Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_airoboros

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
gsmyrnis commited on
Commit
c294ed1
·
verified ·
1 Parent(s): 2a10f3c

Training in progress, epoch 3

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 +32 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a8ebb3f7add85da3947931aa0344fb9c8476a4f319857d0a520d79e9abad30d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc1726f8a315f3505774c8c33e501394cee5c1e64dfa87026ee3f4632519580
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f78e5884b96670d8f640f13bdf80051a7fb3b5f0cd933066be59cd733fa23f8b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6078e3d06089f7864278c246d8ad74816685983fcb7bbbcd338e8e27dc27526
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b5662b15dc81b266f94526bd3d7bd3648a7e2e0320c4bdffa00a7bc0efd7f9c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f93f984dc38e544989ee7880f9e41af682ffbfeeec4d1b68c878702101c74a7
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61cc200ed5bcbe5470ea2c68bb82e3a9c95e73a509bb5fbcafa628aeeb019f4e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d81e159f99c90a1124c9369dbbc5f23235a33cce75da25a9f2cdb54e5e31571
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -67,3 +67,35 @@
67
  {"current_steps": 650, "total_steps": 972, "loss": 0.596, "learning_rate": 5e-06, "epoch": 2.006172839506173, "percentage": 66.87, "elapsed_time": "1:06:47", "remaining_time": "0:33:05"}
68
  {"current_steps": 660, "total_steps": 972, "loss": 0.5645, "learning_rate": 5e-06, "epoch": 2.037037037037037, "percentage": 67.9, "elapsed_time": "1:07:45", "remaining_time": "0:32:01"}
69
  {"current_steps": 670, "total_steps": 972, "loss": 0.558, "learning_rate": 5e-06, "epoch": 2.067901234567901, "percentage": 68.93, "elapsed_time": "1:08:43", "remaining_time": "0:30:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 650, "total_steps": 972, "loss": 0.596, "learning_rate": 5e-06, "epoch": 2.006172839506173, "percentage": 66.87, "elapsed_time": "1:06:47", "remaining_time": "0:33:05"}
68
  {"current_steps": 660, "total_steps": 972, "loss": 0.5645, "learning_rate": 5e-06, "epoch": 2.037037037037037, "percentage": 67.9, "elapsed_time": "1:07:45", "remaining_time": "0:32:01"}
69
  {"current_steps": 670, "total_steps": 972, "loss": 0.558, "learning_rate": 5e-06, "epoch": 2.067901234567901, "percentage": 68.93, "elapsed_time": "1:08:43", "remaining_time": "0:30:58"}
70
+ {"current_steps": 680, "total_steps": 972, "loss": 0.5591, "learning_rate": 5e-06, "epoch": 2.0987654320987654, "percentage": 69.96, "elapsed_time": "1:09:41", "remaining_time": "0:29:55"}
71
+ {"current_steps": 690, "total_steps": 972, "loss": 0.5573, "learning_rate": 5e-06, "epoch": 2.1296296296296298, "percentage": 70.99, "elapsed_time": "1:10:39", "remaining_time": "0:28:52"}
72
+ {"current_steps": 700, "total_steps": 972, "loss": 0.5571, "learning_rate": 5e-06, "epoch": 2.1604938271604937, "percentage": 72.02, "elapsed_time": "1:11:37", "remaining_time": "0:27:49"}
73
+ {"current_steps": 710, "total_steps": 972, "loss": 0.56, "learning_rate": 5e-06, "epoch": 2.191358024691358, "percentage": 73.05, "elapsed_time": "1:12:35", "remaining_time": "0:26:47"}
74
+ {"current_steps": 720, "total_steps": 972, "loss": 0.5571, "learning_rate": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "1:13:33", "remaining_time": "0:25:44"}
75
+ {"current_steps": 730, "total_steps": 972, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.253086419753086, "percentage": 75.1, "elapsed_time": "1:14:32", "remaining_time": "0:24:42"}
76
+ {"current_steps": 740, "total_steps": 972, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.2839506172839505, "percentage": 76.13, "elapsed_time": "1:15:30", "remaining_time": "0:23:40"}
77
+ {"current_steps": 750, "total_steps": 972, "loss": 0.567, "learning_rate": 5e-06, "epoch": 2.314814814814815, "percentage": 77.16, "elapsed_time": "1:16:28", "remaining_time": "0:22:38"}
78
+ {"current_steps": 760, "total_steps": 972, "loss": 0.5569, "learning_rate": 5e-06, "epoch": 2.3456790123456788, "percentage": 78.19, "elapsed_time": "1:17:26", "remaining_time": "0:21:36"}
79
