Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v3.1-gemini-1.5-pro

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
7d6731b
·
verified ·
1 Parent(s): 44de1df

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 sha256:927ea0d7cca3dc2d5000803d4f913e4956576711456cc26cb213e884d8fa48da
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc07ca4eaa36fa2e130e174e67e36a2a41b1d0d83dc7d9d9ff8e3afc08dc069
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50006dc0e0f1863023ec7d4f3d7a82cb1d09d2736d7206bf5088c16a654b24
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6330d8b41fd9ab420074c18eed53d08b2801f0b10db6d2c1409de3e5000731b6
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e8052a7d48e005353e88cc4633f8f7a96eb0688206abf5c149b020806fe7214
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225d62253a6b0eccc296902ae8454e5157249dce2a61cbefe1a41beb9c928681
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca8f0e4e6875ecd2d3f94733da03264f211c7e018fca67cba6bc5805d4f427b1
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220cb9557bef435798047779b99525e63d64617bcb6986cdb4ea6b91cb47a15d
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -43,3 +43,48 @@
43
  {"current_steps": 430, "total_steps": 1320, "loss": 0.6438, "lr": 5e-06, "epoch": 0.975886524822695, "percentage": 32.58, "elapsed_time": "3:53:09", "remaining_time": "8:02:34"}
44
  {"current_steps": 440, "total_steps": 1320, "loss": 0.6478, "lr": 5e-06, "epoch": 0.9985815602836879, "percentage": 33.33, "elapsed_time": "3:58:33", "remaining_time": "7:57:06"}
45
  {"current_steps": 440, "total_steps": 1320, "eval_loss": 0.64774489402771, "epoch": 0.9985815602836879, "percentage": 33.33, "elapsed_time": "4:04:04", "remaining_time": "8:08:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1320, "loss": 0.6438, "lr": 5e-06, "epoch": 0.975886524822695, "percentage": 32.58, "elapsed_time": "3:53:09", "remaining_time": "8:02:34"}
44
  {"current_steps": 440, "total_steps": 1320, "loss": 0.6478, "lr": 5e-06, "epoch": 0.9985815602836879, "percentage": 33.33, "elapsed_time": "3:58:33", "remaining_time": "7:57:06"}
45
  {"current_steps": 440, "total_steps": 1320, "eval_loss": 0.64774489402771, "epoch": 0.9985815602836879, "percentage": 33.33, "elapsed_time": "4:04:04", "remaining_time": "8:08:08"}
46
+ {"current_steps": 450, "total_steps": 1320, "loss": 0.6161, "lr": 5e-06, "epoch": 1.0212765957446808, "percentage": 34.09, "elapsed_time": "4:10:25", "remaining_time": "8:04:09"}
47
+ {"current_steps": 460, "total_steps": 1320, "loss": 0.589, "lr": 5e-06, "epoch": 1.0439716312056737, "percentage": 34.85, "elapsed_time": "4:15:51", "remaining_time": "7:58:19"}
48
+ {"current_steps": 470, "total_steps": 1320, "loss": 0.5912, "lr": 5e-06, "epoch": 1.0666666666666667, "percentage": 35.61, "elapsed_time": "4:21:13", "remaining_time": "7:52:25"}
49
+ {"current_steps": 480, "total_steps": 1320, "loss": 0.5913, "lr": 5e-06, "epoch": 1.0893617021276596, "percentage": 36.36, "elapsed_time": "4:26:37", "remaining_time": "7:46:35"}
50
+ {"current_steps": 490, "total_steps": 1320, "loss": 0.5976, "lr": 5e-06, "epoch": 1.1120567375886525, "percentage": 37.12, "elapsed_time": "4:32:01", "remaining_time": "7:40:46"}
51
+ {"current_steps": 500, "total_steps": 1320, "loss": 0.5931, "lr": 5e-06, "epoch": 1.1347517730496455, "percentage": 37.88, "elapsed_time": "4:37:26", "remaining_time": "7:35:00"}
52
+ {"current_steps": 510, "total_steps": 1320, "loss": 0.5913, "lr": 5e-06, "epoch": 1.1574468085106382, "percentage": 38.64, "elapsed_time": "4:42:51", "remaining_time": "7:29:15"}
