Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_baseline_dcft_oh_v3

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
gsmyrnis commited on
Commit
e6f15ff
·
verified ·
1 Parent(s): b8e4b92

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 +41 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36c39236718e043836bdf6e12e2354bedfb10c9b5b756600b05111517fe92460
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd41fe622d3a440fadab27aa6a279944d122818af429527a7115a11d9d6d8cc3
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f3461dbb7accc48351fd4fe9350d4ff8750256f7ed65a835d08880502faf2e0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194beca1fe970e150904b314e13b41c54656a7f222cd3ef0802692585594a23d
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:ce8e8700129f300b9461b23f70b9746575e582f89e439e0596ea3c7ce1481fe0
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618006f9ac3aa64349d640c367b7b287fef960a6fe8732585313f612198b8e6a
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:de233b15c15e9f19eaf8debb7c0f983200f967290b360fee1a53058117724a17
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0097ea7e9e448f4ed09598b3474e8ea1e01d0688ce96daaaaf2d3c338bb1396b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -87,3 +87,44 @@
87
  {"current_steps": 850, "total_steps": 1269, "loss": 0.5878, "learning_rate": 5e-06, "epoch": 2.0094562647754137, "percentage": 66.98, "elapsed_time": "1:37:55", "remaining_time": "0:48:16"}
88
  {"current_steps": 860, "total_steps": 1269, "loss": 0.5595, "learning_rate": 5e-06, "epoch": 2.033096926713948, "percentage": 67.77, "elapsed_time": "1:38:57", "remaining_time": "0:47:03"}
89
  {"current_steps": 870, "total_steps": 1269, "loss": 0.5664, "learning_rate": 5e-06, "epoch": 2.0567375886524824, "percentage": 68.56, "elapsed_time": "1:40:00", "remaining_time": "0:45:51"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 850, "total_steps": 1269, "loss": 0.5878, "learning_rate": 5e-06, "epoch": 2.0094562647754137, "percentage": 66.98, "elapsed_time": "1:37:55", "remaining_time": "0:48:16"}
88
  {"current_steps": 860, "total_steps": 1269, "loss": 0.5595, "learning_rate": 5e-06, "epoch": 2.033096926713948, "percentage": 67.77, "elapsed_time": "1:38:57", "remaining_time": "0:47:03"}
89
  {"current_steps": 870, "total_steps": 1269, "loss": 0.5664, "learning_rate": 5e-06, "epoch": 2.0567375886524824, "percentage": 68.56, "elapsed_time": "1:40:00", "remaining_time": "0:45:51"}
90
+ {"current_steps": 880, "total_steps": 1269, "loss": 0.5594, "learning_rate": 5e-06, "epoch": 2.0803782505910164, "percentage": 69.35, "elapsed_time": "1:41:02", "remaining_time": "0:44:40"}
91
+ {"current_steps": 890, "total_steps": 1269, "loss": 0.5666, "learning_rate": 5e-06, "epoch": 2.104018912529551, "percentage": 70.13, "elapsed_time": "1:42:05", "remaining_time": "0:43:28"}
92
+ {"current_steps": 900, "total_steps": 1269, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.127659574468085, "percentage": 70.92, "elapsed_time": "1:43:08", "remaining_time": "0:42:17"}
93
+ {"current_steps": 910, "total_steps": 1269, "loss": 0.5712, "learning_rate": 5e-06, "epoch": 2.1513002364066196, "percentage": 71.71, "elapsed_time": "1:44:13", "remaining_time": "0:41:06"}
94
+ {"current_steps": 920, "total_steps": 1269, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.1749408983451537, "percentage": 72.5, "elapsed_time": "1:45:16", "remaining_time": "0:39:56"}
95
