Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_dcft_v1_wo_camel_biology_gpt-4o-mini

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
gsmyrnis commited on
Commit
134ce88
·
verified ·
1 Parent(s): 31abe7e

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 +39 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464938412cf817493de74102420ecf66e20746a3384556938c88a451cc0f5750
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712aab6d3633bd335e0c8ba9aa4ff87baffd560d9dd90b4135d96b78b098a8d0
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:b7963afa12cf60841eee1b3cabbbde446b56d7be84cb507189e6d8a4f29dad6f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3abac5f3d5522ac6fa26d8b48652afe11c1f0e22331613bffcaaa80955b7b0
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc7c1e31ecbc5f18a78e835fa711c6752ecd53a02a9214110a551f0d98217ed
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d92cae6d35344443a69b5b1267ddb2d1797ea8d3af010c05763056f156a8cd
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:e07ed86613bf6335e3f5193fc4d2e091ad6ca4903dd9bd602450a5c9511dc4e7
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8023d1c07aec616d68ceac23c96f3f4da59687391bed340445f2adc640134f25
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -80,3 +80,42 @@
80
  {"current_steps": 780, "total_steps": 1170, "eval_loss": 0.5533561706542969, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:30:41", "remaining_time": "0:45:20"}
81
  {"current_steps": 790, "total_steps": 1170, "loss": 0.4847, "learning_rate": 5e-06, "epoch": 2.0256410256410255, "percentage": 67.52, "elapsed_time": "1:35:34", "remaining_time": "0:45:58"}
82
  {"current_steps": 800, "total_steps": 1170, "loss": 0.4906, "learning_rate": 5e-06, "epoch": 2.051282051282051, "percentage": 68.38, "elapsed_time": "1:36:39", "remaining_time": "0:44:42"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  {"current_steps": 780, "total_steps": 1170, "eval_loss": 0.5533561706542969, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:30:41", "remaining_time": "0:45:20"}
81
  {"current_steps": 790, "total_steps": 1170, "loss": 0.4847, "learning_rate": 5e-06, "epoch": 2.0256410256410255, "percentage": 67.52, "elapsed_time": "1:35:34", "remaining_time": "0:45:58"}
82
  {"current_steps": 800, "total_steps": 1170, "loss": 0.4906, "learning_rate": 5e-06, "epoch": 2.051282051282051, "percentage": 68.38, "elapsed_time": "1:36:39", "remaining_time": "0:44:42"}
83
+ {"current_steps": 810, "total_steps": 1170, "loss": 0.4857, "learning_rate": 5e-06, "epoch": 2.076923076923077, "percentage": 69.23, "elapsed_time": "1:37:44", "remaining_time": "0:43:26"}
84
+ {"current_steps": 820, "total_steps": 1170, "loss": 0.4861, "learning_rate": 5e-06, "epoch": 2.1025641025641026, "percentage": 70.09, "elapsed_time": "1:38:49", "remaining_time": "0:42:10"}
85
+ {"current_steps": 830, "total_steps": 1170, "loss": 0.4847, "learning_rate": 5e-06, "epoch": 2.128205128205128, "percentage": 70.94, "elapsed_time": "1:39:54", "remaining_time": "0:40:55"}
86
+ {"current_steps": 840, "total_steps": 1170, "loss": 0.4895, "learning_rate": 5e-06, "epoch": 2.1538461538461537, "percentage": 71.79, "elapsed_time": "1:41:00", "remaining_time": "0:39:41"}
87
