Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_opengpt_x8

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
469c1bc
•
1 Parent(s): 52ce66b

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 sha256:9a07ef487cb321e65115b8186f2c2497999f228822570684b6863e4260391eb0
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a043da359e951e6996e778beed5122d81d075566be927632d84938826a8e47
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f3f02c24b6d2097878debd6cbfb6ab9ed121c6208e5c01f7ef6a05dea625422
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9604bdd336350d342e616cfb7a56db3fb21f064fe8ef2bc9113733c502c4d3e
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:cbac47f02fabac71f42a7815080362f779e63b9196ab2ec5d1830d25705b015d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81405a8c8546822be2693be905dc62e59a56142d229cee21fc214d56bbd5dfda
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:555255a3cc7cbfda0d053d3777595ddc581c9d813606a8dcb4832e4784acf236
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f129be760a286f5a80a006036753c37e86aa084acfce99dba6218705fd5ce7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -58,3 +58,29 @@
58
  {"current_steps": 560, "total_steps": 825, "loss": 0.6351, "learning_rate": 5e-06, "epoch": 2.036363636363636, "percentage": 67.88, "elapsed_time": "0:59:27", "remaining_time": "0:28:08"}
59
  {"current_steps": 570, "total_steps": 825, "loss": 0.6307, "learning_rate": 5e-06, "epoch": 2.0727272727272728, "percentage": 69.09, "elapsed_time": "1:00:26", "remaining_time": "0:27:02"}
60
  {"current_steps": 580, "total_steps": 825, "loss": 0.6357, "learning_rate": 5e-06, "epoch": 2.109090909090909, "percentage": 70.3, "elapsed_time": "1:01:25", "remaining_time": "0:25:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  {"current_steps": 560, "total_steps": 825, "loss": 0.6351, "learning_rate": 5e-06, "epoch": 2.036363636363636, "percentage": 67.88, "elapsed_time": "0:59:27", "remaining_time": "0:28:08"}
59
  {"current_steps": 570, "total_steps": 825, "loss": 0.6307, "learning_rate": 5e-06, "epoch": 2.0727272727272728, "percentage": 69.09, "elapsed_time": "1:00:26", "remaining_time": "0:27:02"}
60
  {"current_steps": 580, "total_steps": 825, "loss": 0.6357, "learning_rate": 5e-06, "epoch": 2.109090909090909, "percentage": 70.3, "elapsed_time": "1:01:25", "remaining_time": "0:25:56"}
61
+ {"current_steps": 590, "total_steps": 825, "loss": 0.6375, "learning_rate": 5e-06, "epoch": 2.1454545454545455, "percentage": 71.52, "elapsed_time": "1:02:24", "remaining_time": "0:24:51"}
62
+ {"current_steps": 600, "total_steps": 825, "loss": 0.635, "learning_rate": 5e-06, "epoch": 2.1818181818181817, "percentage": 72.73, "elapsed_time": "1:03:23", "remaining_time": "0:23:46"}
63
+ {"current_steps": 610, "total_steps": 825, "loss": 0.6383, "learning_rate": 5e-06, "epoch": 2.2181818181818183, "percentage": 73.94, "elapsed_time": "1:04:22", "remaining_time": "0:22:41"}
64
+ {"current_steps": 620, "total_steps": 825, "loss": 0.6321, "learning_rate": 5e-06, "epoch": 2.2545454545454544, "percentage": 75.15, "elapsed_time": "1:05:21", "remaining_time": "0:21:36"}
65
+ {"current_steps": 630, "total_steps": 825, "loss": 0.6341, "learning_rate": 5e-06, "epoch": 2.290909090909091, "percentage": 76.36, "elapsed_time": "1:06:21", "remaining_time": "0:20:32"}
66
+ {"current_steps": 640, "total_steps": 825, "loss": 0.6326, "learning_rate": 5e-06, "epoch": 2.327272727272727, "percentage": 77.58, "elapsed_time": "1:07:20", "remaining_time": "0:19:27"}
67
+ {"current_steps": 650, "total_steps": 825, "loss": 0.6385, "learning_rate": 5e-06, "epoch": 2.3636363636363638, "percentage": 78.79, "elapsed_time": "1:08:19", "remaining_time": "0:18:23"}