53
+ {"current_steps": 520, "total_steps": 1320, "loss": 0.5888, "lr": 5e-06, "epoch": 1.1801418439716311, "percentage": 39.39, "elapsed_time": "4:48:17", "remaining_time": "7:23:30"}
54
+ {"current_steps": 530, "total_steps": 1320, "loss": 0.5926, "lr": 5e-06, "epoch": 1.202836879432624, "percentage": 40.15, "elapsed_time": "4:53:42", "remaining_time": "7:17:47"}
55
+ {"current_steps": 540, "total_steps": 1320, "loss": 0.5905, "lr": 5e-06, "epoch": 1.225531914893617, "percentage": 40.91, "elapsed_time": "4:59:09", "remaining_time": "7:12:06"}
56
+ {"current_steps": 550, "total_steps": 1320, "loss": 0.5915, "lr": 5e-06, "epoch": 1.24822695035461, "percentage": 41.67, "elapsed_time": "5:04:35", "remaining_time": "7:06:25"}
57
+ {"current_steps": 560, "total_steps": 1320, "loss": 0.5948, "lr": 5e-06, "epoch": 1.270921985815603, "percentage": 42.42, "elapsed_time": "5:10:01", "remaining_time": "7:00:44"}
58
+ {"current_steps": 570, "total_steps": 1320, "loss": 0.5904, "lr": 5e-06, "epoch": 1.2936170212765958, "percentage": 43.18, "elapsed_time": "5:15:27", "remaining_time": "6:55:04"}
59
+ {"current_steps": 580, "total_steps": 1320, "loss": 0.5927, "lr": 5e-06, "epoch": 1.3163120567375888, "percentage": 43.94, "elapsed_time": "5:20:52", "remaining_time": "6:49:23"}
60
+ {"current_steps": 590, "total_steps": 1320, "loss": 0.5889, "lr": 5e-06, "epoch": 1.3390070921985815, "percentage": 44.7, "elapsed_time": "5:26:17", "remaining_time": "6:43:43"}
61
+ {"current_steps": 600, "total_steps": 1320, "loss": 0.5998, "lr": 5e-06, "epoch": 1.3617021276595744, "percentage": 45.45, "elapsed_time": "5:31:41", "remaining_time": "6:38:02"}
62
+ {"current_steps": 610, "total_steps": 1320, "loss": 0.5933, "lr": 5e-06, "epoch": 1.3843971631205674, "percentage": 46.21, "elapsed_time": "5:37:07", "remaining_time": "6:32:23"}
63
+ {"current_steps": 620, "total_steps": 1320, "loss": 0.5967, "lr": 5e-06, "epoch": 1.4070921985815603, "percentage": 46.97, "elapsed_time": "5:42:31", "remaining_time": "6:26:43"}
64
+ {"current_steps": 630, "total_steps": 1320, "loss": 0.5886, "lr": 5e-06, "epoch": 1.4297872340425533, "percentage": 47.73, "elapsed_time": "5:47:57", "remaining_time": "6:21:05"}
65
+ {"current_steps": 640, "total_steps": 1320, "loss": 0.5931, "lr": 5e-06, "epoch": 1.452482269503546, "percentage": 48.48, "elapsed_time": "5:53:23", "remaining_time": "6:15:28"}
66
+ {"current_steps": 650, "total_steps": 1320, "loss": 0.5926, "lr": 5e-06, "epoch": 1.475177304964539, "percentage": 49.24, "elapsed_time": "5:58:46", "remaining_time": "6:09:48"}
67
+ {"current_steps": 660, "total_steps": 1320, "loss": 0.5969, "lr": 5e-06, "epoch": 1.4978723404255319, "percentage": 50.0, "elapsed_time": "6:04:11", "remaining_time": "6:04:11"}
68
+ {"current_steps": 670, "total_steps": 1320, "loss": 0.5868, "lr": 5e-06, "epoch": 1.5205673758865248, "percentage": 50.76, "elapsed_time": "6:09:36", "remaining_time": "5:58:34"}
69
+ {"current_steps": 680, "total_steps": 1320, "loss": 0.5893, "lr": 5e-06, "epoch": 1.5432624113475177, "percentage": 51.52, "elapsed_time": "6:15:02", "remaining_time": "5:52:59"}
70
+ {"current_steps": 690, "total_steps": 1320, "loss": 0.5937, "lr": 5e-06, "epoch": 1.5659574468085107, "percentage": 52.27, "elapsed_time": "6:20:28", "remaining_time": "5:47:23"}
71
+ {"current_steps": 700, "total_steps": 1320, "loss": 0.5856, "lr": 5e-06, "epoch": 1.5886524822695036, "percentage": 53.03, "elapsed_time": "6:25:55", "remaining_time": "5:41:48"}