+ {"current_steps": 850, "total_steps": 1170, "loss": 0.4897, "learning_rate": 5e-06, "epoch": 2.1794871794871793, "percentage": 72.65, "elapsed_time": "1:42:06", "remaining_time": "0:38:26"}
88
+ {"current_steps": 860, "total_steps": 1170, "loss": 0.4861, "learning_rate": 5e-06, "epoch": 2.2051282051282053, "percentage": 73.5, "elapsed_time": "1:43:12", "remaining_time": "0:37:12"}
89
+ {"current_steps": 870, "total_steps": 1170, "loss": 0.484, "learning_rate": 5e-06, "epoch": 2.230769230769231, "percentage": 74.36, "elapsed_time": "1:44:18", "remaining_time": "0:35:58"}
90
+ {"current_steps": 880, "total_steps": 1170, "loss": 0.4936, "learning_rate": 5e-06, "epoch": 2.2564102564102564, "percentage": 75.21, "elapsed_time": "1:45:24", "remaining_time": "0:34:44"}
91
+ {"current_steps": 890, "total_steps": 1170, "loss": 0.4915, "learning_rate": 5e-06, "epoch": 2.282051282051282, "percentage": 76.07, "elapsed_time": "1:46:29", "remaining_time": "0:33:30"}
92
+ {"current_steps": 900, "total_steps": 1170, "loss": 0.4894, "learning_rate": 5e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "1:47:35", "remaining_time": "0:32:16"}
93
+ {"current_steps": 910, "total_steps": 1170, "loss": 0.4873, "learning_rate": 5e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "1:48:41", "remaining_time": "0:31:03"}
94
+ {"current_steps": 920, "total_steps": 1170, "loss": 0.4882, "learning_rate": 5e-06, "epoch": 2.358974358974359, "percentage": 78.63, "elapsed_time": "1:49:47", "remaining_time": "0:29:50"}
95
+ {"current_steps": 930, "total_steps": 1170, "loss": 0.486, "learning_rate": 5e-06, "epoch": 2.3846153846153846, "percentage": 79.49, "elapsed_time": "1:50:53", "remaining_time": "0:28:37"}
96
+ {"current_steps": 940, "total_steps": 1170, "loss": 0.4963, "learning_rate": 5e-06, "epoch": 2.41025641025641, "percentage": 80.34, "elapsed_time": "1:51:59", "remaining_time": "0:27:24"}
97
+ {"current_steps": 950, "total_steps": 1170, "loss": 0.4855, "learning_rate": 5e-06, "epoch": 2.435897435897436, "percentage": 81.2, "elapsed_time": "1:53:05", "remaining_time": "0:26:11"}
98
+ {"current_steps": 960, "total_steps": 1170, "loss": 0.4859, "learning_rate": 5e-06, "epoch": 2.4615384615384617, "percentage": 82.05, "elapsed_time": "1:54:11", "remaining_time": "0:24:58"}
99
+ {"current_steps": 970, "total_steps": 1170, "loss": 0.4884, "learning_rate": 5e-06, "epoch": 2.4871794871794872, "percentage": 82.91, "elapsed_time": "1:55:17", "remaining_time": "0:23:46"}
100
+ {"current_steps": 980, "total_steps": 1170, "loss": 0.4858, "learning_rate": 5e-06, "epoch": 2.5128205128205128, "percentage": 83.76, "elapsed_time": "1:56:22", "remaining_time": "0:22:33"}
101
+ {"current_steps": 990, "total_steps": 1170, "loss": 0.4864, "learning_rate": 5e-06, "epoch": 2.5384615384615383, "percentage": 84.62, "elapsed_time": "1:57:27", "remaining_time": "0:21:21"}
102
+ {"current_steps": 1000, "total_steps": 1170, "loss": 0.4859, "learning_rate": 5e-06, "epoch": 2.564102564102564, "percentage": 85.47, "elapsed_time": "1:58:33", "remaining_time": "0:20:09"}
103
+ {"current_steps": 1010, "total_steps": 1170, "loss": 0.4867, "learning_rate": 5e-06, "epoch": 2.58974358974359, "percentage": 86.32, "elapsed_time": "1:59:38", "remaining_time": "0:18:57"}
104
+ {"current_steps": 1020, "total_steps": 1170, "loss": 0.4921, "learning_rate": 5e-06, "epoch": 2.6153846153846154, "percentage": 87.18, "elapsed_time": "2:00:44", "remaining_time": "0:17:45"}
