Hugging Face's logo

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

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
a42fc25
·
verified ·
1 Parent(s): 736a7ee

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 sha256:54511f9871d597ea6182cf0d02011ce925fd945297e9626bd09231071271ee96
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd49ae000d34b01d8f5c6ae1afd24563f92a86cf2dbecebb2efbdaebdb3a547b
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:ca9062c16e401734b0a3271993e4a7503425f079f8b43d8401b8393bf48e34a4
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb27085af591b779285fd170f63a3a5d4d6bfbeb42753d7247f9d08ce922dc1
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d1f99dbad6f32c94b8daf649562f2d073c473560b6e44c61ada2c983e5356b1
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216912a6c1c618903eb2cfab7cd5335c7a5dbcdd31956ca7b220fe0865e92ca2
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:c35e0a6607d62eca4a9d08a569f754fb102f95bfd42ae7a71bb28f5e2ed78145
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c15b141c9bb45f4e78ed3ca7891afd7e4f00548e192913f27fb04d7b38cc48
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -64,3 +64,33 @@
64
  {"current_steps": 620, "total_steps": 927, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.0064724919093853, "percentage": 66.88, "elapsed_time": "1:04:53", "remaining_time": "0:32:08"}
65
  {"current_steps": 630, "total_steps": 927, "loss": 0.5422, "learning_rate": 5e-06, "epoch": 2.0388349514563107, "percentage": 67.96, "elapsed_time": "1:05:52", "remaining_time": "0:31:03"}
66
  {"current_steps": 640, "total_steps": 927, "loss": 0.5364, "learning_rate": 5e-06, "epoch": 2.071197411003236, "percentage": 69.04, "elapsed_time": "1:06:51", "remaining_time": "0:29:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  {"current_steps": 620, "total_steps": 927, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.0064724919093853, "percentage": 66.88, "elapsed_time": "1:04:53", "remaining_time": "0:32:08"}
65
  {"current_steps": 630, "total_steps": 927, "loss": 0.5422, "learning_rate": 5e-06, "epoch": 2.0388349514563107, "percentage": 67.96, "elapsed_time": "1:05:52", "remaining_time": "0:31:03"}
66
  {"current_steps": 640, "total_steps": 927, "loss": 0.5364, "learning_rate": 5e-06, "epoch": 2.071197411003236, "percentage": 69.04, "elapsed_time": "1:06:51", "remaining_time": "0:29:58"}
67
+ {"current_steps": 650, "total_steps": 927, "loss": 0.5448, "learning_rate": 5e-06, "epoch": 2.103559870550162, "percentage": 70.12, "elapsed_time": "1:07:49", "remaining_time": "0:28:54"}
68
+ {"current_steps": 660, "total_steps": 927, "loss": 0.5406, "learning_rate": 5e-06, "epoch": 2.1359223300970873, "percentage": 71.2, "elapsed_time": "1:08:47", "remaining_time": "0:27:49"}
69
+ {"current_steps": 670, "total_steps": 927, "loss": 0.5464, "learning_rate": 5e-06, "epoch": 2.168284789644013, "percentage": 72.28, "elapsed_time": "1:09:45", "remaining_time": "0:26:45"}
70
+ {"current_steps": 680, "total_steps": 927, "loss": 0.5406, "learning_rate": 5e-06, "epoch": 2.2006472491909386, "percentage": 73.35, "elapsed_time": "1:10:44", "remaining_time": "0:25:41"}
71
+ {"current_steps": 690, "total_steps": 927, "loss": 0.5479, "learning_rate": 5e-06, "epoch": 2.233009708737864, "percentage": 74.43, "elapsed_time": "1:11:42", "remaining_time": "0:24:37"}
72
+ {"current_steps": 700, "total_steps": 927, "loss": 0.5428, "learning_rate": 5e-06, "epoch": 2.26537216828479, "percentage": 75.51, "elapsed_time": "1:12:42", "remaining_time": "0:23:34"}
73
+ {"current_steps": 710, "total_steps": 927, "loss": 0.5456, "learning_rate": 5e-06, "epoch": 2.2977346278317152, "percentage": 76.59, "elapsed_time": "1:13:42", "remaining_time": "0:22:31"}
74
+ {"current_steps": 720, "total_steps": 927, "loss": 0.5479, "learning_rate": 5e-06, "epoch": 2.3300970873786406, "percentage": 77.67, "elapsed_time": "1:14:40", "remaining_time": "0:21:28"}
75
+ {"current_steps": 730, "total_steps": 927, "loss": 0.5496, "learning_rate": 5e-06, "epoch": 2.3624595469255665, "percentage": 78.75, "elapsed_time": "1:15:39", "remaining_time": "0:20:25"}
