Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_opengpt_x.25

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
gsmyrnis commited on
Commit
e5a1af9
·
verified ·
1 Parent(s): de9ed0e

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 +26 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1abfcf75628fddf4413c1ba0722a259d17b57419803034994c05412b7e59c63b
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43e939843d94e5f791ad2bec4713114ee6642e24b173a9ab1b6dee503a97830
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a0b26dae4cbdb7196d047a427916a9c3f730218d277aecbf26130e33e27655c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f60d006e3ac1943697485e02a48d18ddbf79c03563578ccf39518dae45e02f
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7578fb3077861ce1721be3d3b7c2705e106a2e949b0fc6bd5eef18158fb7a630
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270c58b6e556f0ca1c0ae18ab25bcb906c8697482cf12451ae42798b86ac121f
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:ffe0056e237ca24f63902a94f11e83a2c0b0258ab1a673e9117b464cf08daeda
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c4a4f25fd909d49d502fa4098c54533c71f0b68ea0b45923b552699cc67ad20
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -57,3 +57,29 @@
57
  {"current_steps": 550, "total_steps": 819, "loss": 0.6632, "learning_rate": 5e-06, "epoch": 2.0146520146520146, "percentage": 67.16, "elapsed_time": "0:59:11", "remaining_time": "0:28:56"}
58
  {"current_steps": 560, "total_steps": 819, "loss": 0.6268, "learning_rate": 5e-06, "epoch": 2.051282051282051, "percentage": 68.38, "elapsed_time": "1:00:10", "remaining_time": "0:27:49"}
59
  {"current_steps": 570, "total_steps": 819, "loss": 0.6288, "learning_rate": 5e-06, "epoch": 2.087912087912088, "percentage": 69.6, "elapsed_time": "1:01:10", "remaining_time": "0:26:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  {"current_steps": 550, "total_steps": 819, "loss": 0.6632, "learning_rate": 5e-06, "epoch": 2.0146520146520146, "percentage": 67.16, "elapsed_time": "0:59:11", "remaining_time": "0:28:56"}
58
  {"current_steps": 560, "total_steps": 819, "loss": 0.6268, "learning_rate": 5e-06, "epoch": 2.051282051282051, "percentage": 68.38, "elapsed_time": "1:00:10", "remaining_time": "0:27:49"}
59
  {"current_steps": 570, "total_steps": 819, "loss": 0.6288, "learning_rate": 5e-06, "epoch": 2.087912087912088, "percentage": 69.6, "elapsed_time": "1:01:10", "remaining_time": "0:26:43"}
60
+ {"current_steps": 580, "total_steps": 819, "loss": 0.6268, "learning_rate": 5e-06, "epoch": 2.1245421245421245, "percentage": 70.82, "elapsed_time": "1:02:09", "remaining_time": "0:25:36"}
61
+ {"current_steps": 590, "total_steps": 819, "loss": 0.6284, "learning_rate": 5e-06, "epoch": 2.161172161172161, "percentage": 72.04, "elapsed_time": "1:03:08", "remaining_time": "0:24:30"}
62
+ {"current_steps": 600, "total_steps": 819, "loss": 0.6303, "learning_rate": 5e-06, "epoch": 2.197802197802198, "percentage": 73.26, "elapsed_time": "1:04:08", "remaining_time": "0:23:24"}
63
+ {"current_steps": 610, "total_steps": 819, "loss": 0.6286, "learning_rate": 5e-06, "epoch": 2.2344322344322345, "percentage": 74.48, "elapsed_time": "1:05:07", "remaining_time": "0:22:18"}
64
+ {"current_steps": 620, "total_steps": 819, "loss": 0.6363, "learning_rate": 5e-06, "epoch": 2.271062271062271, "percentage": 75.7, "elapsed_time": "1:06:06", "remaining_time": "0:21:13"}
65
+ {"current_steps": 630, "total_steps": 819, "loss": 0.6325, "learning_rate": 5e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "1:07:05", "remaining_time": "0:20:07"}
66
