Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_dcft_v1_wo_alpaca_threshold90_it

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
gsmyrnis commited on
Commit
403ceb0
·
verified ·
1 Parent(s): 5314ba0

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 sha256:63115591d1dcab868b0f4a7ca8560862e3b97be42e476adb45b35b59172e9e89
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2983d9c90bbd2e0a57cfdbec459a3fb7f4b08537214fbfc65ead491466218a
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:ac23679a8a9e60ba58c56e8a0eecdaa697c63cdf8889039fb940a5d06ae0cbe6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a05e68f2dc0c9c988aac9b28649b8d58f653471c22a5fd9c758210fe30f853
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:c7c4d5a271b775e49974806614e9aa83f4f0340a33d8e50c0545c5ec9842eec0
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a17e55dd3e3718b172c8d454a0c0c1a778b13f3927442ab292d00c18e48db0a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42cd54f7fa07a64717be39d36e7d981685ffb209ad37620c7b28bac239f8556f
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da1bf6ebec3fa71c684c87ed808588de8e5d64e3cf1e93ce725edf0a71409e1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -81,3 +81,42 @@
81
  {"current_steps": 790, "total_steps": 1182, "loss": 0.5004, "learning_rate": 5e-06, "epoch": 2.00507614213198, "percentage": 66.84, "elapsed_time": "1:31:34", "remaining_time": "0:45:26"}
82
  {"current_steps": 800, "total_steps": 1182, "loss": 0.4726, "learning_rate": 5e-06, "epoch": 2.030456852791878, "percentage": 67.68, "elapsed_time": "1:32:36", "remaining_time": "0:44:13"}
83
  {"current_steps": 810, "total_steps": 1182, "loss": 0.4689, "learning_rate": 5e-06, "epoch": 2.0558375634517767, "percentage": 68.53, "elapsed_time": "1:33:38", "remaining_time": "0:43:00"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81
  {"current_steps": 790, "total_steps": 1182, "loss": 0.5004, "learning_rate": 5e-06, "epoch": 2.00507614213198, "percentage": 66.84, "elapsed_time": "1:31:34", "remaining_time": "0:45:26"}
82
  {"current_steps": 800, "total_steps": 1182, "loss": 0.4726, "learning_rate": 5e-06, "epoch": 2.030456852791878, "percentage": 67.68, "elapsed_time": "1:32:36", "remaining_time": "0:44:13"}
83
  {"current_steps": 810, "total_steps": 1182, "loss": 0.4689, "learning_rate": 5e-06, "epoch": 2.0558375634517767, "percentage": 68.53, "elapsed_time": "1:33:38", "remaining_time": "0:43:00"}
84
+ {"current_steps": 820, "total_steps": 1182, "loss": 0.4679, "learning_rate": 5e-06, "epoch": 2.081218274111675, "percentage": 69.37, "elapsed_time": "1:34:41", "remaining_time": "0:41:48"}
85
+ {"current_steps": 830, "total_steps": 1182, "loss": 0.4735, "learning_rate": 5e-06, "epoch": 2.1065989847715736, "percentage": 70.22, "elapsed_time": "1:35:44", "remaining_time": "0:40:36"}
86
+ {"current_steps": 840, "total_steps": 1182, "loss": 0.465, "learning_rate": 5e-06, "epoch": 2.1319796954314723, "percentage": 71.07, "elapsed_time": "1:36:47", "remaining_time": "0:39:24"}
87
+ {"current_steps": 850, "total_steps": 1182, "loss": 0.4662, "learning_rate": 5e-06, "epoch": 2.1573604060913705, "percentage": 71.91, "elapsed_time": "1:37:49", "remaining_time": "0:38:12"}
88
+ {"current_steps": 860, "total_steps": 1182, "loss": 0.4681, "learning_rate": 5e-06, "epoch": 2.182741116751269, "percentage": 72.76, "elapsed_time": "1:38:51", "remaining_time": "0:37:01"}
