Hugging Face's logo

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

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
gsmyrnis commited on
Commit
6979494
·
verified ·
1 Parent(s): b907766

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 +30 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:126c7a7e4793809c43e2c4a93843184bd59b61870604fe42501db7dfafb9e5ee
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:177bf8229926a926ab64731991d342ceffd59dd0c05d2121d961dc4c30aa6f59
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:b3e1752259ae55754c09b86a225042216023bc58554fbc4bece5730243c00dbc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b592e1f5b4a39683a31df53ee615b3ef83bb183e97f078e5bc0c8cba9e7c05b8
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:aea47101c9721aae9832117d86616d1567b1a9072417c478d5c6675416b09bbf
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5bc3c5735476f56c8f354673a624b8d8d361a5bc9e86efcec89ad6efe70722a
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:cdf4349b03201f92349afbbddc3050a0d61e8a3605e860cd35a03f99bae48d83
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25264608b27a5a4cb984833d7afe5a84b9dcb83576fe322ad7c5cdddc41ae5a5
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -63,3 +63,33 @@
63
  {"current_steps": 612, "total_steps": 918, "eval_loss": 0.6249033808708191, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:03:15", "remaining_time": "0:31:37"}
64
  {"current_steps": 620, "total_steps": 918, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 2.026143790849673, "percentage": 67.54, "elapsed_time": "1:05:23", "remaining_time": "0:31:25"}
65
  {"current_steps": 630, "total_steps": 918, "loss": 0.5407, "learning_rate": 5e-06, "epoch": 2.0588235294117645, "percentage": 68.63, "elapsed_time": "1:06:23", "remaining_time": "0:30:21"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  {"current_steps": 612, "total_steps": 918, "eval_loss": 0.6249033808708191, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:03:15", "remaining_time": "0:31:37"}
64
  {"current_steps": 620, "total_steps": 918, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 2.026143790849673, "percentage": 67.54, "elapsed_time": "1:05:23", "remaining_time": "0:31:25"}
65
  {"current_steps": 630, "total_steps": 918, "loss": 0.5407, "learning_rate": 5e-06, "epoch": 2.0588235294117645, "percentage": 68.63, "elapsed_time": "1:06:23", "remaining_time": "0:30:21"}
66
+ {"current_steps": 640, "total_steps": 918, "loss": 0.5442, "learning_rate": 5e-06, "epoch": 2.0915032679738563, "percentage": 69.72, "elapsed_time": "1:07:23", "remaining_time": "0:29:16"}
67
+ {"current_steps": 650, "total_steps": 918, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 2.1241830065359477, "percentage": 70.81, "elapsed_time": "1:08:23", "remaining_time": "0:28:11"}
68
+ {"current_steps": 660, "total_steps": 918, "loss": 0.5495, "learning_rate": 5e-06, "epoch": 2.156862745098039, "percentage": 71.9, "elapsed_time": "1:09:23", "remaining_time": "0:27:07"}
69
+ {"current_steps": 670, "total_steps": 918, "loss": 0.5477, "learning_rate": 5e-06, "epoch": 2.189542483660131, "percentage": 72.98, "elapsed_time": "1:10:23", "remaining_time": "0:26:03"}
70
+ {"current_steps": 680, "total_steps": 918, "loss": 0.5453, "learning_rate": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "1:11:24", "remaining_time": "0:24:59"}
71
+ {"current_steps": 690, "total_steps": 918, "loss": 0.5491, "learning_rate": 5e-06, "epoch": 2.2549019607843137, "percentage": 75.16, "elapsed_time": "1:12:24", "remaining_time": "0:23:55"}
72
+ {"current_steps": 700, "total_steps": 918, "loss": 0.5411, "learning_rate": 5e-06, "epoch": 2.287581699346405, "percentage": 76.25, "elapsed_time": "1:13:25", "remaining_time": "0:22:51"}
73
+ {"current_steps": 710, "total_steps": 918, "loss": 0.539, "learning_rate": 5e-06, "epoch": 2.3202614379084965, "percentage": 77.34, "elapsed_time": "1:14:25", "remaining_time": "0:21:48"}
74