+ {"current_steps": 640, "total_steps": 819, "loss": 0.6392, "learning_rate": 5e-06, "epoch": 2.3443223443223444, "percentage": 78.14, "elapsed_time": "1:08:04", "remaining_time": "0:19:02"}
67
+ {"current_steps": 650, "total_steps": 819, "loss": 0.6337, "learning_rate": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "1:09:04", "remaining_time": "0:17:57"}
68
+ {"current_steps": 660, "total_steps": 819, "loss": 0.6405, "learning_rate": 5e-06, "epoch": 2.4175824175824174, "percentage": 80.59, "elapsed_time": "1:10:03", "remaining_time": "0:16:52"}
69
+ {"current_steps": 670, "total_steps": 819, "loss": 0.6342, "learning_rate": 5e-06, "epoch": 2.4542124542124544, "percentage": 81.81, "elapsed_time": "1:11:02", "remaining_time": "0:15:48"}
70
+ {"current_steps": 680, "total_steps": 819, "loss": 0.6348, "learning_rate": 5e-06, "epoch": 2.490842490842491, "percentage": 83.03, "elapsed_time": "1:12:02", "remaining_time": "0:14:43"}
71
+ {"current_steps": 690, "total_steps": 819, "loss": 0.6375, "learning_rate": 5e-06, "epoch": 2.5274725274725274, "percentage": 84.25, "elapsed_time": "1:13:01", "remaining_time": "0:13:39"}
72
+ {"current_steps": 700, "total_steps": 819, "loss": 0.6376, "learning_rate": 5e-06, "epoch": 2.564102564102564, "percentage": 85.47, "elapsed_time": "1:14:01", "remaining_time": "0:12:35"}
73
+ {"current_steps": 710, "total_steps": 819, "loss": 0.6337, "learning_rate": 5e-06, "epoch": 2.600732600732601, "percentage": 86.69, "elapsed_time": "1:15:00", "remaining_time": "0:11:30"}
74
+ {"current_steps": 720, "total_steps": 819, "loss": 0.6362, "learning_rate": 5e-06, "epoch": 2.6373626373626373, "percentage": 87.91, "elapsed_time": "1:15:59", "remaining_time": "0:10:26"}
75
+ {"current_steps": 730, "total_steps": 819, "loss": 0.6348, "learning_rate": 5e-06, "epoch": 2.6739926739926743, "percentage": 89.13, "elapsed_time": "1:16:59", "remaining_time": "0:09:23"}
76
+ {"current_steps": 740, "total_steps": 819, "loss": 0.6346, "learning_rate": 5e-06, "epoch": 2.7106227106227108, "percentage": 90.35, "elapsed_time": "1:17:58", "remaining_time": "0:08:19"}
77
+ {"current_steps": 750, "total_steps": 819, "loss": 0.6346, "learning_rate": 5e-06, "epoch": 2.7472527472527473, "percentage": 91.58, "elapsed_time": "1:18:58", "remaining_time": "0:07:15"}
78
+ {"current_steps": 760, "total_steps": 819, "loss": 0.6371, "learning_rate": 5e-06, "epoch": 2.7838827838827838, "percentage": 92.8, "elapsed_time": "1:19:57", "remaining_time": "0:06:12"}
79
+ {"current_steps": 770, "total_steps": 819, "loss": 0.6377, "learning_rate": 5e-06, "epoch": 2.8205128205128203, "percentage": 94.02, "elapsed_time": "1:20:56", "remaining_time": "0:05:09"}
80
+ {"current_steps": 780, "total_steps": 819, "loss": 0.634, "learning_rate": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:21:55", "remaining_time": "0:04:05"}
81
+ {"current_steps": 790, "total_steps": 819, "loss": 0.637, "learning_rate": 5e-06, "epoch": 2.8937728937728937, "percentage": 96.46, "elapsed_time": "1:22:54", "remaining_time": "0:03:02"}
82
+ {"current_steps": 800, "total_steps": 819, "loss": 0.6352, "learning_rate": 5e-06, "epoch": 2.9304029304029307, "percentage": 97.68, "elapsed_time": "1:23:54", "remaining_time": "0:01:59"}
83
+ {"current_steps": 810, "total_steps": 819, "loss": 0.634, "learning_rate": 5e-06, "epoch": 2.967032967032967, "percentage": 98.9, "elapsed_time": "1:24:53", "remaining_time": "0:00:56"}
84
+ {"current_steps": 819, "total_steps": 819, "eval_loss": 0.731658935546875, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:27:46", "remaining_time": "0:00:00"}
85
+ {"current_steps": 819, "total_steps": 819, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:29:25", "remaining_time": "0:00:00"}