Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.995_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
5a9ff3f
•
1 Parent(s): 57b2999

Training in progress, epoch 2

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 sha256:148095ef68c8274c73d683bf79a6cb09db892bf600bf7624082408e1ff9789da
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85071f7363f95e48b02564a4ac9de527c521ffe3770428c3186bf22c75c39b08
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bc23a8a1b35ba3ac6453a4a1e50c6a4531f5cf7bd9ccc2ac33cbdf3aa9b7a31
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9e4659f5f5b0adbb70a9e349135eb743a956be62dd6d92794b957c697c032e
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:e3a5625495c997c43878198e85bbdff0690e29913ac1c0b00af4dae1f11acd41
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:761c18d208280cb5a535c973ff937daa227ff05a1f120b0e26f6178ca2a94dab
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:232a9ad23db4319b2aeddd84edeefbf1490221e278b6ff268fe9c5a9fd18de70
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcc6718a4bc05bdce70664287b3fa1184acadbc6a35f04977b9fd520be4eba4
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -67,3 +67,36 @@
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:22:31", "remaining_time": "8:29:07"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6157492399215698, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:43:01", "remaining_time": "8:21:30"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6006, "learning_rate": 5e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:47:10", "remaining_time": "8:19:04"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:22:31", "remaining_time": "8:29:07"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6157492399215698, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:43:01", "remaining_time": "8:21:30"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6006, "learning_rate": 5e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:47:10", "remaining_time": "8:19:04"}
70
+ {"current_steps": 680, "total_steps": 1002, "loss": 0.4848, "learning_rate": 5e-06, "epoch": 2.0355472404115997, "percentage": 67.86, "elapsed_time": "17:01:56", "remaining_time": "8:03:55"}
71
+ {"current_steps": 690, "total_steps": 1002, "loss": 0.4807, "learning_rate": 5e-06, "epoch": 2.065481758652947, "percentage": 68.86, "elapsed_time": "17:16:39", "remaining_time": "7:48:44"}
72
+ {"current_steps": 700, "total_steps": 1002, "loss": 0.4851, "learning_rate": 5e-06, "epoch": 2.095416276894294, "percentage": 69.86, "elapsed_time": "17:31:25", "remaining_time": "7:33:36"}
73
+ {"current_steps": 710, "total_steps": 1002, "loss": 0.4854, "learning_rate": 5e-06, "epoch": 2.125350795135641, "percentage": 70.86, "elapsed_time": "17:46:09", "remaining_time": "7:18:28"}
74
+ {"current_steps": 720, "total_steps": 1002, "loss": 0.4889, "learning_rate": 5e-06, "epoch": 2.155285313376988, "percentage": 71.86, "elapsed_time": "18:00:54", "remaining_time": "7:03:21"}
75
+ {"current_steps": 730, "total_steps": 1002, "loss": 0.4889, "learning_rate": 5e-06, "epoch": 2.185219831618335, "percentage": 72.85, "elapsed_time": "18:15:41", "remaining_time": "6:48:15"}
76
+ {"current_steps": 740, "total_steps": 1002, "loss": 0.4897, "learning_rate": 5e-06, "epoch": 2.2151543498596817, "percentage": 73.85, "elapsed_time": "18:30:27", "remaining_time": "6:33:09"}
77
+ {"current_steps": 750, "total_steps": 1002, "loss": 0.492, "learning_rate": 5e-06, "epoch": 2.245088868101029, "percentage": 74.85, "elapsed_time": "18:45:12", "remaining_time": "6:18:04"}
78
+ {"current_steps": 760, "total_steps": 1002, "loss": 0.4876, "learning_rate": 5e-06, "epoch": 2.275023386342376, "percentage": 75.85, "elapsed_time": "19:00:00", "remaining_time": "6:03:00"}
79
+ {"current_steps": 770, "total_steps": 1002, "loss": 0.4927, "learning_rate": 5e-06, "epoch": 2.304957904583723, "percentage": 76.85, "elapsed_time": "19:14:46", "remaining_time": "5:47:55"}
80
+ {"current_steps": 780, "total_steps": 1002, "loss": 0.4885, "learning_rate": 5e-06, "epoch": 2.33489242282507, "percentage": 77.84, "elapsed_time": "19:29:32", "remaining_time": "5:32:52"}
81
