Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_scheduler_cosine_warmup0.05_minlr1e-7_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
3819568
·
verified ·
1 Parent(s): 28d11c6

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:c9891e893251e1b4acc20c833dba56b2198433410706b6c01fb36d91a75e4711
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8269ae3b9ca47d0c8a2290b96d5d7dab9f49107d884d1b4cedebf51dde52b08f
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ed5fbf9f16ec3c8d6b3df9142c8c47fa6650847b433577bd1cac5bb9b895328
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49779793044ea980a187123d0e8c47493d56313cb0b1168e2e438336da9b20dc
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6260983daa5b823e665a7cdda6ef746470bc897d850835938c1be79cee5dc71f
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ad9890934db5149e458410b4cc07b6aa30bc8d914037018f5b45cffa82b7bf
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:fc688b990c84e80bf60ffee2c4ec7f12b1d7cdcd93bc85d6d91617d20cf1b520
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd25ca2171419da854b57b7b11d7d1b96d079cc3c805cd120fcdcfec9a21dbb3
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -67,3 +67,36 @@
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.556, "learning_rate": 1.5042051212221528e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:26:03", "remaining_time": "8:30:57"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6115813851356506, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:46:44", "remaining_time": "8:23:22"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6015, "learning_rate": 1.4315980246185532e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:50:52", "remaining_time": "8:20:54"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.556, "learning_rate": 1.5042051212221528e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:26:03", "remaining_time": "8:30:57"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6115813851356506, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:46:44", "remaining_time": "8:23:22"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.6015, "learning_rate": 1.4315980246185532e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:50:52", "remaining_time": "8:20:54"}
70
+ {"current_steps": 680, "total_steps": 1002, "loss": 0.5063, "learning_rate": 1.3602113138036206e-06, "epoch": 2.0355472404115997, "percentage": 67.86, "elapsed_time": "17:05:43", "remaining_time": "8:05:42"}
71
+ {"current_steps": 690, "total_steps": 1002, "loss": 0.5035, "learning_rate": 1.290122885034065e-06, "epoch": 2.065481758652947, "percentage": 68.86, "elapsed_time": "17:20:31", "remaining_time": "7:50:30"}
72
+ {"current_steps": 700, "total_steps": 1002, "loss": 0.5073, "learning_rate": 1.221409217897996e-06, "epoch": 2.095416276894294, "percentage": 69.86, "elapsed_time": "17:35:23", "remaining_time": "7:35:19"}
73
+ {"current_steps": 710, "total_steps": 1002, "loss": 0.5065, "learning_rate": 1.1541452918613912e-06, "epoch": 2.125350795135641, "percentage": 70.86, "elapsed_time": "17:50:11", "remaining_time": "7:20:08"}
74
+ {"current_steps": 720, "total_steps": 1002, "loss": 0.5096, "learning_rate": 1.0884045044514633e-06, "epoch": 2.155285313376988, "percentage": 71.86, "elapsed_time": "18:05:00", "remaining_time": "7:04:57"}
75
+ {"current_steps": 730, "total_steps": 1002, "loss": 0.5084, "learning_rate": 1.0242585911662346e-06, "epoch": 2.185219831618335, "percentage": 72.85, "elapsed_time": "18:19:49", "remaining_time": "6:49:47"}
76
+ {"current_steps": 740, "total_steps": 1002, "loss": 0.5085, "learning_rate": 9.617775471976801e-07, "epoch": 2.2151543498596817, "percentage": 73.85, "elapsed_time": "18:34:34", "remaining_time": "6:34:37"}
77
+ {"current_steps": 750, "total_steps": 1002, "loss": 0.5096, "learning_rate": 9.010295510538854e-07, "epoch": 2.245088868101029, "percentage": 74.85, "elapsed_time": "18:49:23", "remaining_time": "6:19:28"}
78
+ {"current_steps": 760, "total_steps": 1002, "loss": 0.5042, "learning_rate": 8.420808901635359e-07, "epoch": 2.275023386342376, "percentage": 75.85, "elapsed_time": "19:04:13", "remaining_time": "6:04:20"}
79
+ {"current_steps": 770, "total_steps": 1002, "loss": 0.5097, "learning_rate": 7.849958885439292e-07, "epoch": 2.304957904583723, "percentage": 76.85, "elapsed_time": "19:19:03", "remaining_time": "5:49:13"}
80
+ {"current_steps": 780, "total_steps": 1002, "loss": 0.5039, "learning_rate": 7.298368366114427e-07, "epoch": 2.33489242282507, "percentage": 77.84, "elapsed_time": "19:33:51", "remaining_time": "5:34:05"}
81
