Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_lr2e-6_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
131cdd8
•
1 Parent(s): ffe16f9

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 sha256:03e0fdf614dcf443df4ef89d13a03a980bcdb32b84b169c970dacfc2f11b7b5a
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35824b9a774210b96946f1fcfb30fd230fe104d8391981abca7999f7caedab2c
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4835dabba759110b5a4d12bd5f5b92df130aa4608e5c9ce9231dcb02a2dda8a9
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064c4b0a77dd8f2740f30b3c1c1bcba7fd27e9a7de1c7657ede70904d17d2b0b
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89d857cf7b742dde297072519ce696c19f0847b8bcbb96146a6b1d813bb1ea98
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26fe961eadade720338635ad86ad47083c9149b3576457ae03744d355ba44eb2
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27accd5e713021c090356f3ff035855e06f5b37cf77733223b16cd24f6c904fd
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb273f86108a95a9744c451e1616d66cd51f327866c66b645de2085d47d6e42
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -67,3 +67,36 @@
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5868, "learning_rate": 2e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:33:46", "remaining_time": "8:34:57"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6162874102592468, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:54:31", "remaining_time": "8:27:15"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6381, "learning_rate": 2e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:58:41", "remaining_time": "8:24:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5868, "learning_rate": 2e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:33:46", "remaining_time": "8:34:57"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6162874102592468, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:54:31", "remaining_time": "8:27:15"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6381, "learning_rate": 2e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:58:41", "remaining_time": "8:24:46"}
70
+ {"current_steps": 680, "total_steps": 1002, "loss": 0.5476, "learning_rate": 2e-06, "epoch": 2.0355472404115997, "percentage": 67.86, "elapsed_time": "17:13:37", "remaining_time": "8:09:27"}
71
+ {"current_steps": 690, "total_steps": 1002, "loss": 0.5451, "learning_rate": 2e-06, "epoch": 2.065481758652947, "percentage": 68.86, "elapsed_time": "17:28:30", "remaining_time": "7:54:06"}
72
+ {"current_steps": 700, "total_steps": 1002, "loss": 0.5498, "learning_rate": 2e-06, "epoch": 2.095416276894294, "percentage": 69.86, "elapsed_time": "17:43:23", "remaining_time": "7:38:46"}
73
+ {"current_steps": 710, "total_steps": 1002, "loss": 0.5495, "learning_rate": 2e-06, "epoch": 2.125350795135641, "percentage": 70.86, "elapsed_time": "17:58:17", "remaining_time": "7:23:28"}
74
+ {"current_steps": 720, "total_steps": 1002, "loss": 0.5524, "learning_rate": 2e-06, "epoch": 2.155285313376988, "percentage": 71.86, "elapsed_time": "18:13:11", "remaining_time": "7:08:10"}
75
+ {"current_steps": 730, "total_steps": 1002, "loss": 0.5516, "learning_rate": 2e-06, "epoch": 2.185219831618335, "percentage": 72.85, "elapsed_time": "18:28:05", "remaining_time": "6:52:52"}
76
+ {"current_steps": 740, "total_steps": 1002, "loss": 0.5517, "learning_rate": 2e-06, "epoch": 2.2151543498596817, "percentage": 73.85, "elapsed_time": "18:42:58", "remaining_time": "6:37:35"}
77
+ {"current_steps": 750, "total_steps": 1002, "loss": 0.5538, "learning_rate": 2e-06, "epoch": 2.245088868101029, "percentage": 74.85, "elapsed_time": "18:57:53", "remaining_time": "6:22:20"}
78
+ {"current_steps": 760, "total_steps": 1002, "loss": 0.5478, "learning_rate": 2e-06, "epoch": 2.275023386342376, "percentage": 75.85, "elapsed_time": "19:12:50", "remaining_time": "6:07:05"}
79
+ {"current_steps": 770, "total_steps": 1002, "loss": 0.5538, "learning_rate": 2e-06, "epoch": 2.304957904583723, "percentage": 76.85, "elapsed_time": "19:27:44", "remaining_time": "5:51:50"}
80
+ {"current_steps": 780, "total_steps": 1002, "loss": 0.5481, "learning_rate": 2e-06, "epoch": 2.33489242282507, "percentage": 77.84, "elapsed_time": "19:42:41", "remaining_time": "5:36:36"}
81