89
+ {"current_steps": 870, "total_steps": 1182, "loss": 0.4711, "learning_rate": 5e-06, "epoch": 2.2081218274111674, "percentage": 73.6, "elapsed_time": "1:39:54", "remaining_time": "0:35:49"}
90
+ {"current_steps": 880, "total_steps": 1182, "loss": 0.4757, "learning_rate": 5e-06, "epoch": 2.233502538071066, "percentage": 74.45, "elapsed_time": "1:40:56", "remaining_time": "0:34:38"}
91
+ {"current_steps": 890, "total_steps": 1182, "loss": 0.4691, "learning_rate": 5e-06, "epoch": 2.2588832487309647, "percentage": 75.3, "elapsed_time": "1:41:59", "remaining_time": "0:33:27"}
92
+ {"current_steps": 900, "total_steps": 1182, "loss": 0.4696, "learning_rate": 5e-06, "epoch": 2.284263959390863, "percentage": 76.14, "elapsed_time": "1:43:01", "remaining_time": "0:32:16"}
93
+ {"current_steps": 910, "total_steps": 1182, "loss": 0.4685, "learning_rate": 5e-06, "epoch": 2.3096446700507616, "percentage": 76.99, "elapsed_time": "1:44:04", "remaining_time": "0:31:06"}
94
+ {"current_steps": 920, "total_steps": 1182, "loss": 0.4737, "learning_rate": 5e-06, "epoch": 2.33502538071066, "percentage": 77.83, "elapsed_time": "1:45:06", "remaining_time": "0:29:56"}
95
+ {"current_steps": 930, "total_steps": 1182, "loss": 0.4637, "learning_rate": 5e-06, "epoch": 2.3604060913705585, "percentage": 78.68, "elapsed_time": "1:46:09", "remaining_time": "0:28:46"}
96
+ {"current_steps": 940, "total_steps": 1182, "loss": 0.4708, "learning_rate": 5e-06, "epoch": 2.3857868020304567, "percentage": 79.53, "elapsed_time": "1:47:12", "remaining_time": "0:27:35"}
97
+ {"current_steps": 950, "total_steps": 1182, "loss": 0.4673, "learning_rate": 5e-06, "epoch": 2.4111675126903553, "percentage": 80.37, "elapsed_time": "1:48:14", "remaining_time": "0:26:26"}
98
+ {"current_steps": 960, "total_steps": 1182, "loss": 0.4728, "learning_rate": 5e-06, "epoch": 2.436548223350254, "percentage": 81.22, "elapsed_time": "1:49:17", "remaining_time": "0:25:16"}
99
+ {"current_steps": 970, "total_steps": 1182, "loss": 0.4657, "learning_rate": 5e-06, "epoch": 2.4619289340101522, "percentage": 82.06, "elapsed_time": "1:50:19", "remaining_time": "0:24:06"}
100
+ {"current_steps": 980, "total_steps": 1182, "loss": 0.4705, "learning_rate": 5e-06, "epoch": 2.487309644670051, "percentage": 82.91, "elapsed_time": "1:51:21", "remaining_time": "0:22:57"}
101
+ {"current_steps": 990, "total_steps": 1182, "loss": 0.4703, "learning_rate": 5e-06, "epoch": 2.512690355329949, "percentage": 83.76, "elapsed_time": "1:52:24", "remaining_time": "0:21:47"}
102
+ {"current_steps": 1000, "total_steps": 1182, "loss": 0.4701, "learning_rate": 5e-06, "epoch": 2.5380710659898478, "percentage": 84.6, "elapsed_time": "1:53:26", "remaining_time": "0:20:38"}
103
+ {"current_steps": 1010, "total_steps": 1182, "loss": 0.4671, "learning_rate": 5e-06, "epoch": 2.563451776649746, "percentage": 85.45, "elapsed_time": "1:54:29", "remaining_time": "0:19:29"}
104
+ {"current_steps": 1020, "total_steps": 1182, "loss": 0.4652, "learning_rate": 5e-06, "epoch": 2.5888324873096447, "percentage": 86.29, "elapsed_time": "1:55:31", "remaining_time": "0:18:20"}
105
+ {"current_steps": 1030, "total_steps": 1182, "loss": 0.472, "learning_rate": 5e-06, "epoch": 2.6142131979695433, "percentage": 87.14, "elapsed_time": "1:56:34", "remaining_time": "0:17:12"}
