Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_adambeta2_0.95_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
4029b89
•
1 Parent(s): 3ac7cb6

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:d4508df679f2bae3ee713b795a553032606d1456f4c11d871fcfde692e295a43
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89a48d69a9283728ac9bdef3c104d99c57c6de0b0ef8875d334810baead470a
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:c429dfd792b957d1228cb5ecd4bca53c5e669c3f7cd24516e7fb31ea36985af3
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37bf97c62ea47acac9957d26ba54a265be5e45bc8928abd073b153f1e440a8d
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:563898317b02918feb3c31d32779c8b1b1da9dbf8e81d2403f4ab0ce1715711a
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470ada4e163842c73ac462cc9ce6b07a463406a1019364881127b91397d1e6b1
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:c4ca06f425fda4ddcc679a813dd716ce64635958df958d24fcfd7367c3b96686
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebceb71ba2fbf970e90021c4ad60b7a739cff3a6cc81c5cada4d4a8e3e447ad
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -67,3 +67,36 @@
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:23:42", "remaining_time": "8:29:44"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6155872941017151, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:44:15", "remaining_time": "8:22:07"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6011, "learning_rate": 5e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:48:25", "remaining_time": "8:19:41"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:23:42", "remaining_time": "8:29:44"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6155872941017151, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:44:15", "remaining_time": "8:22:07"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6011, "learning_rate": 5e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:48:25", "remaining_time": "8:19:41"}
70
+ {"current_steps": 680, "total_steps": 1002, "loss": 0.4861, "learning_rate": 5e-06, "epoch": 2.0355472404115997, "percentage": 67.86, "elapsed_time": "17:03:09", "remaining_time": "8:04:29"}
71
+ {"current_steps": 690, "total_steps": 1002, "loss": 0.4822, "learning_rate": 5e-06, "epoch": 2.065481758652947, "percentage": 68.86, "elapsed_time": "17:17:55", "remaining_time": "7:49:19"}
72
+ {"current_steps": 700, "total_steps": 1002, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 2.095416276894294, "percentage": 69.86, "elapsed_time": "17:32:41", "remaining_time": "7:34:09"}
73
+ {"current_steps": 710, "total_steps": 1002, "loss": 0.4864, "learning_rate": 5e-06, "epoch": 2.125350795135641, "percentage": 70.86, "elapsed_time": "17:47:25", "remaining_time": "7:18:59"}
74
+ {"current_steps": 720, "total_steps": 1002, "loss": 0.4898, "learning_rate": 5e-06, "epoch": 2.155285313376988, "percentage": 71.86, "elapsed_time": "18:02:11", "remaining_time": "7:03:51"}
75
+ {"current_steps": 730, "total_steps": 1002, "loss": 0.4897, "learning_rate": 5e-06, "epoch": 2.185219831618335, "percentage": 72.85, "elapsed_time": "18:16:58", "remaining_time": "6:48:44"}
76
+ {"current_steps": 740, "total_steps": 1002, "loss": 0.4901, "learning_rate": 5e-06, "epoch": 2.2151543498596817, "percentage": 73.85, "elapsed_time": "18:31:43", "remaining_time": "6:33:36"}
77
+ {"current_steps": 750, "total_steps": 1002, "loss": 0.4923, "learning_rate": 5e-06, "epoch": 2.245088868101029, "percentage": 74.85, "elapsed_time": "18:46:30", "remaining_time": "6:18:30"}
78
+ {"current_steps": 760, "total_steps": 1002, "loss": 0.4878, "learning_rate": 5e-06, "epoch": 2.275023386342376, "percentage": 75.85, "elapsed_time": "19:01:14", "remaining_time": "6:03:23"}
79
+ {"current_steps": 770, "total_steps": 1002, "loss": 0.4929, "learning_rate": 5e-06, "epoch": 2.304957904583723, "percentage": 76.85, "elapsed_time": "19:15:58", "remaining_time": "5:48:17"}
80
+ {"current_steps": 780, "total_steps": 1002, "loss": 0.4887, "learning_rate": 5e-06, "epoch": 2.33489242282507, "percentage": 77.84, "elapsed_time": "19:30:43", "remaining_time": "5:33:12"}
81