76
+ {"current_steps": 740, "total_steps": 927, "loss": 0.5426, "learning_rate": 5e-06, "epoch": 2.394822006472492, "percentage": 79.83, "elapsed_time": "1:16:40", "remaining_time": "0:19:22"}
77
+ {"current_steps": 750, "total_steps": 927, "loss": 0.541, "learning_rate": 5e-06, "epoch": 2.4271844660194173, "percentage": 80.91, "elapsed_time": "1:17:39", "remaining_time": "0:18:19"}
78
+ {"current_steps": 760, "total_steps": 927, "loss": 0.5482, "learning_rate": 5e-06, "epoch": 2.459546925566343, "percentage": 81.98, "elapsed_time": "1:18:37", "remaining_time": "0:17:16"}
79
+ {"current_steps": 770, "total_steps": 927, "loss": 0.5406, "learning_rate": 5e-06, "epoch": 2.4919093851132685, "percentage": 83.06, "elapsed_time": "1:19:37", "remaining_time": "0:16:14"}
80
+ {"current_steps": 780, "total_steps": 927, "loss": 0.5468, "learning_rate": 5e-06, "epoch": 2.524271844660194, "percentage": 84.14, "elapsed_time": "1:20:36", "remaining_time": "0:15:11"}
81
+ {"current_steps": 790, "total_steps": 927, "loss": 0.5439, "learning_rate": 5e-06, "epoch": 2.55663430420712, "percentage": 85.22, "elapsed_time": "1:21:35", "remaining_time": "0:14:08"}
82
+ {"current_steps": 800, "total_steps": 927, "loss": 0.5458, "learning_rate": 5e-06, "epoch": 2.588996763754045, "percentage": 86.3, "elapsed_time": "1:22:35", "remaining_time": "0:13:06"}
83
+ {"current_steps": 810, "total_steps": 927, "loss": 0.5475, "learning_rate": 5e-06, "epoch": 2.6213592233009706, "percentage": 87.38, "elapsed_time": "1:23:33", "remaining_time": "0:12:04"}
84
+ {"current_steps": 820, "total_steps": 927, "loss": 0.5455, "learning_rate": 5e-06, "epoch": 2.6537216828478964, "percentage": 88.46, "elapsed_time": "1:24:33", "remaining_time": "0:11:02"}
85
+ {"current_steps": 830, "total_steps": 927, "loss": 0.5429, "learning_rate": 5e-06, "epoch": 2.686084142394822, "percentage": 89.54, "elapsed_time": "1:25:32", "remaining_time": "0:09:59"}
86
+ {"current_steps": 840, "total_steps": 927, "loss": 0.5475, "learning_rate": 5e-06, "epoch": 2.7184466019417477, "percentage": 90.61, "elapsed_time": "1:26:32", "remaining_time": "0:08:57"}
87
+ {"current_steps": 850, "total_steps": 927, "loss": 0.5471, "learning_rate": 5e-06, "epoch": 2.750809061488673, "percentage": 91.69, "elapsed_time": "1:27:32", "remaining_time": "0:07:55"}
88
+ {"current_steps": 860, "total_steps": 927, "loss": 0.5472, "learning_rate": 5e-06, "epoch": 2.783171521035599, "percentage": 92.77, "elapsed_time": "1:28:30", "remaining_time": "0:06:53"}
89
+ {"current_steps": 870, "total_steps": 927, "loss": 0.5483, "learning_rate": 5e-06, "epoch": 2.8155339805825244, "percentage": 93.85, "elapsed_time": "1:29:30", "remaining_time": "0:05:51"}
90
+ {"current_steps": 880, "total_steps": 927, "loss": 0.548, "learning_rate": 5e-06, "epoch": 2.8478964401294498, "percentage": 94.93, "elapsed_time": "1:30:29", "remaining_time": "0:04:49"}
91
+ {"current_steps": 890, "total_steps": 927, "loss": 0.5413, "learning_rate": 5e-06, "epoch": 2.8802588996763756, "percentage": 96.01, "elapsed_time": "1:31:29", "remaining_time": "0:03:48"}
92
+ {"current_steps": 900, "total_steps": 927, "loss": 0.5475, "learning_rate": 5e-06, "epoch": 2.912621359223301, "percentage": 97.09, "elapsed_time": "1:32:28", "remaining_time": "0:02:46"}
93
+ {"current_steps": 910, "total_steps": 927, "loss": 0.5453, "learning_rate": 5e-06, "epoch": 2.9449838187702264, "percentage": 98.17, "elapsed_time": "1:33:27", "remaining_time": "0:01:44"}
94
+ {"current_steps": 920, "total_steps": 927, "loss": 0.5403, "learning_rate": 5e-06, "epoch": 2.9773462783171523, "percentage": 99.24, "elapsed_time": "1:34:26", "remaining_time": "0:00:43"}
95
+ {"current_steps": 927, "total_steps": 927, "eval_loss": 0.6338526010513306, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:36:54", "remaining_time": "0:00:00"}
96
+ {"current_steps": 927, "total_steps": 927, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:38:18", "remaining_time": "0:00:00"}