+ {"current_steps": 790, "total_steps": 1002, "loss": 0.4902, "learning_rate": 5e-06, "epoch": 2.364826941066417, "percentage": 78.84, "elapsed_time": "19:44:16", "remaining_time": "5:17:48"}
82
+ {"current_steps": 800, "total_steps": 1002, "loss": 0.493, "learning_rate": 5e-06, "epoch": 2.394761459307764, "percentage": 79.84, "elapsed_time": "19:59:01", "remaining_time": "5:02:45"}
83
+ {"current_steps": 810, "total_steps": 1002, "loss": 0.4997, "learning_rate": 5e-06, "epoch": 2.4246959775491113, "percentage": 80.84, "elapsed_time": "20:13:44", "remaining_time": "4:47:42"}
84
+ {"current_steps": 820, "total_steps": 1002, "loss": 0.4969, "learning_rate": 5e-06, "epoch": 2.4546304957904583, "percentage": 81.84, "elapsed_time": "20:28:26", "remaining_time": "4:32:39"}
85
+ {"current_steps": 830, "total_steps": 1002, "loss": 0.4966, "learning_rate": 5e-06, "epoch": 2.4845650140318054, "percentage": 82.83, "elapsed_time": "20:43:07", "remaining_time": "4:17:36"}
86
+ {"current_steps": 840, "total_steps": 1002, "loss": 0.4938, "learning_rate": 5e-06, "epoch": 2.5144995322731525, "percentage": 83.83, "elapsed_time": "20:57:52", "remaining_time": "4:02:35"}
87
+ {"current_steps": 850, "total_steps": 1002, "loss": 0.4974, "learning_rate": 5e-06, "epoch": 2.5444340505144996, "percentage": 84.83, "elapsed_time": "21:12:38", "remaining_time": "3:47:34"}
88
+ {"current_steps": 860, "total_steps": 1002, "loss": 0.4955, "learning_rate": 5e-06, "epoch": 2.5743685687558466, "percentage": 85.83, "elapsed_time": "21:27:21", "remaining_time": "3:32:33"}
89
+ {"current_steps": 870, "total_steps": 1002, "loss": 0.4933, "learning_rate": 5e-06, "epoch": 2.6043030869971937, "percentage": 86.83, "elapsed_time": "21:42:05", "remaining_time": "3:17:33"}
90
+ {"current_steps": 880, "total_steps": 1002, "loss": 0.4914, "learning_rate": 5e-06, "epoch": 2.634237605238541, "percentage": 87.82, "elapsed_time": "21:56:52", "remaining_time": "3:02:33"}
91
+ {"current_steps": 890, "total_steps": 1002, "loss": 0.4975, "learning_rate": 5e-06, "epoch": 2.664172123479888, "percentage": 88.82, "elapsed_time": "22:11:37", "remaining_time": "2:47:34"}
92
+ {"current_steps": 900, "total_steps": 1002, "loss": 0.5002, "learning_rate": 5e-06, "epoch": 2.694106641721235, "percentage": 89.82, "elapsed_time": "22:26:23", "remaining_time": "2:32:35"}
93
+ {"current_steps": 910, "total_steps": 1002, "loss": 0.4938, "learning_rate": 5e-06, "epoch": 2.724041159962582, "percentage": 90.82, "elapsed_time": "22:41:09", "remaining_time": "2:17:36"}
94
+ {"current_steps": 920, "total_steps": 1002, "loss": 0.495, "learning_rate": 5e-06, "epoch": 2.753975678203929, "percentage": 91.82, "elapsed_time": "22:55:54", "remaining_time": "2:02:38"}
95
+ {"current_steps": 930, "total_steps": 1002, "loss": 0.5007, "learning_rate": 5e-06, "epoch": 2.7839101964452757, "percentage": 92.81, "elapsed_time": "23:10:41", "remaining_time": "1:47:39"}
96
+ {"current_steps": 940, "total_steps": 1002, "loss": 0.4986, "learning_rate": 5e-06, "epoch": 2.8138447146866232, "percentage": 93.81, "elapsed_time": "23:25:26", "remaining_time": "1:32:41"}
97
+ {"current_steps": 950, "total_steps": 1002, "loss": 0.4981, "learning_rate": 5e-06, "epoch": 2.84377923292797, "percentage": 94.81, "elapsed_time": "23:40:11", "remaining_time": "1:17:44"}
98
+ {"current_steps": 960, "total_steps": 1002, "loss": 0.5002, "learning_rate": 5e-06, "epoch": 2.8737137511693174, "percentage": 95.81, "elapsed_time": "23:54:57", "remaining_time": "1:02:46"}
99
+ {"current_steps": 970, "total_steps": 1002, "loss": 0.4956, "learning_rate": 5e-06, "epoch": 2.903648269410664, "percentage": 96.81, "elapsed_time": "1 day, 0:09:41", "remaining_time": "0:47:49"}
100
+ {"current_steps": 980, "total_steps": 1002, "loss": 0.5013, "learning_rate": 5e-06, "epoch": 2.933582787652011, "percentage": 97.8, "elapsed_time": "1 day, 0:24:24", "remaining_time": "0:32:52"}
101
+ {"current_steps": 990, "total_steps": 1002, "loss": 0.5029, "learning_rate": 5e-06, "epoch": 2.963517305893358, "percentage": 98.8, "elapsed_time": "1 day, 0:39:09", "remaining_time": "0:17:55"}
102
+ {"current_steps": 1000, "total_steps": 1002, "loss": 0.5039, "learning_rate": 5e-06, "epoch": 2.9934518241347052, "percentage": 99.8, "elapsed_time": "1 day, 0:53:53", "remaining_time": "0:02:59"}