+ {"current_steps": 790, "total_steps": 1002, "loss": 0.5047, "learning_rate": 6.76663923211031e-07, "epoch": 2.364826941066417, "percentage": 78.84, "elapsed_time": "19:48:42", "remaining_time": "5:18:59"}
82
+ {"current_steps": 800, "total_steps": 1002, "loss": 0.5081, "learning_rate": 6.255351699389413e-07, "epoch": 2.394761459307764, "percentage": 79.84, "elapsed_time": "20:03:29", "remaining_time": "5:03:52"}
83
+ {"current_steps": 810, "total_steps": 1002, "loss": 0.5141, "learning_rate": 5.765063678302913e-07, "epoch": 2.4246959775491113, "percentage": 80.84, "elapsed_time": "20:18:16", "remaining_time": "4:48:46"}
84
+ {"current_steps": 820, "total_steps": 1002, "loss": 0.5105, "learning_rate": 5.296310164806165e-07, "epoch": 2.4546304957904583, "percentage": 81.84, "elapsed_time": "20:33:05", "remaining_time": "4:33:41"}
85
+ {"current_steps": 830, "total_steps": 1002, "loss": 0.5092, "learning_rate": 4.849602656678017e-07, "epoch": 2.4845650140318054, "percentage": 82.83, "elapsed_time": "20:47:53", "remaining_time": "4:18:35"}
86
+ {"current_steps": 840, "total_steps": 1002, "loss": 0.5063, "learning_rate": 4.425428595381022e-07, "epoch": 2.5144995322731525, "percentage": 83.83, "elapsed_time": "21:02:42", "remaining_time": "4:03:31"}
87
+ {"current_steps": 850, "total_steps": 1002, "loss": 0.5095, "learning_rate": 4.02425083417164e-07, "epoch": 2.5444340505144996, "percentage": 84.83, "elapsed_time": "21:17:30", "remaining_time": "3:48:26"}
88
+ {"current_steps": 860, "total_steps": 1002, "loss": 0.5069, "learning_rate": 3.646507133040708e-07, "epoch": 2.5743685687558466, "percentage": 85.83, "elapsed_time": "21:32:19", "remaining_time": "3:33:23"}
89
+ {"current_steps": 870, "total_steps": 1002, "loss": 0.5037, "learning_rate": 3.2926096810354405e-07, "epoch": 2.6043030869971937, "percentage": 86.83, "elapsed_time": "21:47:08", "remaining_time": "3:18:19"}
90
+ {"current_steps": 880, "total_steps": 1002, "loss": 0.5025, "learning_rate": 2.962944646484012e-07, "epoch": 2.634237605238541, "percentage": 87.82, "elapsed_time": "22:01:56", "remaining_time": "3:03:16"}
91
+ {"current_steps": 890, "total_steps": 1002, "loss": 0.5082, "learning_rate": 2.657871755613707e-07, "epoch": 2.664172123479888, "percentage": 88.82, "elapsed_time": "22:16:44", "remaining_time": "2:48:13"}
92
+ {"current_steps": 900, "total_steps": 1002, "loss": 0.5108, "learning_rate": 2.3777239000222903e-07, "epoch": 2.694106641721235, "percentage": 89.82, "elapsed_time": "22:31:34", "remaining_time": "2:33:10"}
93
+ {"current_steps": 910, "total_steps": 1002, "loss": 0.5033, "learning_rate": 2.1228067734309915e-07, "epoch": 2.724041159962582, "percentage": 90.82, "elapsed_time": "22:46:25", "remaining_time": "2:18:08"}
94
+ {"current_steps": 920, "total_steps": 1002, "loss": 0.5038, "learning_rate": 1.8933985381154809e-07, "epoch": 2.753975678203929, "percentage": 91.82, "elapsed_time": "23:01:16", "remaining_time": "2:03:06"}
95
+ {"current_steps": 930, "total_steps": 1002, "loss": 0.5099, "learning_rate": 1.6897495213787648e-07, "epoch": 2.7839101964452757, "percentage": 92.81, "elapsed_time": "23:16:07", "remaining_time": "1:48:05"}
96
+ {"current_steps": 940, "total_steps": 1002, "loss": 0.5078, "learning_rate": 1.512081942397292e-07, "epoch": 2.8138447146866232, "percentage": 93.81, "elapsed_time": "23:30:54", "remaining_time": "1:33:03"}
97
+ {"current_steps": 950, "total_steps": 1002, "loss": 0.5068, "learning_rate": 1.3605896697382345e-07, "epoch": 2.84377923292797, "percentage": 94.81, "elapsed_time": "23:45:44", "remaining_time": "1:18:02"}
98
+ {"current_steps": 960, "total_steps": 1002, "loss": 0.5089, "learning_rate": 1.2354380098126337e-07, "epoch": 2.8737137511693174, "percentage": 95.81, "elapsed_time": "1 day, 0:00:34", "remaining_time": "1:03:01"}
99
+ {"current_steps": 970, "total_steps": 1002, "loss": 0.5036, "learning_rate": 1.136763526495162e-07, "epoch": 2.903648269410664, "percentage": 96.81, "elapsed_time": "1 day, 0:15:23", "remaining_time": "0:48:00"}
100
+ {"current_steps": 980, "total_steps": 1002, "loss": 0.509, "learning_rate": 1.0646738921073959e-07, "epoch": 2.933582787652011, "percentage": 97.8, "elapsed_time": "1 day, 0:30:10", "remaining_time": "0:33:00"}
101
+ {"current_steps": 990, "total_steps": 1002, "loss": 0.5105, "learning_rate": 1.019247769927164e-07, "epoch": 2.963517305893358, "percentage": 98.8, "elapsed_time": "1 day, 0:45:01", "remaining_time": "0:18:00"}
102
+ {"current_steps": 1000, "total_steps": 1002, "loss": 0.511, "learning_rate": 1.0005347283522054e-07, "epoch": 2.9934518241347052, "percentage": 99.8, "elapsed_time": "1 day, 0:59:47", "remaining_time": "0:02:59"}