Hugging Face's logo

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

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
d8863f7
·
verified ·
1 Parent(s): 237c6d3

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:a38ae44149380785b70596620612bc7982a2f81b3a3b913ea33d59a38c37e5e1
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:235e5e128fa2e67b82de6600eeae88e3dfb811abac0ee0af77c76630ab93205c
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:adbbc59cbcfb7ecd3670896d880d6cb83bfed9bd78fa32d5ec4370400e2ac435
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72e58112a493d0ff2bf9671735e074543bcf3ebe1dff8e5b0d04085508110c7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a42aefdaf55285656379d9cc0f2d0b98616121212ffc86e63ccd900173a6032
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3b2b2834a7ca6542e7bfd18b017c06682973da34749eda269cb0c840aab53c
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:c6b3e8acd61aafd504e326fa80fbc8356484490ceb0c4ca7b8e74747853effc2
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f68bcf0128f6843b5d2eaaad0c319ff2589cac3ca19e9280cd0c99d8108ffe8
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -34,3 +34,36 @@
34
  {"current_steps": 330, "total_steps": 969, "loss": 0.6318, "learning_rate": 5e-06, "epoch": 1.021671826625387, "percentage": 34.06, "elapsed_time": "0:33:46", "remaining_time": "1:05:24"}
35
  {"current_steps": 340, "total_steps": 969, "loss": 0.6153, "learning_rate": 5e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "0:34:45", "remaining_time": "1:04:17"}
36
  {"current_steps": 350, "total_steps": 969, "loss": 0.6182, "learning_rate": 5e-06, "epoch": 1.08359133126935, "percentage": 36.12, "elapsed_time": "0:35:43", "remaining_time": "1:03:10"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  {"current_steps": 330, "total_steps": 969, "loss": 0.6318, "learning_rate": 5e-06, "epoch": 1.021671826625387, "percentage": 34.06, "elapsed_time": "0:33:46", "remaining_time": "1:05:24"}
35
  {"current_steps": 340, "total_steps": 969, "loss": 0.6153, "learning_rate": 5e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "0:34:45", "remaining_time": "1:04:17"}
36
  {"current_steps": 350, "total_steps": 969, "loss": 0.6182, "learning_rate": 5e-06, "epoch": 1.08359133126935, "percentage": 36.12, "elapsed_time": "0:35:43", "remaining_time": "1:03:10"}
37
+ {"current_steps": 360, "total_steps": 969, "loss": 0.6155, "learning_rate": 5e-06, "epoch": 1.1145510835913313, "percentage": 37.15, "elapsed_time": "0:36:41", "remaining_time": "1:02:04"}
38
+ {"current_steps": 370, "total_steps": 969, "loss": 0.6181, "learning_rate": 5e-06, "epoch": 1.1455108359133126, "percentage": 38.18, "elapsed_time": "0:37:39", "remaining_time": "1:00:58"}
39
+ {"current_steps": 380, "total_steps": 969, "loss": 0.6145, "learning_rate": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "0:38:38", "remaining_time": "0:59:53"}
40
+ {"current_steps": 390, "total_steps": 969, "loss": 0.6182, "learning_rate": 5e-06, "epoch": 1.2074303405572755, "percentage": 40.25, "elapsed_time": "0:39:36", "remaining_time": "0:58:47"}
41
+ {"current_steps": 400, "total_steps": 969, "loss": 0.6078, "learning_rate": 5e-06, "epoch": 1.238390092879257, "percentage": 41.28, "elapsed_time": "0:40:34", "remaining_time": "0:57:42"}
42
+ {"current_steps": 410, "total_steps": 969, "loss": 0.6178, "learning_rate": 5e-06, "epoch": 1.2693498452012384, "percentage": 42.31, "elapsed_time": "0:41:32", "remaining_time": "0:56:38"}
43
+ {"current_steps": 420, "total_steps": 969, "loss": 0.6118, "learning_rate": 5e-06, "epoch": 1.3003095975232197, "percentage": 43.34, "elapsed_time": "0:42:30", "remaining_time": "0:55:34"}
44
+ {"current_steps": 430, "total_steps": 969, "loss": 0.6152, "learning_rate": 5e-06, "epoch": 1.3312693498452013, "percentage": 44.38, "elapsed_time": "0:43:28", "remaining_time": "0:54:30"}
45
+ {"current_steps": 440, "total_steps": 969, "loss": 0.6189, "learning_rate": 5e-06, "epoch": 1.3622291021671826, "percentage": 45.41, "elapsed_time": "0:44:27", "remaining_time": "0:53:26"}
46
+ {"current_steps": 450, "total_steps": 969, "loss": 0.6143, "learning_rate": 5e-06, "epoch": 1.3931888544891642, "percentage": 46.44, "elapsed_time": "0:45:25", "remaining_time": "0:52:22"}
47