106
+ {"current_steps": 1040, "total_steps": 1182, "loss": 0.46, "learning_rate": 5e-06, "epoch": 2.6395939086294415, "percentage": 87.99, "elapsed_time": "1:57:36", "remaining_time": "0:16:03"}
107
+ {"current_steps": 1050, "total_steps": 1182, "loss": 0.4699, "learning_rate": 5e-06, "epoch": 2.66497461928934, "percentage": 88.83, "elapsed_time": "1:58:39", "remaining_time": "0:14:54"}
108
+ {"current_steps": 1060, "total_steps": 1182, "loss": 0.4718, "learning_rate": 5e-06, "epoch": 2.6903553299492384, "percentage": 89.68, "elapsed_time": "1:59:41", "remaining_time": "0:13:46"}
109
+ {"current_steps": 1070, "total_steps": 1182, "loss": 0.4703, "learning_rate": 5e-06, "epoch": 2.715736040609137, "percentage": 90.52, "elapsed_time": "2:00:44", "remaining_time": "0:12:38"}
110
+ {"current_steps": 1080, "total_steps": 1182, "loss": 0.4673, "learning_rate": 5e-06, "epoch": 2.7411167512690353, "percentage": 91.37, "elapsed_time": "2:01:46", "remaining_time": "0:11:30"}
111
+ {"current_steps": 1090, "total_steps": 1182, "loss": 0.466, "learning_rate": 5e-06, "epoch": 2.766497461928934, "percentage": 92.22, "elapsed_time": "2:02:49", "remaining_time": "0:10:21"}
112
+ {"current_steps": 1100, "total_steps": 1182, "loss": 0.4675, "learning_rate": 5e-06, "epoch": 2.7918781725888326, "percentage": 93.06, "elapsed_time": "2:03:52", "remaining_time": "0:09:14"}
113
+ {"current_steps": 1110, "total_steps": 1182, "loss": 0.466, "learning_rate": 5e-06, "epoch": 2.817258883248731, "percentage": 93.91, "elapsed_time": "2:04:55", "remaining_time": "0:08:06"}
114
+ {"current_steps": 1120, "total_steps": 1182, "loss": 0.4681, "learning_rate": 5e-06, "epoch": 2.8426395939086295, "percentage": 94.75, "elapsed_time": "2:05:57", "remaining_time": "0:06:58"}
115
+ {"current_steps": 1130, "total_steps": 1182, "loss": 0.4705, "learning_rate": 5e-06, "epoch": 2.868020304568528, "percentage": 95.6, "elapsed_time": "2:07:00", "remaining_time": "0:05:50"}
116
+ {"current_steps": 1140, "total_steps": 1182, "loss": 0.4709, "learning_rate": 5e-06, "epoch": 2.8934010152284264, "percentage": 96.45, "elapsed_time": "2:08:03", "remaining_time": "0:04:43"}
117
+ {"current_steps": 1150, "total_steps": 1182, "loss": 0.4726, "learning_rate": 5e-06, "epoch": 2.9187817258883246, "percentage": 97.29, "elapsed_time": "2:09:05", "remaining_time": "0:03:35"}
118
+ {"current_steps": 1160, "total_steps": 1182, "loss": 0.4622, "learning_rate": 5e-06, "epoch": 2.9441624365482233, "percentage": 98.14, "elapsed_time": "2:10:08", "remaining_time": "0:02:28"}
119
+ {"current_steps": 1170, "total_steps": 1182, "loss": 0.4724, "learning_rate": 5e-06, "epoch": 2.969543147208122, "percentage": 98.98, "elapsed_time": "2:11:10", "remaining_time": "0:01:20"}
120
+ {"current_steps": 1180, "total_steps": 1182, "loss": 0.4704, "learning_rate": 5e-06, "epoch": 2.99492385786802, "percentage": 99.83, "elapsed_time": "2:12:12", "remaining_time": "0:00:13"}
121
+ {"current_steps": 1182, "total_steps": 1182, "eval_loss": 0.5297877788543701, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:17:05", "remaining_time": "0:00:00"}
122
+ {"current_steps": 1182, "total_steps": 1182, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:20:39", "remaining_time": "0:00:00"}