Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_v3.1_wo_glaive_code_assistant

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
gsmyrnis commited on
Commit
74ce581
·
verified ·
1 Parent(s): 79b0378

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 sha256:4214cf1e900f79ddcaafec3e09ab77d0fc467908b8981c73621c16ef48c68d53
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4ceacb29e766574fe0258f6db2fb86594ad5bcf0570aa0ef83ca8a88728b8e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6198058d5975b33a5348ddc110097d96ee8e4142044e711614220aaf641f13a4
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f91b6cc40f01ff035593027ae322bc5a8c13660dce629a281a121daaf7121a
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:f6464e61593a0a47e78c31b6dc25488f85257da74492407f58e5077a41f7cc0e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740eb55f2952a1e2d1fe48d2398f84310e825926e45667789831a4e4af6da3ed
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75063680e00b669b3aa812e97741d4d8a1932b05d4b41d8d9d1f0b0400783e26
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff16ae157d2b2922cc3694bf0fbb699d14062fed717bdb0d6662ad41a098f7fa
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -65,3 +65,33 @@
65
  {"current_steps": 630, "total_steps": 939, "loss": 0.6152, "learning_rate": 5e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "1:05:31", "remaining_time": "0:32:08"}
66
  {"current_steps": 640, "total_steps": 939, "loss": 0.5881, "learning_rate": 5e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "1:06:30", "remaining_time": "0:31:04"}
67
  {"current_steps": 650, "total_steps": 939, "loss": 0.5871, "learning_rate": 5e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "1:07:28", "remaining_time": "0:29:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  {"current_steps": 630, "total_steps": 939, "loss": 0.6152, "learning_rate": 5e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "1:05:31", "remaining_time": "0:32:08"}
66
  {"current_steps": 640, "total_steps": 939, "loss": 0.5881, "learning_rate": 5e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "1:06:30", "remaining_time": "0:31:04"}
67
  {"current_steps": 650, "total_steps": 939, "loss": 0.5871, "learning_rate": 5e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "1:07:28", "remaining_time": "0:29:59"}
68
+ {"current_steps": 660, "total_steps": 939, "loss": 0.5896, "learning_rate": 5e-06, "epoch": 2.108626198083067, "percentage": 70.29, "elapsed_time": "1:08:26", "remaining_time": "0:28:55"}
69
+ {"current_steps": 670, "total_steps": 939, "loss": 0.589, "learning_rate": 5e-06, "epoch": 2.1405750798722045, "percentage": 71.35, "elapsed_time": "1:09:24", "remaining_time": "0:27:52"}
70
+ {"current_steps": 680, "total_steps": 939, "loss": 0.5901, "learning_rate": 5e-06, "epoch": 2.1725239616613417, "percentage": 72.42, "elapsed_time": "1:10:24", "remaining_time": "0:26:49"}
71
+ {"current_steps": 690, "total_steps": 939, "loss": 0.5863, "learning_rate": 5e-06, "epoch": 2.2044728434504792, "percentage": 73.48, "elapsed_time": "1:11:23", "remaining_time": "0:25:45"}
72
+ {"current_steps": 700, "total_steps": 939, "loss": 0.5846, "learning_rate": 5e-06, "epoch": 2.236421725239617, "percentage": 74.55, "elapsed_time": "1:12:22", "remaining_time": "0:24:42"}
73
+ {"current_steps": 710, "total_steps": 939, "loss": 0.5885, "learning_rate": 5e-06, "epoch": 2.268370607028754, "percentage": 75.61, "elapsed_time": "1:13:22", "remaining_time": "0:23:40"}
74
+ {"current_steps": 720, "total_steps": 939, "loss": 0.584, "learning_rate": 5e-06, "epoch": 2.3003194888178915, "percentage": 76.68, "elapsed_time": "1:14:21", "remaining_time": "0:22:36"}
75
+ {"current_steps": 730, "total_steps": 939, "loss": 0.5888, "learning_rate": 5e-06, "epoch": 2.3322683706070286, "percentage": 77.74, "elapsed_time": "1:15:21", "remaining_time": "0:21:34"}
76
+ {"current_steps": 740, "total_steps": 939, "loss": 0.591, "learning_rate": 5e-06, "epoch": 2.364217252396166, "percentage": 78.81, "elapsed_time": "1:16:19", "remaining_time": "0:20:31"}