+ {"current_steps": 460, "total_steps": 969, "loss": 0.6184, "learning_rate": 5e-06, "epoch": 1.4241486068111455, "percentage": 47.47, "elapsed_time": "0:46:23", "remaining_time": "0:51:19"}
48
+ {"current_steps": 470, "total_steps": 969, "loss": 0.6146, "learning_rate": 5e-06, "epoch": 1.4551083591331269, "percentage": 48.5, "elapsed_time": "0:47:21", "remaining_time": "0:50:16"}
49
+ {"current_steps": 480, "total_steps": 969, "loss": 0.6235, "learning_rate": 5e-06, "epoch": 1.4860681114551084, "percentage": 49.54, "elapsed_time": "0:48:19", "remaining_time": "0:49:13"}
50
+ {"current_steps": 490, "total_steps": 969, "loss": 0.6146, "learning_rate": 5e-06, "epoch": 1.5170278637770898, "percentage": 50.57, "elapsed_time": "0:49:17", "remaining_time": "0:48:10"}
51
+ {"current_steps": 500, "total_steps": 969, "loss": 0.6109, "learning_rate": 5e-06, "epoch": 1.5479876160990713, "percentage": 51.6, "elapsed_time": "0:50:15", "remaining_time": "0:47:08"}
52
+ {"current_steps": 510, "total_steps": 969, "loss": 0.6127, "learning_rate": 5e-06, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "0:51:13", "remaining_time": "0:46:06"}
53
+ {"current_steps": 520, "total_steps": 969, "loss": 0.6158, "learning_rate": 5e-06, "epoch": 1.609907120743034, "percentage": 53.66, "elapsed_time": "0:52:11", "remaining_time": "0:45:04"}
54
+ {"current_steps": 530, "total_steps": 969, "loss": 0.6152, "learning_rate": 5e-06, "epoch": 1.6408668730650153, "percentage": 54.7, "elapsed_time": "0:53:09", "remaining_time": "0:44:02"}
55
+ {"current_steps": 540, "total_steps": 969, "loss": 0.6135, "learning_rate": 5e-06, "epoch": 1.671826625386997, "percentage": 55.73, "elapsed_time": "0:54:07", "remaining_time": "0:43:00"}
56
+ {"current_steps": 550, "total_steps": 969, "loss": 0.615, "learning_rate": 5e-06, "epoch": 1.7027863777089784, "percentage": 56.76, "elapsed_time": "0:55:05", "remaining_time": "0:41:58"}
57
+ {"current_steps": 560, "total_steps": 969, "loss": 0.6125, "learning_rate": 5e-06, "epoch": 1.7337461300309598, "percentage": 57.79, "elapsed_time": "0:56:03", "remaining_time": "0:40:56"}
58
+ {"current_steps": 570, "total_steps": 969, "loss": 0.6118, "learning_rate": 5e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "0:57:02", "remaining_time": "0:39:55"}
59
+ {"current_steps": 580, "total_steps": 969, "loss": 0.6128, "learning_rate": 5e-06, "epoch": 1.7956656346749225, "percentage": 59.86, "elapsed_time": "0:58:00", "remaining_time": "0:38:54"}
60
+ {"current_steps": 590, "total_steps": 969, "loss": 0.6172, "learning_rate": 5e-06, "epoch": 1.826625386996904, "percentage": 60.89, "elapsed_time": "0:58:58", "remaining_time": "0:37:52"}
61
+ {"current_steps": 600, "total_steps": 969, "loss": 0.615, "learning_rate": 5e-06, "epoch": 1.8575851393188856, "percentage": 61.92, "elapsed_time": "0:59:56", "remaining_time": "0:36:51"}
62
+ {"current_steps": 610, "total_steps": 969, "loss": 0.6182, "learning_rate": 5e-06, "epoch": 1.888544891640867, "percentage": 62.95, "elapsed_time": "1:00:54", "remaining_time": "0:35:50"}
63
+ {"current_steps": 620, "total_steps": 969, "loss": 0.6131, "learning_rate": 5e-06, "epoch": 1.9195046439628483, "percentage": 63.98, "elapsed_time": "1:01:52", "remaining_time": "0:34:49"}
64
+ {"current_steps": 630, "total_steps": 969, "loss": 0.6152, "learning_rate": 5e-06, "epoch": 1.9504643962848296, "percentage": 65.02, "elapsed_time": "1:02:50", "remaining_time": "0:33:49"}
65
+ {"current_steps": 640, "total_steps": 969, "loss": 0.6073, "learning_rate": 5e-06, "epoch": 1.9814241486068112, "percentage": 66.05, "elapsed_time": "1:03:48", "remaining_time": "0:32:48"}
66
+ {"current_steps": 646, "total_steps": 969, "eval_loss": 0.6524380445480347, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:04:54", "remaining_time": "0:32:27"}
67
+ {"current_steps": 650, "total_steps": 969, "loss": 0.591, "learning_rate": 5e-06, "epoch": 2.0123839009287927, "percentage": 67.08, "elapsed_time": "1:06:53", "remaining_time": "0:32:49"}
68
+ {"current_steps": 660, "total_steps": 969, "loss": 0.5646, "learning_rate": 5e-06, "epoch": 2.043343653250774, "percentage": 68.11, "elapsed_time": "1:07:52", "remaining_time": "0:31:46"}
69
+ {"current_steps": 670, "total_steps": 969, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.0743034055727554, "percentage": 69.14, "elapsed_time": "1:08:50", "remaining_time": "0:30:43"}