+ {"current_steps": 770, "total_steps": 972, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.376543209876543, "percentage": 79.22, "elapsed_time": "1:18:24", "remaining_time": "0:20:34"}
80
+ {"current_steps": 780, "total_steps": 972, "loss": 0.5622, "learning_rate": 5e-06, "epoch": 2.4074074074074074, "percentage": 80.25, "elapsed_time": "1:19:22", "remaining_time": "0:19:32"}
81
+ {"current_steps": 790, "total_steps": 972, "loss": 0.5634, "learning_rate": 5e-06, "epoch": 2.4382716049382718, "percentage": 81.28, "elapsed_time": "1:20:20", "remaining_time": "0:18:30"}
82
+ {"current_steps": 800, "total_steps": 972, "loss": 0.5594, "learning_rate": 5e-06, "epoch": 2.4691358024691357, "percentage": 82.3, "elapsed_time": "1:21:19", "remaining_time": "0:17:29"}
83
+ {"current_steps": 810, "total_steps": 972, "loss": 0.5685, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:22:17", "remaining_time": "0:16:27"}
84
+ {"current_steps": 820, "total_steps": 972, "loss": 0.5629, "learning_rate": 5e-06, "epoch": 2.5308641975308643, "percentage": 84.36, "elapsed_time": "1:23:15", "remaining_time": "0:15:25"}
85
+ {"current_steps": 830, "total_steps": 972, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.5617283950617287, "percentage": 85.39, "elapsed_time": "1:24:13", "remaining_time": "0:14:24"}
86
+ {"current_steps": 840, "total_steps": 972, "loss": 0.5663, "learning_rate": 5e-06, "epoch": 2.5925925925925926, "percentage": 86.42, "elapsed_time": "1:25:11", "remaining_time": "0:13:23"}
87
+ {"current_steps": 850, "total_steps": 972, "loss": 0.5635, "learning_rate": 5e-06, "epoch": 2.623456790123457, "percentage": 87.45, "elapsed_time": "1:26:09", "remaining_time": "0:12:21"}
88
+ {"current_steps": 860, "total_steps": 972, "loss": 0.5654, "learning_rate": 5e-06, "epoch": 2.6543209876543212, "percentage": 88.48, "elapsed_time": "1:27:07", "remaining_time": "0:11:20"}
89
+ {"current_steps": 870, "total_steps": 972, "loss": 0.5669, "learning_rate": 5e-06, "epoch": 2.685185185185185, "percentage": 89.51, "elapsed_time": "1:28:05", "remaining_time": "0:10:19"}
90
+ {"current_steps": 880, "total_steps": 972, "loss": 0.5642, "learning_rate": 5e-06, "epoch": 2.7160493827160495, "percentage": 90.53, "elapsed_time": "1:29:03", "remaining_time": "0:09:18"}
91
+ {"current_steps": 890, "total_steps": 972, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.746913580246914, "percentage": 91.56, "elapsed_time": "1:30:01", "remaining_time": "0:08:17"}
92
+ {"current_steps": 900, "total_steps": 972, "loss": 0.5629, "learning_rate": 5e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "1:31:00", "remaining_time": "0:07:16"}
93
+ {"current_steps": 910, "total_steps": 972, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.808641975308642, "percentage": 93.62, "elapsed_time": "1:31:58", "remaining_time": "0:06:15"}
94
+ {"current_steps": 920, "total_steps": 972, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.8395061728395063, "percentage": 94.65, "elapsed_time": "1:32:56", "remaining_time": "0:05:15"}
95
+ {"current_steps": 930, "total_steps": 972, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.8703703703703702, "percentage": 95.68, "elapsed_time": "1:33:54", "remaining_time": "0:04:14"}
96
+ {"current_steps": 940, "total_steps": 972, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.9012345679012346, "percentage": 96.71, "elapsed_time": "1:34:52", "remaining_time": "0:03:13"}
97
+ {"current_steps": 950, "total_steps": 972, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.932098765432099, "percentage": 97.74, "elapsed_time": "1:35:50", "remaining_time": "0:02:13"}
98
+ {"current_steps": 960, "total_steps": 972, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.962962962962963, "percentage": 98.77, "elapsed_time": "1:36:48", "remaining_time": "0:01:12"}
99
+ {"current_steps": 970, "total_steps": 972, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.993827160493827, "percentage": 99.79, "elapsed_time": "1:37:46", "remaining_time": "0:00:12"}
100
+ {"current_steps": 972, "total_steps": 972, "eval_loss": 0.6513996720314026, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:39:51", "remaining_time": "0:00:00"}
101
+ {"current_steps": 972, "total_steps": 972, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:41:12", "remaining_time": "0:00:00"}