+ {"current_steps": 790, "total_steps": 1002, "loss": 0.549, "learning_rate": 2e-06, "epoch": 2.364826941066417, "percentage": 78.84, "elapsed_time": "19:57:38", "remaining_time": "5:21:23"}
82
+ {"current_steps": 800, "total_steps": 1002, "loss": 0.552, "learning_rate": 2e-06, "epoch": 2.394761459307764, "percentage": 79.84, "elapsed_time": "20:12:29", "remaining_time": "5:06:09"}
83
+ {"current_steps": 810, "total_steps": 1002, "loss": 0.5593, "learning_rate": 2e-06, "epoch": 2.4246959775491113, "percentage": 80.84, "elapsed_time": "20:27:23", "remaining_time": "4:50:56"}
84
+ {"current_steps": 820, "total_steps": 1002, "loss": 0.5552, "learning_rate": 2e-06, "epoch": 2.4546304957904583, "percentage": 81.84, "elapsed_time": "20:42:15", "remaining_time": "4:35:43"}
85
+ {"current_steps": 830, "total_steps": 1002, "loss": 0.5542, "learning_rate": 2e-06, "epoch": 2.4845650140318054, "percentage": 82.83, "elapsed_time": "20:57:06", "remaining_time": "4:20:30"}
86
+ {"current_steps": 840, "total_steps": 1002, "loss": 0.5512, "learning_rate": 2e-06, "epoch": 2.5144995322731525, "percentage": 83.83, "elapsed_time": "21:12:01", "remaining_time": "4:05:19"}
87
+ {"current_steps": 850, "total_steps": 1002, "loss": 0.5545, "learning_rate": 2e-06, "epoch": 2.5444340505144996, "percentage": 84.83, "elapsed_time": "21:26:55", "remaining_time": "3:50:08"}
88
+ {"current_steps": 860, "total_steps": 1002, "loss": 0.5527, "learning_rate": 2e-06, "epoch": 2.5743685687558466, "percentage": 85.83, "elapsed_time": "21:41:51", "remaining_time": "3:34:57"}
89
+ {"current_steps": 870, "total_steps": 1002, "loss": 0.5487, "learning_rate": 2e-06, "epoch": 2.6043030869971937, "percentage": 86.83, "elapsed_time": "21:56:47", "remaining_time": "3:19:47"}
90
+ {"current_steps": 880, "total_steps": 1002, "loss": 0.5478, "learning_rate": 2e-06, "epoch": 2.634237605238541, "percentage": 87.82, "elapsed_time": "22:11:42", "remaining_time": "3:04:37"}
91
+ {"current_steps": 890, "total_steps": 1002, "loss": 0.5534, "learning_rate": 2e-06, "epoch": 2.664172123479888, "percentage": 88.82, "elapsed_time": "22:26:38", "remaining_time": "2:49:27"}
92
+ {"current_steps": 900, "total_steps": 1002, "loss": 0.5561, "learning_rate": 2e-06, "epoch": 2.694106641721235, "percentage": 89.82, "elapsed_time": "22:41:32", "remaining_time": "2:34:18"}
93
+ {"current_steps": 910, "total_steps": 1002, "loss": 0.5488, "learning_rate": 2e-06, "epoch": 2.724041159962582, "percentage": 90.82, "elapsed_time": "22:56:25", "remaining_time": "2:19:09"}
94
+ {"current_steps": 920, "total_steps": 1002, "loss": 0.55, "learning_rate": 2e-06, "epoch": 2.753975678203929, "percentage": 91.82, "elapsed_time": "23:11:18", "remaining_time": "2:04:00"}
95
+ {"current_steps": 930, "total_steps": 1002, "loss": 0.5554, "learning_rate": 2e-06, "epoch": 2.7839101964452757, "percentage": 92.81, "elapsed_time": "23:26:14", "remaining_time": "1:48:52"}
96
+ {"current_steps": 940, "total_steps": 1002, "loss": 0.5544, "learning_rate": 2e-06, "epoch": 2.8138447146866232, "percentage": 93.81, "elapsed_time": "23:41:06", "remaining_time": "1:33:43"}
97
+ {"current_steps": 950, "total_steps": 1002, "loss": 0.5526, "learning_rate": 2e-06, "epoch": 2.84377923292797, "percentage": 94.81, "elapsed_time": "23:55:58", "remaining_time": "1:18:36"}
98
+ {"current_steps": 960, "total_steps": 1002, "loss": 0.5548, "learning_rate": 2e-06, "epoch": 2.8737137511693174, "percentage": 95.81, "elapsed_time": "1 day, 0:10:55", "remaining_time": "1:03:28"}
99
+ {"current_steps": 970, "total_steps": 1002, "loss": 0.5491, "learning_rate": 2e-06, "epoch": 2.903648269410664, "percentage": 96.81, "elapsed_time": "1 day, 0:25:46", "remaining_time": "0:48:21"}
100
+ {"current_steps": 980, "total_steps": 1002, "loss": 0.5552, "learning_rate": 2e-06, "epoch": 2.933582787652011, "percentage": 97.8, "elapsed_time": "1 day, 0:40:41", "remaining_time": "0:33:14"}
101
+ {"current_steps": 990, "total_steps": 1002, "loss": 0.5568, "learning_rate": 2e-06, "epoch": 2.963517305893358, "percentage": 98.8, "elapsed_time": "1 day, 0:55:37", "remaining_time": "0:18:07"}
102
+ {"current_steps": 1000, "total_steps": 1002, "loss": 0.5572, "learning_rate": 2e-06, "epoch": 2.9934518241347052, "percentage": 99.8, "elapsed_time": "1 day, 1:10:34", "remaining_time": "0:03:01"}