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
e449570
·
verified ·
1 Parent(s): d8863f7

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 +31 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:235e5e128fa2e67b82de6600eeae88e3dfb811abac0ee0af77c76630ab93205c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62e65fdd2ee4e16e35ce870d1e75572e7f39349eca7bc80e77cf46d0905532b
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:a72e58112a493d0ff2bf9671735e074543bcf3ebe1dff8e5b0d04085508110c7
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e2313124ad159f45ee19a600e92144b227748794b50e4e26dfe18ba5028f03
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f3b2b2834a7ca6542e7bfd18b017c06682973da34749eda269cb0c840aab53c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf815064baa5f641daae9cfa07c0e74998fe30f3eb0d530c9c9f8ae9f90eeda
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f68bcf0128f6843b5d2eaaad0c319ff2589cac3ca19e9280cd0c99d8108ffe8
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb5b82fb401a9c9293dc6ad1cbb3e0fd03ab28ebdcde2890f55974e44e27cf9
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -67,3 +67,34 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
70
+ {"current_steps": 680, "total_steps": 969, "loss": 0.5621, "learning_rate": 5e-06, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "1:09:49", "remaining_time": "0:29:40"}
71
+ {"current_steps": 690, "total_steps": 969, "loss": 0.5664, "learning_rate": 5e-06, "epoch": 2.136222910216718, "percentage": 71.21, "elapsed_time": "1:10:47", "remaining_time": "0:28:37"}
72
+ {"current_steps": 700, "total_steps": 969, "loss": 0.5659, "learning_rate": 5e-06, "epoch": 2.1671826625387, "percentage": 72.24, "elapsed_time": "1:11:46", "remaining_time": "0:27:34"}
73
+ {"current_steps": 710, "total_steps": 969, "loss": 0.5744, "learning_rate": 5e-06, "epoch": 2.198142414860681, "percentage": 73.27, "elapsed_time": "1:12:44", "remaining_time": "0:26:32"}
74
+ {"current_steps": 720, "total_steps": 969, "loss": 0.5634, "learning_rate": 5e-06, "epoch": 2.2291021671826625, "percentage": 74.3, "elapsed_time": "1:13:42", "remaining_time": "0:25:29"}
75
+ {"current_steps": 730, "total_steps": 969, "loss": 0.5633, "learning_rate": 5e-06, "epoch": 2.260061919504644, "percentage": 75.34, "elapsed_time": "1:14:41", "remaining_time": "0:24:27"}
76
+ {"current_steps": 740, "total_steps": 969, "loss": 0.572, "learning_rate": 5e-06, "epoch": 2.291021671826625, "percentage": 76.37, "elapsed_time": "1:15:39", "remaining_time": "0:23:24"}
77
+ {"current_steps": 750, "total_steps": 969, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.321981424148607, "percentage": 77.4, "elapsed_time": "1:16:37", "remaining_time": "0:22:22"}
78
+ {"current_steps": 760, "total_steps": 969, "loss": 0.5729, "learning_rate": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "1:17:36", "remaining_time": "0:21:20"}
79
+ {"current_steps": 770, "total_steps": 969, "loss": 0.5665, "learning_rate": 5e-06, "epoch": 2.3839009287925697, "percentage": 79.46, "elapsed_time": "1:18:34", "remaining_time": "0:20:18"}
80
+ {"current_steps": 780, "total_steps": 969, "loss": 0.5702, "learning_rate": 5e-06, "epoch": 2.414860681114551, "percentage": 80.5, "elapsed_time": "1:19:33", "remaining_time": "0:19:16"}
81
+ {"current_steps": 790, "total_steps": 969, "loss": 0.5706, "learning_rate": 5e-06, "epoch": 2.4458204334365323, "percentage": 81.53, "elapsed_time": "1:20:31", "remaining_time": "0:18:14"}
82
+ {"current_steps": 800, "total_steps": 969, "loss": 0.5739, "learning_rate": 5e-06, "epoch": 2.476780185758514, "percentage": 82.56, "elapsed_time": "1:21:29", "remaining_time": "0:17:12"}
83
+ {"current_steps": 810, "total_steps": 969, "loss": 0.5707, "learning_rate": 5e-06, "epoch": 2.5077399380804954, "percentage": 83.59, "elapsed_time": "1:22:28", "remaining_time": "0:16:11"}
84
+ {"current_steps": 820, "total_steps": 969, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.538699690402477, "percentage": 84.62, "elapsed_time": "1:23:26", "remaining_time": "0:15:09"}
85
+ {"current_steps": 830, "total_steps": 969, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.569659442724458, "percentage": 85.66, "elapsed_time": "1:24:25", "remaining_time": "0:14:08"}
86
+ {"current_steps": 840, "total_steps": 969, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.6006191950464395, "percentage": 86.69, "elapsed_time": "1:25:23", "remaining_time": "0:13:06"}
87
+ {"current_steps": 850, "total_steps": 969, "loss": 0.5711, "learning_rate": 5e-06, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "1:26:22", "remaining_time": "0:12:05"}
88
+ {"current_steps": 860, "total_steps": 969, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.6625386996904026, "percentage": 88.75, "elapsed_time": "1:27:20", "remaining_time": "0:11:04"}
89
+ {"current_steps": 870, "total_steps": 969, "loss": 0.5727, "learning_rate": 5e-06, "epoch": 2.693498452012384, "percentage": 89.78, "elapsed_time": "1:28:18", "remaining_time": "0:10:02"}
90
+ {"current_steps": 880, "total_steps": 969, "loss": 0.5676, "learning_rate": 5e-06, "epoch": 2.7244582043343653, "percentage": 90.82, "elapsed_time": "1:29:16", "remaining_time": "0:09:01"}
91
+ {"current_steps": 890, "total_steps": 969, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.7554179566563466, "percentage": 91.85, "elapsed_time": "1:30:14", "remaining_time": "0:08:00"}
92
+ {"current_steps": 900, "total_steps": 969, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.7863777089783284, "percentage": 92.88, "elapsed_time": "1:31:12", "remaining_time": "0:06:59"}
93
+ {"current_steps": 910, "total_steps": 969, "loss": 0.5717, "learning_rate": 5e-06, "epoch": 2.8173374613003097, "percentage": 93.91, "elapsed_time": "1:32:10", "remaining_time": "0:05:58"}
94
+ {"current_steps": 920, "total_steps": 969, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.848297213622291, "percentage": 94.94, "elapsed_time": "1:33:08", "remaining_time": "0:04:57"}
95
+ {"current_steps": 930, "total_steps": 969, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.8792569659442724, "percentage": 95.98, "elapsed_time": "1:34:06", "remaining_time": "0:03:56"}
96
+ {"current_steps": 940, "total_steps": 969, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.9102167182662537, "percentage": 97.01, "elapsed_time": "1:35:05", "remaining_time": "0:02:56"}
97
+ {"current_steps": 950, "total_steps": 969, "loss": 0.5743, "learning_rate": 5e-06, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "1:36:03", "remaining_time": "0:01:55"}
98
+ {"current_steps": 960, "total_steps": 969, "loss": 0.5733, "learning_rate": 5e-06, "epoch": 2.972136222910217, "percentage": 99.07, "elapsed_time": "1:37:01", "remaining_time": "0:00:54"}
99
+ {"current_steps": 969, "total_steps": 969, "eval_loss": 0.6580318212509155, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:39:47", "remaining_time": "0:00:00"}
100
+ {"current_steps": 969, "total_steps": 969, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:41:12", "remaining_time": "0:00:00"}