72
+ {"current_steps": 710, "total_steps": 1320, "loss": 0.5796, "lr": 5e-06, "epoch": 1.6113475177304966, "percentage": 53.79, "elapsed_time": "6:31:19", "remaining_time": "5:36:12"}
73
+ {"current_steps": 720, "total_steps": 1320, "loss": 0.584, "lr": 5e-06, "epoch": 1.6340425531914895, "percentage": 54.55, "elapsed_time": "6:36:45", "remaining_time": "5:30:37"}
74
+ {"current_steps": 730, "total_steps": 1320, "loss": 0.5882, "lr": 5e-06, "epoch": 1.6567375886524822, "percentage": 55.3, "elapsed_time": "6:42:11", "remaining_time": "5:25:03"}
75
+ {"current_steps": 740, "total_steps": 1320, "loss": 0.5893, "lr": 5e-06, "epoch": 1.6794326241134752, "percentage": 56.06, "elapsed_time": "6:47:37", "remaining_time": "5:19:29"}
76
+ {"current_steps": 750, "total_steps": 1320, "loss": 0.5895, "lr": 5e-06, "epoch": 1.702127659574468, "percentage": 56.82, "elapsed_time": "6:53:02", "remaining_time": "5:13:54"}
77
+ {"current_steps": 760, "total_steps": 1320, "loss": 0.5883, "lr": 5e-06, "epoch": 1.724822695035461, "percentage": 57.58, "elapsed_time": "6:58:24", "remaining_time": "5:08:17"}
78
+ {"current_steps": 770, "total_steps": 1320, "loss": 0.5908, "lr": 5e-06, "epoch": 1.7475177304964538, "percentage": 58.33, "elapsed_time": "7:03:47", "remaining_time": "5:02:42"}
79
+ {"current_steps": 780, "total_steps": 1320, "loss": 0.5935, "lr": 5e-06, "epoch": 1.7702127659574467, "percentage": 59.09, "elapsed_time": "7:09:14", "remaining_time": "4:57:09"}
80
+ {"current_steps": 790, "total_steps": 1320, "loss": 0.5833, "lr": 5e-06, "epoch": 1.7929078014184396, "percentage": 59.85, "elapsed_time": "7:14:40", "remaining_time": "4:51:37"}
81
+ {"current_steps": 800, "total_steps": 1320, "loss": 0.5853, "lr": 5e-06, "epoch": 1.8156028368794326, "percentage": 60.61, "elapsed_time": "7:20:04", "remaining_time": "4:46:02"}
82
+ {"current_steps": 810, "total_steps": 1320, "loss": 0.5823, "lr": 5e-06, "epoch": 1.8382978723404255, "percentage": 61.36, "elapsed_time": "7:25:29", "remaining_time": "4:40:29"}
83
+ {"current_steps": 820, "total_steps": 1320, "loss": 0.5903, "lr": 5e-06, "epoch": 1.8609929078014185, "percentage": 62.12, "elapsed_time": "7:30:55", "remaining_time": "4:34:57"}
84
+ {"current_steps": 830, "total_steps": 1320, "loss": 0.5832, "lr": 5e-06, "epoch": 1.8836879432624114, "percentage": 62.88, "elapsed_time": "7:36:19", "remaining_time": "4:29:23"}
85
+ {"current_steps": 840, "total_steps": 1320, "loss": 0.5855, "lr": 5e-06, "epoch": 1.9063829787234043, "percentage": 63.64, "elapsed_time": "7:41:43", "remaining_time": "4:23:50"}
86
+ {"current_steps": 850, "total_steps": 1320, "loss": 0.5842, "lr": 5e-06, "epoch": 1.9290780141843973, "percentage": 64.39, "elapsed_time": "7:47:09", "remaining_time": "4:18:18"}
87
+ {"current_steps": 860, "total_steps": 1320, "loss": 0.5821, "lr": 5e-06, "epoch": 1.9517730496453902, "percentage": 65.15, "elapsed_time": "7:52:35", "remaining_time": "4:12:46"}
88
+ {"current_steps": 870, "total_steps": 1320, "loss": 0.5865, "lr": 5e-06, "epoch": 1.974468085106383, "percentage": 65.91, "elapsed_time": "7:58:00", "remaining_time": "4:07:14"}
89
+ {"current_steps": 880, "total_steps": 1320, "loss": 0.5869, "lr": 5e-06, "epoch": 1.9971631205673759, "percentage": 66.67, "elapsed_time": "8:03:23", "remaining_time": "4:01:41"}
90
+ {"current_steps": 881, "total_steps": 1320, "eval_loss": 0.63065505027771, "epoch": 1.9994326241134752, "percentage": 66.74, "elapsed_time": "8:08:57", "remaining_time": "4:03:38"}