+ {"current_steps": 930, "total_steps": 1269, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.198581560283688, "percentage": 73.29, "elapsed_time": "1:46:19", "remaining_time": "0:38:45"}
96
+ {"current_steps": 940, "total_steps": 1269, "loss": 0.565, "learning_rate": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "1:47:23", "remaining_time": "0:37:35"}
97
+ {"current_steps": 950, "total_steps": 1269, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.2458628841607564, "percentage": 74.86, "elapsed_time": "1:48:28", "remaining_time": "0:36:25"}
98
+ {"current_steps": 960, "total_steps": 1269, "loss": 0.567, "learning_rate": 5e-06, "epoch": 2.269503546099291, "percentage": 75.65, "elapsed_time": "1:49:34", "remaining_time": "0:35:16"}
99
+ {"current_steps": 970, "total_steps": 1269, "loss": 0.5755, "learning_rate": 5e-06, "epoch": 2.293144208037825, "percentage": 76.44, "elapsed_time": "1:50:40", "remaining_time": "0:34:06"}
100
+ {"current_steps": 980, "total_steps": 1269, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.3167848699763596, "percentage": 77.23, "elapsed_time": "1:51:44", "remaining_time": "0:32:57"}
101
+ {"current_steps": 990, "total_steps": 1269, "loss": 0.5641, "learning_rate": 5e-06, "epoch": 2.3404255319148937, "percentage": 78.01, "elapsed_time": "1:52:46", "remaining_time": "0:31:47"}
102
+ {"current_steps": 1000, "total_steps": 1269, "loss": 0.5632, "learning_rate": 5e-06, "epoch": 2.3640661938534278, "percentage": 78.8, "elapsed_time": "1:53:49", "remaining_time": "0:30:37"}
103
+ {"current_steps": 1010, "total_steps": 1269, "loss": 0.5652, "learning_rate": 5e-06, "epoch": 2.3877068557919623, "percentage": 79.59, "elapsed_time": "1:54:52", "remaining_time": "0:29:27"}
104
+ {"current_steps": 1020, "total_steps": 1269, "loss": 0.5739, "learning_rate": 5e-06, "epoch": 2.4113475177304964, "percentage": 80.38, "elapsed_time": "1:55:55", "remaining_time": "0:28:17"}
105
+ {"current_steps": 1030, "total_steps": 1269, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.434988179669031, "percentage": 81.17, "elapsed_time": "1:56:58", "remaining_time": "0:27:08"}
106
+ {"current_steps": 1040, "total_steps": 1269, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.458628841607565, "percentage": 81.95, "elapsed_time": "1:58:00", "remaining_time": "0:25:59"}
107
+ {"current_steps": 1050, "total_steps": 1269, "loss": 0.5667, "learning_rate": 5e-06, "epoch": 2.482269503546099, "percentage": 82.74, "elapsed_time": "1:59:03", "remaining_time": "0:24:49"}
108
+ {"current_steps": 1060, "total_steps": 1269, "loss": 0.5715, "learning_rate": 5e-06, "epoch": 2.5059101654846336, "percentage": 83.53, "elapsed_time": "2:00:06", "remaining_time": "0:23:40"}
109
+ {"current_steps": 1070, "total_steps": 1269, "loss": 0.5596, "learning_rate": 5e-06, "epoch": 2.5295508274231677, "percentage": 84.32, "elapsed_time": "2:01:10", "remaining_time": "0:22:32"}
110
+ {"current_steps": 1080, "total_steps": 1269, "loss": 0.5704, "learning_rate": 5e-06, "epoch": 2.5531914893617023, "percentage": 85.11, "elapsed_time": "2:02:15", "remaining_time": "0:21:23"}
111
+ {"current_steps": 1090, "total_steps": 1269, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.5768321513002364, "percentage": 85.89, "elapsed_time": "2:03:20", "remaining_time": "0:20:15"}
112
+ {"current_steps": 1100, "total_steps": 1269, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.6004728132387704, "percentage": 86.68, "elapsed_time": "2:04:23", "remaining_time": "0:19:06"}
