Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_lr8e-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
1cfc63f
·
verified ·
1 Parent(s): 45e156b

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:ad1409fca4c697e74cc3ad2795fe2ab9342b7c8cbb9851cf56ace62038c62012
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3a8e173896fa1e39cdf41d57931c08327e2ae43eab5d076b6e642943452ffa
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b33f47bc93353797d288194d64d896eb36101eff79c5d0489779454c598c340
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061dda6611d49f1eb2ec6c55a5f07f316f0f8ee15337cd7ed6711479df5fb38f
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d8aafc99de5fb076923f00854d40e788074f6c8d264e23f969d4f234bf17a3
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a073d24c25dc9153a48dd02eb2a5edca6be86564a7db8ddb5c88a0c13ba2bc25
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:c193c4fb5e06e79468990c29ae9093890bfa62270adf2c8e6a94832738189f7d
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d46562d3950283cea46ab4272cf44ad67219fa2ced76388c8306300085e198f
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -67,3 +67,36 @@
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5452, "learning_rate": 8e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:27:06", "remaining_time": "8:31:29"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6230265498161316, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:47:45", "remaining_time": "8:23:52"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.5812, "learning_rate": 8e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:51:53", "remaining_time": "8:21:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5452, "learning_rate": 8e-06, "epoch": 1.9756782039289056, "percentage": 65.87, "elapsed_time": "16:27:06", "remaining_time": "8:31:29"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.6230265498161316, "epoch": 1.999625818521983, "percentage": 66.67, "elapsed_time": "16:47:45", "remaining_time": "8:23:52"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.5812, "learning_rate": 8e-06, "epoch": 2.0056127221702527, "percentage": 66.87, "elapsed_time": "16:51:53", "remaining_time": "8:21:24"}
70
+ {"current_steps": 680, "total_steps": 1002, "loss": 0.4457, "learning_rate": 8e-06, "epoch": 2.0355472404115997, "percentage": 67.86, "elapsed_time": "17:06:39", "remaining_time": "8:06:09"}
71
+ {"current_steps": 690, "total_steps": 1002, "loss": 0.4401, "learning_rate": 8e-06, "epoch": 2.065481758652947, "percentage": 68.86, "elapsed_time": "17:21:28", "remaining_time": "7:50:55"}
72
+ {"current_steps": 700, "total_steps": 1002, "loss": 0.4442, "learning_rate": 8e-06, "epoch": 2.095416276894294, "percentage": 69.86, "elapsed_time": "17:36:16", "remaining_time": "7:35:42"}
73
+ {"current_steps": 710, "total_steps": 1002, "loss": 0.4449, "learning_rate": 8e-06, "epoch": 2.125350795135641, "percentage": 70.86, "elapsed_time": "17:51:03", "remaining_time": "7:20:29"}
74
+ {"current_steps": 720, "total_steps": 1002, "loss": 0.4488, "learning_rate": 8e-06, "epoch": 2.155285313376988, "percentage": 71.86, "elapsed_time": "18:05:50", "remaining_time": "7:05:17"}
75
+ {"current_steps": 730, "total_steps": 1002, "loss": 0.4493, "learning_rate": 8e-06, "epoch": 2.185219831618335, "percentage": 72.85, "elapsed_time": "18:20:39", "remaining_time": "6:50:06"}
76
+ {"current_steps": 740, "total_steps": 1002, "loss": 0.4504, "learning_rate": 8e-06, "epoch": 2.2151543498596817, "percentage": 73.85, "elapsed_time": "18:35:25", "remaining_time": "6:34:55"}
77
+ {"current_steps": 750, "total_steps": 1002, "loss": 0.4527, "learning_rate": 8e-06, "epoch": 2.245088868101029, "percentage": 74.85, "elapsed_time": "18:50:12", "remaining_time": "6:19:45"}
78
+ {"current_steps": 760, "total_steps": 1002, "loss": 0.4497, "learning_rate": 8e-06, "epoch": 2.275023386342376, "percentage": 75.85, "elapsed_time": "19:05:00", "remaining_time": "6:04:35"}
79
+ {"current_steps": 770, "total_steps": 1002, "loss": 0.4543, "learning_rate": 8e-06, "epoch": 2.304957904583723, "percentage": 76.85, "elapsed_time": "19:19:48", "remaining_time": "5:49:26"}
80
+ {"current_steps": 780, "total_steps": 1002, "loss": 0.4517, "learning_rate": 8e-06, "epoch": 2.33489242282507, "percentage": 77.84, "elapsed_time": "19:34:37", "remaining_time": "5:34:18"}