+ {"current_steps": 790, "total_steps": 1002, "loss": 0.4905, "learning_rate": 5e-06, "epoch": 2.364826941066417, "percentage": 78.84, "elapsed_time": "19:45:30", "remaining_time": "5:18:08"}
82
+ {"current_steps": 800, "total_steps": 1002, "loss": 0.4933, "learning_rate": 5e-06, "epoch": 2.394761459307764, "percentage": 79.84, "elapsed_time": "20:00:17", "remaining_time": "5:03:04"}
83
+ {"current_steps": 810, "total_steps": 1002, "loss": 0.5002, "learning_rate": 5e-06, "epoch": 2.4246959775491113, "percentage": 80.84, "elapsed_time": "20:15:04", "remaining_time": "4:48:01"}
84
+ {"current_steps": 820, "total_steps": 1002, "loss": 0.4973, "learning_rate": 5e-06, "epoch": 2.4546304957904583, "percentage": 81.84, "elapsed_time": "20:29:49", "remaining_time": "4:32:57"}
85
+ {"current_steps": 830, "total_steps": 1002, "loss": 0.497, "learning_rate": 5e-06, "epoch": 2.4845650140318054, "percentage": 82.83, "elapsed_time": "20:44:33", "remaining_time": "4:17:54"}
86
+ {"current_steps": 840, "total_steps": 1002, "loss": 0.4944, "learning_rate": 5e-06, "epoch": 2.5144995322731525, "percentage": 83.83, "elapsed_time": "20:59:20", "remaining_time": "4:02:52"}
87
+ {"current_steps": 850, "total_steps": 1002, "loss": 0.4978, "learning_rate": 5e-06, "epoch": 2.5444340505144996, "percentage": 84.83, "elapsed_time": "21:14:06", "remaining_time": "3:47:50"}
88
+ {"current_steps": 860, "total_steps": 1002, "loss": 0.496, "learning_rate": 5e-06, "epoch": 2.5743685687558466, "percentage": 85.83, "elapsed_time": "21:28:53", "remaining_time": "3:32:48"}
89
+ {"current_steps": 870, "total_steps": 1002, "loss": 0.4936, "learning_rate": 5e-06, "epoch": 2.6043030869971937, "percentage": 86.83, "elapsed_time": "21:43:40", "remaining_time": "3:17:47"}
90
+ {"current_steps": 880, "total_steps": 1002, "loss": 0.492, "learning_rate": 5e-06, "epoch": 2.634237605238541, "percentage": 87.82, "elapsed_time": "21:58:27", "remaining_time": "3:02:47"}
91
+ {"current_steps": 890, "total_steps": 1002, "loss": 0.498, "learning_rate": 5e-06, "epoch": 2.664172123479888, "percentage": 88.82, "elapsed_time": "22:13:15", "remaining_time": "2:47:46"}
92
+ {"current_steps": 900, "total_steps": 1002, "loss": 0.5006, "learning_rate": 5e-06, "epoch": 2.694106641721235, "percentage": 89.82, "elapsed_time": "22:28:02", "remaining_time": "2:32:46"}
93
+ {"current_steps": 910, "total_steps": 1002, "loss": 0.4942, "learning_rate": 5e-06, "epoch": 2.724041159962582, "percentage": 90.82, "elapsed_time": "22:42:48", "remaining_time": "2:17:46"}
94
+ {"current_steps": 920, "total_steps": 1002, "loss": 0.4955, "learning_rate": 5e-06, "epoch": 2.753975678203929, "percentage": 91.82, "elapsed_time": "22:57:32", "remaining_time": "2:02:46"}
95
+ {"current_steps": 930, "total_steps": 1002, "loss": 0.5013, "learning_rate": 5e-06, "epoch": 2.7839101964452757, "percentage": 92.81, "elapsed_time": "23:12:17", "remaining_time": "1:47:47"}
96
+ {"current_steps": 940, "total_steps": 1002, "loss": 0.4994, "learning_rate": 5e-06, "epoch": 2.8138447146866232, "percentage": 93.81, "elapsed_time": "23:27:02", "remaining_time": "1:32:48"}
97
+ {"current_steps": 950, "total_steps": 1002, "loss": 0.4988, "learning_rate": 5e-06, "epoch": 2.84377923292797, "percentage": 94.81, "elapsed_time": "23:41:50", "remaining_time": "1:17:49"}
98
+ {"current_steps": 960, "total_steps": 1002, "loss": 0.5009, "learning_rate": 5e-06, "epoch": 2.8737137511693174, "percentage": 95.81, "elapsed_time": "23:56:34", "remaining_time": "1:02:51"}
99
+ {"current_steps": 970, "total_steps": 1002, "loss": 0.4964, "learning_rate": 5e-06, "epoch": 2.903648269410664, "percentage": 96.81, "elapsed_time": "1 day, 0:11:19", "remaining_time": "0:47:52"}
100
+ {"current_steps": 980, "total_steps": 1002, "loss": 0.502, "learning_rate": 5e-06, "epoch": 2.933582787652011, "percentage": 97.8, "elapsed_time": "1 day, 0:26:04", "remaining_time": "0:32:54"}
101
+ {"current_steps": 990, "total_steps": 1002, "loss": 0.5036, "learning_rate": 5e-06, "epoch": 2.963517305893358, "percentage": 98.8, "elapsed_time": "1 day, 0:40:50", "remaining_time": "0:17:56"}
102
+ {"current_steps": 1000, "total_steps": 1002, "loss": 0.5047, "learning_rate": 5e-06, "epoch": 2.9934518241347052, "percentage": 99.8, "elapsed_time": "1 day, 0:55:36", "remaining_time": "0:02:59"}