113
+ {"current_steps": 1110, "total_steps": 1269, "loss": 0.5742, "learning_rate": 5e-06, "epoch": 2.624113475177305, "percentage": 87.47, "elapsed_time": "2:05:25", "remaining_time": "0:17:57"}
114
+ {"current_steps": 1120, "total_steps": 1269, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.6477541371158395, "percentage": 88.26, "elapsed_time": "2:06:28", "remaining_time": "0:16:49"}
115
+ {"current_steps": 1130, "total_steps": 1269, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.6713947990543736, "percentage": 89.05, "elapsed_time": "2:07:30", "remaining_time": "0:15:41"}
116
+ {"current_steps": 1140, "total_steps": 1269, "loss": 0.5675, "learning_rate": 5e-06, "epoch": 2.6950354609929077, "percentage": 89.83, "elapsed_time": "2:08:33", "remaining_time": "0:14:32"}
117
+ {"current_steps": 1150, "total_steps": 1269, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.7186761229314422, "percentage": 90.62, "elapsed_time": "2:09:36", "remaining_time": "0:13:24"}
118
+ {"current_steps": 1160, "total_steps": 1269, "loss": 0.5712, "learning_rate": 5e-06, "epoch": 2.7423167848699763, "percentage": 91.41, "elapsed_time": "2:10:39", "remaining_time": "0:12:16"}
119
+ {"current_steps": 1170, "total_steps": 1269, "loss": 0.5661, "learning_rate": 5e-06, "epoch": 2.7659574468085104, "percentage": 92.2, "elapsed_time": "2:11:42", "remaining_time": "0:11:08"}
120
+ {"current_steps": 1180, "total_steps": 1269, "loss": 0.573, "learning_rate": 5e-06, "epoch": 2.789598108747045, "percentage": 92.99, "elapsed_time": "2:12:45", "remaining_time": "0:10:00"}
121
+ {"current_steps": 1190, "total_steps": 1269, "loss": 0.5717, "learning_rate": 5e-06, "epoch": 2.813238770685579, "percentage": 93.77, "elapsed_time": "2:13:49", "remaining_time": "0:08:53"}
122
+ {"current_steps": 1200, "total_steps": 1269, "loss": 0.5619, "learning_rate": 5e-06, "epoch": 2.8368794326241136, "percentage": 94.56, "elapsed_time": "2:14:54", "remaining_time": "0:07:45"}
123
+ {"current_steps": 1210, "total_steps": 1269, "loss": 0.5699, "learning_rate": 5e-06, "epoch": 2.8605200945626477, "percentage": 95.35, "elapsed_time": "2:16:00", "remaining_time": "0:06:37"}
124
+ {"current_steps": 1220, "total_steps": 1269, "loss": 0.5725, "learning_rate": 5e-06, "epoch": 2.884160756501182, "percentage": 96.14, "elapsed_time": "2:17:06", "remaining_time": "0:05:30"}
125
+ {"current_steps": 1230, "total_steps": 1269, "loss": 0.5685, "learning_rate": 5e-06, "epoch": 2.9078014184397163, "percentage": 96.93, "elapsed_time": "2:18:13", "remaining_time": "0:04:22"}
126
+ {"current_steps": 1240, "total_steps": 1269, "loss": 0.5696, "learning_rate": 5e-06, "epoch": 2.9314420803782504, "percentage": 97.71, "elapsed_time": "2:19:19", "remaining_time": "0:03:15"}
127
+ {"current_steps": 1250, "total_steps": 1269, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.955082742316785, "percentage": 98.5, "elapsed_time": "2:20:23", "remaining_time": "0:02:08"}
128
+ {"current_steps": 1260, "total_steps": 1269, "loss": 0.5839, "learning_rate": 5e-06, "epoch": 2.978723404255319, "percentage": 99.29, "elapsed_time": "2:21:26", "remaining_time": "0:01:00"}
129
+ {"current_steps": 1269, "total_steps": 1269, "eval_loss": 0.6423146724700928, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:27:06", "remaining_time": "0:00:00"}
130
+ {"current_steps": 1269, "total_steps": 1269, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:30:25", "remaining_time": "0:00:00"}