105
+ {"current_steps": 1030, "total_steps": 1170, "loss": 0.4898, "learning_rate": 5e-06, "epoch": 2.641025641025641, "percentage": 88.03, "elapsed_time": "2:01:49", "remaining_time": "0:16:33"}
106
+ {"current_steps": 1040, "total_steps": 1170, "loss": 0.487, "learning_rate": 5e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "2:02:55", "remaining_time": "0:15:21"}
107
+ {"current_steps": 1050, "total_steps": 1170, "loss": 0.4896, "learning_rate": 5e-06, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "2:04:00", "remaining_time": "0:14:10"}
108
+ {"current_steps": 1060, "total_steps": 1170, "loss": 0.4883, "learning_rate": 5e-06, "epoch": 2.717948717948718, "percentage": 90.6, "elapsed_time": "2:05:06", "remaining_time": "0:12:58"}
109
+ {"current_steps": 1070, "total_steps": 1170, "loss": 0.4895, "learning_rate": 5e-06, "epoch": 2.7435897435897436, "percentage": 91.45, "elapsed_time": "2:06:13", "remaining_time": "0:11:47"}
110
+ {"current_steps": 1080, "total_steps": 1170, "loss": 0.4854, "learning_rate": 5e-06, "epoch": 2.769230769230769, "percentage": 92.31, "elapsed_time": "2:07:18", "remaining_time": "0:10:36"}
111
+ {"current_steps": 1090, "total_steps": 1170, "loss": 0.4929, "learning_rate": 5e-06, "epoch": 2.7948717948717947, "percentage": 93.16, "elapsed_time": "2:08:24", "remaining_time": "0:09:25"}
112
+ {"current_steps": 1100, "total_steps": 1170, "loss": 0.4847, "learning_rate": 5e-06, "epoch": 2.8205128205128203, "percentage": 94.02, "elapsed_time": "2:09:30", "remaining_time": "0:08:14"}
113
+ {"current_steps": 1110, "total_steps": 1170, "loss": 0.4824, "learning_rate": 5e-06, "epoch": 2.8461538461538463, "percentage": 94.87, "elapsed_time": "2:10:36", "remaining_time": "0:07:03"}
114
+ {"current_steps": 1120, "total_steps": 1170, "loss": 0.4843, "learning_rate": 5e-06, "epoch": 2.871794871794872, "percentage": 95.73, "elapsed_time": "2:11:42", "remaining_time": "0:05:52"}
115
+ {"current_steps": 1130, "total_steps": 1170, "loss": 0.4822, "learning_rate": 5e-06, "epoch": 2.8974358974358974, "percentage": 96.58, "elapsed_time": "2:12:47", "remaining_time": "0:04:42"}
116
+ {"current_steps": 1140, "total_steps": 1170, "loss": 0.4856, "learning_rate": 5e-06, "epoch": 2.9230769230769234, "percentage": 97.44, "elapsed_time": "2:13:53", "remaining_time": "0:03:31"}
117
+ {"current_steps": 1150, "total_steps": 1170, "loss": 0.4888, "learning_rate": 5e-06, "epoch": 2.948717948717949, "percentage": 98.29, "elapsed_time": "2:14:59", "remaining_time": "0:02:20"}
118
+ {"current_steps": 1160, "total_steps": 1170, "loss": 0.4913, "learning_rate": 5e-06, "epoch": 2.9743589743589745, "percentage": 99.15, "elapsed_time": "2:16:05", "remaining_time": "0:01:10"}
119
+ {"current_steps": 1170, "total_steps": 1170, "loss": 0.4851, "learning_rate": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:17:10", "remaining_time": "0:00:00"}
120
+ {"current_steps": 1170, "total_steps": 1170, "eval_loss": 0.5471954345703125, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:21:33", "remaining_time": "0:00:00"}
121
+ {"current_steps": 1170, "total_steps": 1170, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:25:07", "remaining_time": "0:00:00"}