+ {"current_steps": 720, "total_steps": 918, "loss": 0.546, "learning_rate": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "1:15:25", "remaining_time": "0:20:44"}
75
+ {"current_steps": 730, "total_steps": 918, "loss": 0.5424, "learning_rate": 5e-06, "epoch": 2.3856209150326797, "percentage": 79.52, "elapsed_time": "1:16:25", "remaining_time": "0:19:40"}
76
+ {"current_steps": 740, "total_steps": 918, "loss": 0.5467, "learning_rate": 5e-06, "epoch": 2.418300653594771, "percentage": 80.61, "elapsed_time": "1:17:25", "remaining_time": "0:18:37"}
77
+ {"current_steps": 750, "total_steps": 918, "loss": 0.551, "learning_rate": 5e-06, "epoch": 2.450980392156863, "percentage": 81.7, "elapsed_time": "1:18:24", "remaining_time": "0:17:33"}
78
+ {"current_steps": 760, "total_steps": 918, "loss": 0.5454, "learning_rate": 5e-06, "epoch": 2.4836601307189543, "percentage": 82.79, "elapsed_time": "1:19:24", "remaining_time": "0:16:30"}
79
+ {"current_steps": 770, "total_steps": 918, "loss": 0.546, "learning_rate": 5e-06, "epoch": 2.5163398692810457, "percentage": 83.88, "elapsed_time": "1:20:25", "remaining_time": "0:15:27"}
80
+ {"current_steps": 780, "total_steps": 918, "loss": 0.5434, "learning_rate": 5e-06, "epoch": 2.549019607843137, "percentage": 84.97, "elapsed_time": "1:21:25", "remaining_time": "0:14:24"}
81
+ {"current_steps": 790, "total_steps": 918, "loss": 0.5515, "learning_rate": 5e-06, "epoch": 2.581699346405229, "percentage": 86.06, "elapsed_time": "1:22:26", "remaining_time": "0:13:21"}
82
+ {"current_steps": 800, "total_steps": 918, "loss": 0.5513, "learning_rate": 5e-06, "epoch": 2.6143790849673203, "percentage": 87.15, "elapsed_time": "1:23:26", "remaining_time": "0:12:18"}
83
+ {"current_steps": 810, "total_steps": 918, "loss": 0.5472, "learning_rate": 5e-06, "epoch": 2.6470588235294117, "percentage": 88.24, "elapsed_time": "1:24:26", "remaining_time": "0:11:15"}
84
+ {"current_steps": 820, "total_steps": 918, "loss": 0.5496, "learning_rate": 5e-06, "epoch": 2.6797385620915035, "percentage": 89.32, "elapsed_time": "1:25:25", "remaining_time": "0:10:12"}
85
+ {"current_steps": 830, "total_steps": 918, "loss": 0.5444, "learning_rate": 5e-06, "epoch": 2.712418300653595, "percentage": 90.41, "elapsed_time": "1:26:26", "remaining_time": "0:09:09"}
86
+ {"current_steps": 840, "total_steps": 918, "loss": 0.5501, "learning_rate": 5e-06, "epoch": 2.7450980392156863, "percentage": 91.5, "elapsed_time": "1:27:27", "remaining_time": "0:08:07"}
87
+ {"current_steps": 850, "total_steps": 918, "loss": 0.5477, "learning_rate": 5e-06, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "1:28:26", "remaining_time": "0:07:04"}
88
+ {"current_steps": 860, "total_steps": 918, "loss": 0.5472, "learning_rate": 5e-06, "epoch": 2.810457516339869, "percentage": 93.68, "elapsed_time": "1:29:26", "remaining_time": "0:06:01"}
89
+ {"current_steps": 870, "total_steps": 918, "loss": 0.5512, "learning_rate": 5e-06, "epoch": 2.843137254901961, "percentage": 94.77, "elapsed_time": "1:30:26", "remaining_time": "0:04:59"}
90
+ {"current_steps": 880, "total_steps": 918, "loss": 0.5521, "learning_rate": 5e-06, "epoch": 2.8758169934640523, "percentage": 95.86, "elapsed_time": "1:31:26", "remaining_time": "0:03:56"}
91
+ {"current_steps": 890, "total_steps": 918, "loss": 0.5449, "learning_rate": 5e-06, "epoch": 2.9084967320261437, "percentage": 96.95, "elapsed_time": "1:32:26", "remaining_time": "0:02:54"}
92
+ {"current_steps": 900, "total_steps": 918, "loss": 0.5498, "learning_rate": 5e-06, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "1:33:26", "remaining_time": "0:01:52"}
93
+ {"current_steps": 910, "total_steps": 918, "loss": 0.5495, "learning_rate": 5e-06, "epoch": 2.973856209150327, "percentage": 99.13, "elapsed_time": "1:34:25", "remaining_time": "0:00:49"}
94
+ {"current_steps": 918, "total_steps": 918, "eval_loss": 0.628399670124054, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:36:59", "remaining_time": "0:00:00"}
95
+ {"current_steps": 918, "total_steps": 918, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:38:17", "remaining_time": "0:00:00"}