, "epoch": 1.5796897038081805, "percentage": 52.67, "elapsed_time": "9:01:32", "remaining_time": "8:06:37"}
72
+ {"current_steps": 710, "total_steps": 1329, "loss": 0.5437, "lr": 5e-06, "epoch": 1.6022566995768688, "percentage": 53.42, "elapsed_time": "9:09:11", "remaining_time": "7:58:48"}
73
+ {"current_steps": 720, "total_steps": 1329, "loss": 0.5516, "lr": 5e-06, "epoch": 1.6248236953455573, "percentage": 54.18, "elapsed_time": "9:16:50", "remaining_time": "7:50:59"}
74
+ {"current_steps": 730, "total_steps": 1329, "loss": 0.5347, "lr": 5e-06, "epoch": 1.6473906911142455, "percentage": 54.93, "elapsed_time": "9:24:27", "remaining_time": "7:43:10"}
75
+ {"current_steps": 740, "total_steps": 1329, "loss": 0.5506, "lr": 5e-06, "epoch": 1.6699576868829338, "percentage": 55.68, "elapsed_time": "9:32:06", "remaining_time": "7:35:21"}
76
+ {"current_steps": 750, "total_steps": 1329, "loss": 0.5424, "lr": 5e-06, "epoch": 1.692524682651622, "percentage": 56.43, "elapsed_time": "9:39:44", "remaining_time": "7:27:33"}
77
+ {"current_steps": 760, "total_steps": 1329, "loss": 0.5412, "lr": 5e-06, "epoch": 1.7150916784203103, "percentage": 57.19, "elapsed_time": "9:47:22", "remaining_time": "7:19:45"}
78
+ {"current_steps": 770, "total_steps": 1329, "loss": 0.5414, "lr": 5e-06, "epoch": 1.7376586741889986, "percentage": 57.94, "elapsed_time": "9:55:00", "remaining_time": "7:11:57"}
79
+ {"current_steps": 780, "total_steps": 1329, "loss": 0.5372, "lr": 5e-06, "epoch": 1.7602256699576868, "percentage": 58.69, "elapsed_time": "10:02:39", "remaining_time": "7:04:10"}
80
+ {"current_steps": 790, "total_steps": 1329, "loss": 0.5411, "lr": 5e-06, "epoch": 1.782792665726375, "percentage": 59.44, "elapsed_time": "10:10:17", "remaining_time": "6:56:23"}
81
+ {"current_steps": 800, "total_steps": 1329, "loss": 0.5364, "lr": 5e-06, "epoch": 1.8053596614950633, "percentage": 60.2, "elapsed_time": "10:17:55", "remaining_time": "6:48:36"}
82
+ {"current_steps": 810, "total_steps": 1329, "loss": 0.5471, "lr": 5e-06, "epoch": 1.8279266572637518, "percentage": 60.95, "elapsed_time": "10:25:34", "remaining_time": "6:40:49"}
83
+ {"current_steps": 820, "total_steps": 1329, "loss": 0.5343, "lr": 5e-06, "epoch": 1.85049365303244, "percentage": 61.7, "elapsed_time": "10:33:12", "remaining_time": "6:33:03"}
84
+ {"current_steps": 830, "total_steps": 1329, "loss": 0.546, "lr": 5e-06, "epoch": 1.8730606488011283, "percentage": 62.45, "elapsed_time": "10:40:50", "remaining_time": "6:25:16"}
85
+ {"current_steps": 840, "total_steps": 1329, "loss": 0.5461, "lr": 5e-06, "epoch": 1.8956276445698168, "percentage": 63.21, "elapsed_time": "10:48:28", "remaining_time": "6:17:30"}
86
+ {"current_steps": 850, "total_steps": 1329, "loss": 0.5342, "lr": 5e-06, "epoch": 1.918194640338505, "percentage": 63.96, "elapsed_time": "10:56:07", "remaining_time": "6:09:44"}
87
+ {"current_steps": 860, "total_steps": 1329, "loss": 0.5391, "lr": 5e-06, "epoch": 1.9407616361071933, "percentage": 64.71, "elapsed_time": "11:03:45", "remaining_time": "6:01:58"}
88
+ {"current_steps": 870, "total_steps": 1329, "loss": 0.5457, "lr": 5e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "11:11:23", "remaining_time": "5:54:12"}
89
+ {"current_steps": 880, "total_steps": 1329, "loss": 0.5435, "lr": 5e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "11:19:01", "remaining_time": "5:46:27"}
90
+ {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5871431231498718, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "11:29:49", "remaining_time": "5:44:54"}