68
+ {"current_steps": 660, "total_steps": 825, "loss": 0.6373, "learning_rate": 5e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "1:09:19", "remaining_time": "0:17:19"}
69
+ {"current_steps": 670, "total_steps": 825, "loss": 0.6399, "learning_rate": 5e-06, "epoch": 2.4363636363636365, "percentage": 81.21, "elapsed_time": "1:10:17", "remaining_time": "0:16:15"}
70
+ {"current_steps": 680, "total_steps": 825, "loss": 0.6393, "learning_rate": 5e-06, "epoch": 2.4727272727272727, "percentage": 82.42, "elapsed_time": "1:11:16", "remaining_time": "0:15:11"}
71
+ {"current_steps": 690, "total_steps": 825, "loss": 0.6405, "learning_rate": 5e-06, "epoch": 2.509090909090909, "percentage": 83.64, "elapsed_time": "1:12:15", "remaining_time": "0:14:08"}
72
+ {"current_steps": 700, "total_steps": 825, "loss": 0.6385, "learning_rate": 5e-06, "epoch": 2.5454545454545454, "percentage": 84.85, "elapsed_time": "1:13:15", "remaining_time": "0:13:04"}
73
+ {"current_steps": 710, "total_steps": 825, "loss": 0.6377, "learning_rate": 5e-06, "epoch": 2.581818181818182, "percentage": 86.06, "elapsed_time": "1:14:15", "remaining_time": "0:12:01"}
74
+ {"current_steps": 720, "total_steps": 825, "loss": 0.6427, "learning_rate": 5e-06, "epoch": 2.618181818181818, "percentage": 87.27, "elapsed_time": "1:15:14", "remaining_time": "0:10:58"}
75
+ {"current_steps": 730, "total_steps": 825, "loss": 0.6346, "learning_rate": 5e-06, "epoch": 2.6545454545454543, "percentage": 88.48, "elapsed_time": "1:16:14", "remaining_time": "0:09:55"}
76
+ {"current_steps": 740, "total_steps": 825, "loss": 0.6414, "learning_rate": 5e-06, "epoch": 2.690909090909091, "percentage": 89.7, "elapsed_time": "1:17:13", "remaining_time": "0:08:52"}
77
+ {"current_steps": 750, "total_steps": 825, "loss": 0.6363, "learning_rate": 5e-06, "epoch": 2.7272727272727275, "percentage": 90.91, "elapsed_time": "1:18:13", "remaining_time": "0:07:49"}
78
+ {"current_steps": 760, "total_steps": 825, "loss": 0.6421, "learning_rate": 5e-06, "epoch": 2.7636363636363637, "percentage": 92.12, "elapsed_time": "1:19:12", "remaining_time": "0:06:46"}
79
+ {"current_steps": 770, "total_steps": 825, "loss": 0.6356, "learning_rate": 5e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "1:20:10", "remaining_time": "0:05:43"}
80
+ {"current_steps": 780, "total_steps": 825, "loss": 0.6425, "learning_rate": 5e-06, "epoch": 2.8363636363636364, "percentage": 94.55, "elapsed_time": "1:21:09", "remaining_time": "0:04:40"}
81
+ {"current_steps": 790, "total_steps": 825, "loss": 0.6368, "learning_rate": 5e-06, "epoch": 2.8727272727272726, "percentage": 95.76, "elapsed_time": "1:22:08", "remaining_time": "0:03:38"}
82
+ {"current_steps": 800, "total_steps": 825, "loss": 0.6405, "learning_rate": 5e-06, "epoch": 2.909090909090909, "percentage": 96.97, "elapsed_time": "1:23:07", "remaining_time": "0:02:35"}
83
+ {"current_steps": 810, "total_steps": 825, "loss": 0.6357, "learning_rate": 5e-06, "epoch": 2.9454545454545453, "percentage": 98.18, "elapsed_time": "1:24:07", "remaining_time": "0:01:33"}
84
+ {"current_steps": 820, "total_steps": 825, "loss": 0.6412, "learning_rate": 5e-06, "epoch": 2.981818181818182, "percentage": 99.39, "elapsed_time": "1:25:06", "remaining_time": "0:00:31"}
85
+ {"current_steps": 825, "total_steps": 825, "eval_loss": 0.7299705147743225, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:27:36", "remaining_time": "0:00:00"}
86
+ {"current_steps": 825, "total_steps": 825, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:29:09", "remaining_time": "0:00:00"}