81
+ {"current_steps": 790, "total_steps": 1002, "loss": 0.4542, "learning_rate": 8e-06, "epoch": 2.364826941066417, "percentage": 78.84, "elapsed_time": "19:49:22", "remaining_time": "5:19:10"}
82
+ {"current_steps": 800, "total_steps": 1002, "loss": 0.4565, "learning_rate": 8e-06, "epoch": 2.394761459307764, "percentage": 79.84, "elapsed_time": "20:04:11", "remaining_time": "5:04:03"}
83
+ {"current_steps": 810, "total_steps": 1002, "loss": 0.4632, "learning_rate": 8e-06, "epoch": 2.4246959775491113, "percentage": 80.84, "elapsed_time": "20:18:59", "remaining_time": "4:48:56"}
84
+ {"current_steps": 820, "total_steps": 1002, "loss": 0.4611, "learning_rate": 8e-06, "epoch": 2.4546304957904583, "percentage": 81.84, "elapsed_time": "20:33:47", "remaining_time": "4:33:50"}
85
+ {"current_steps": 830, "total_steps": 1002, "loss": 0.4613, "learning_rate": 8e-06, "epoch": 2.4845650140318054, "percentage": 82.83, "elapsed_time": "20:48:35", "remaining_time": "4:18:44"}
86
+ {"current_steps": 840, "total_steps": 1002, "loss": 0.4591, "learning_rate": 8e-06, "epoch": 2.5144995322731525, "percentage": 83.83, "elapsed_time": "21:03:23", "remaining_time": "4:03:39"}
87
+ {"current_steps": 850, "total_steps": 1002, "loss": 0.4629, "learning_rate": 8e-06, "epoch": 2.5444340505144996, "percentage": 84.83, "elapsed_time": "21:18:11", "remaining_time": "3:48:34"}
88
+ {"current_steps": 860, "total_steps": 1002, "loss": 0.4607, "learning_rate": 8e-06, "epoch": 2.5743685687558466, "percentage": 85.83, "elapsed_time": "21:32:59", "remaining_time": "3:33:29"}
89
+ {"current_steps": 870, "total_steps": 1002, "loss": 0.4596, "learning_rate": 8e-06, "epoch": 2.6043030869971937, "percentage": 86.83, "elapsed_time": "21:47:47", "remaining_time": "3:18:25"}
90
+ {"current_steps": 880, "total_steps": 1002, "loss": 0.4571, "learning_rate": 8e-06, "epoch": 2.634237605238541, "percentage": 87.82, "elapsed_time": "22:02:36", "remaining_time": "3:03:21"}
91
+ {"current_steps": 890, "total_steps": 1002, "loss": 0.4634, "learning_rate": 8e-06, "epoch": 2.664172123479888, "percentage": 88.82, "elapsed_time": "22:17:25", "remaining_time": "2:48:18"}
92
+ {"current_steps": 900, "total_steps": 1002, "loss": 0.4661, "learning_rate": 8e-06, "epoch": 2.694106641721235, "percentage": 89.82, "elapsed_time": "22:32:12", "remaining_time": "2:33:14"}
93
+ {"current_steps": 910, "total_steps": 1002, "loss": 0.4605, "learning_rate": 8e-06, "epoch": 2.724041159962582, "percentage": 90.82, "elapsed_time": "22:47:00", "remaining_time": "2:18:12"}
94
+ {"current_steps": 920, "total_steps": 1002, "loss": 0.4619, "learning_rate": 8e-06, "epoch": 2.753975678203929, "percentage": 91.82, "elapsed_time": "23:01:49", "remaining_time": "2:03:09"}
95
+ {"current_steps": 930, "total_steps": 1002, "loss": 0.4676, "learning_rate": 8e-06, "epoch": 2.7839101964452757, "percentage": 92.81, "elapsed_time": "23:16:39", "remaining_time": "1:48:07"}
96
+ {"current_steps": 940, "total_steps": 1002, "loss": 0.4651, "learning_rate": 8e-06, "epoch": 2.8138447146866232, "percentage": 93.81, "elapsed_time": "23:31:28", "remaining_time": "1:33:05"}
97
+ {"current_steps": 950, "total_steps": 1002, "loss": 0.4657, "learning_rate": 8e-06, "epoch": 2.84377923292797, "percentage": 94.81, "elapsed_time": "23:46:18", "remaining_time": "1:18:04"}
98
+ {"current_steps": 960, "total_steps": 1002, "loss": 0.4674, "learning_rate": 8e-06, "epoch": 2.8737137511693174, "percentage": 95.81, "elapsed_time": "1 day, 0:01:06", "remaining_time": "1:03:02"}
99
+ {"current_steps": 970, "total_steps": 1002, "loss": 0.4638, "learning_rate": 8e-06, "epoch": 2.903648269410664, "percentage": 96.81, "elapsed_time": "1 day, 0:15:54", "remaining_time": "0:48:01"}
100
+ {"current_steps": 980, "total_steps": 1002, "loss": 0.4688, "learning_rate": 8e-06, "epoch": 2.933582787652011, "percentage": 97.8, "elapsed_time": "1 day, 0:30:42", "remaining_time": "0:33:00"}
101
+ {"current_steps": 990, "total_steps": 1002, "loss": 0.4707, "learning_rate": 8e-06, "epoch": 2.963517305893358, "percentage": 98.8, "elapsed_time": "1 day, 0:45:31", "remaining_time": "0:18:00"}
102
+ {"current_steps": 1000, "total_steps": 1002, "loss": 0.472, "learning_rate": 8e-06, "epoch": 2.9934518241347052, "percentage": 99.8, "elapsed_time": "1 day, 1:00:19", "remaining_time": "0:03:00"}