77
+ {"current_steps": 750, "total_steps": 939, "loss": 0.5975, "learning_rate": 5e-06, "epoch": 2.3961661341853033, "percentage": 79.87, "elapsed_time": "1:17:18", "remaining_time": "0:19:28"}
78
+ {"current_steps": 760, "total_steps": 939, "loss": 0.5907, "learning_rate": 5e-06, "epoch": 2.428115015974441, "percentage": 80.94, "elapsed_time": "1:18:16", "remaining_time": "0:18:26"}
79
+ {"current_steps": 770, "total_steps": 939, "loss": 0.5902, "learning_rate": 5e-06, "epoch": 2.460063897763578, "percentage": 82.0, "elapsed_time": "1:19:15", "remaining_time": "0:17:23"}
80
+ {"current_steps": 780, "total_steps": 939, "loss": 0.5884, "learning_rate": 5e-06, "epoch": 2.4920127795527156, "percentage": 83.07, "elapsed_time": "1:20:13", "remaining_time": "0:16:21"}
81
+ {"current_steps": 790, "total_steps": 939, "loss": 0.5818, "learning_rate": 5e-06, "epoch": 2.523961661341853, "percentage": 84.13, "elapsed_time": "1:21:11", "remaining_time": "0:15:18"}
82
+ {"current_steps": 800, "total_steps": 939, "loss": 0.588, "learning_rate": 5e-06, "epoch": 2.5559105431309903, "percentage": 85.2, "elapsed_time": "1:22:09", "remaining_time": "0:14:16"}
83
+ {"current_steps": 810, "total_steps": 939, "loss": 0.5934, "learning_rate": 5e-06, "epoch": 2.587859424920128, "percentage": 86.26, "elapsed_time": "1:23:09", "remaining_time": "0:13:14"}
84
+ {"current_steps": 820, "total_steps": 939, "loss": 0.5865, "learning_rate": 5e-06, "epoch": 2.619808306709265, "percentage": 87.33, "elapsed_time": "1:24:08", "remaining_time": "0:12:12"}
85
+ {"current_steps": 830, "total_steps": 939, "loss": 0.5926, "learning_rate": 5e-06, "epoch": 2.6517571884984026, "percentage": 88.39, "elapsed_time": "1:25:07", "remaining_time": "0:11:10"}
86
+ {"current_steps": 840, "total_steps": 939, "loss": 0.5921, "learning_rate": 5e-06, "epoch": 2.68370607028754, "percentage": 89.46, "elapsed_time": "1:26:07", "remaining_time": "0:10:09"}
87
+ {"current_steps": 850, "total_steps": 939, "loss": 0.5954, "learning_rate": 5e-06, "epoch": 2.7156549520766773, "percentage": 90.52, "elapsed_time": "1:27:06", "remaining_time": "0:09:07"}
88
+ {"current_steps": 860, "total_steps": 939, "loss": 0.5988, "learning_rate": 5e-06, "epoch": 2.747603833865815, "percentage": 91.59, "elapsed_time": "1:28:05", "remaining_time": "0:08:05"}
89
+ {"current_steps": 870, "total_steps": 939, "loss": 0.6008, "learning_rate": 5e-06, "epoch": 2.779552715654952, "percentage": 92.65, "elapsed_time": "1:29:05", "remaining_time": "0:07:03"}
90
+ {"current_steps": 880, "total_steps": 939, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 2.8115015974440896, "percentage": 93.72, "elapsed_time": "1:30:04", "remaining_time": "0:06:02"}
91
+ {"current_steps": 890, "total_steps": 939, "loss": 0.592, "learning_rate": 5e-06, "epoch": 2.8434504792332267, "percentage": 94.78, "elapsed_time": "1:31:04", "remaining_time": "0:05:00"}
92
+ {"current_steps": 900, "total_steps": 939, "loss": 0.6, "learning_rate": 5e-06, "epoch": 2.8753993610223643, "percentage": 95.85, "elapsed_time": "1:32:02", "remaining_time": "0:03:59"}
93
+ {"current_steps": 910, "total_steps": 939, "loss": 0.5938, "learning_rate": 5e-06, "epoch": 2.9073482428115014, "percentage": 96.91, "elapsed_time": "1:33:01", "remaining_time": "0:02:57"}
94
+ {"current_steps": 920, "total_steps": 939, "loss": 0.586, "learning_rate": 5e-06, "epoch": 2.939297124600639, "percentage": 97.98, "elapsed_time": "1:34:02", "remaining_time": "0:01:56"}
95
+ {"current_steps": 930, "total_steps": 939, "loss": 0.5911, "learning_rate": 5e-06, "epoch": 2.9712460063897765, "percentage": 99.04, "elapsed_time": "1:35:00", "remaining_time": "0:00:55"}
96
+ {"current_steps": 939, "total_steps": 939, "eval_loss": 0.6763173341751099, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:37:59", "remaining_time": "0:00:00"}
97
+ {"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:39:37", "remaining_time": "0:00:00"}