Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_v3.1_wo_collective_cognition

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
gsmyrnis commited on
Commit
3a1d39d
·
verified ·
1 Parent(s): c55d8ef

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 sha256:03c10999657a9ebca9970d00c226bf803f9b69b3511221b13a824ca0cb2c89de
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9691538d39b10a4c47670be01f54be18d85cf4010789597dad7c74ba0bbd320
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:837cc5b31c5079dd124f305e6f1bdd7fe10c0e4cae7aaa9076522f746f89bdad
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ceb7404b6d1b860e606f117de544bd3df1a3824a33cb83e62c6a7823c331c2
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:a010c371a72d3c3ce86baed19b9345276c69fcb76bd6f8821b6492b90715f428
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8fd4c4ddb993f919743283fa7b28ff1099aa8e0ac6c8b543d84ce5fa9e5a30
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d3774887b1a893df40838e9882d426da2253be25b3cdec1134cc33faf08ae2a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977a613be2b9c85096b23d531ae349a97a8092cd8ab01b2bcbd2d8e2606841f3
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -87,3 +87,44 @@
87
  {"current_steps": 850, "total_steps": 1269, "loss": 0.5868, "learning_rate": 5e-06, "epoch": 2.0094562647754137, "percentage": 66.98, "elapsed_time": "1:26:30", "remaining_time": "0:42:38"}
88
  {"current_steps": 860, "total_steps": 1269, "loss": 0.5582, "learning_rate": 5e-06, "epoch": 2.033096926713948, "percentage": 67.77, "elapsed_time": "1:27:28", "remaining_time": "0:41:35"}
89
  {"current_steps": 870, "total_steps": 1269, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 2.0567375886524824, "percentage": 68.56, "elapsed_time": "1:28:26", "remaining_time": "0:40:33"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 850, "total_steps": 1269, "loss": 0.5868, "learning_rate": 5e-06, "epoch": 2.0094562647754137, "percentage": 66.98, "elapsed_time": "1:26:30", "remaining_time": "0:42:38"}
88
  {"current_steps": 860, "total_steps": 1269, "loss": 0.5582, "learning_rate": 5e-06, "epoch": 2.033096926713948, "percentage": 67.77, "elapsed_time": "1:27:28", "remaining_time": "0:41:35"}
89
  {"current_steps": 870, "total_steps": 1269, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 2.0567375886524824, "percentage": 68.56, "elapsed_time": "1:28:26", "remaining_time": "0:40:33"}
90
+ {"current_steps": 880, "total_steps": 1269, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 2.0803782505910164, "percentage": 69.35, "elapsed_time": "1:29:24", "remaining_time": "0:39:31"}
91
+ {"current_steps": 890, "total_steps": 1269, "loss": 0.562, "learning_rate": 5e-06, "epoch": 2.104018912529551, "percentage": 70.13, "elapsed_time": "1:30:21", "remaining_time": "0:38:28"}
92
+ {"current_steps": 900, "total_steps": 1269, "loss": 0.5611, "learning_rate": 5e-06, "epoch": 2.127659574468085, "percentage": 70.92, "elapsed_time": "1:31:19", "remaining_time": "0:37:26"}
93
+ {"current_steps": 910, "total_steps": 1269, "loss": 0.562, "learning_rate": 5e-06, "epoch": 2.1513002364066196, "percentage": 71.71, "elapsed_time": "1:32:17", "remaining_time": "0:36:24"}
94
+ {"current_steps": 920, "total_steps": 1269, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.1749408983451537, "percentage": 72.5, "elapsed_time": "1:33:15", "remaining_time": "0:35:22"}
95
+ {"current_steps": 930, "total_steps": 1269, "loss": 0.5634, "learning_rate": 5e-06, "epoch": 2.198581560283688, "percentage": 73.29, "elapsed_time": "1:34:13", "remaining_time": "0:34:20"}
96
+ {"current_steps": 940, "total_steps": 1269, "loss": 0.5634, "learning_rate": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "1:35:11", "remaining_time": "0:33:19"}
97
+ {"current_steps": 950, "total_steps": 1269, "loss": 0.566, "learning_rate": 5e-06, "epoch": 2.2458628841607564, "percentage": 74.86, "elapsed_time": "1:36:09", "remaining_time": "0:32:17"}
98
+ {"current_steps": 960, "total_steps": 1269, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.269503546099291, "percentage": 75.65, "elapsed_time": "1:37:07", "remaining_time": "0:31:15"}
99
+ {"current_steps": 970, "total_steps": 1269, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.293144208037825, "percentage": 76.44, "elapsed_time": "1:38:05", "remaining_time": "0:30:14"}
100
+ {"current_steps": 980, "total_steps": 1269, "loss": 0.5661, "learning_rate": 5e-06, "epoch": 2.3167848699763596, "percentage": 77.23, "elapsed_time": "1:39:03", "remaining_time": "0:29:12"}
101
+ {"current_steps": 990, "total_steps": 1269, "loss": 0.5656, "learning_rate": 5e-06, "epoch": 2.3404255319148937, "percentage": 78.01, "elapsed_time": "1:40:00", "remaining_time": "0:28:11"}
102
+ {"current_steps": 1000, "total_steps": 1269, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.3640661938534278, "percentage": 78.8, "elapsed_time": "1:40:58", "remaining_time": "0:27:09"}
103
+ {"current_steps": 1010, "total_steps": 1269, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.3877068557919623, "percentage": 79.59, "elapsed_time": "1:41:56", "remaining_time": "0:26:08"}
104
+ {"current_steps": 1020, "total_steps": 1269, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.4113475177304964, "percentage": 80.38, "elapsed_time": "1:42:54", "remaining_time": "0:25:07"}
105
+ {"current_steps": 1030, "total_steps": 1269, "loss": 0.5667, "learning_rate": 5e-06, "epoch": 2.434988179669031, "percentage": 81.17, "elapsed_time": "1:43:52", "remaining_time": "0:24:06"}
106
+ {"current_steps": 1040, "total_steps": 1269, "loss": 0.5643, "learning_rate": 5e-06, "epoch": 2.458628841607565, "percentage": 81.95, "elapsed_time": "1:44:50", "remaining_time": "0:23:05"}
107
+ {"current_steps": 1050, "total_steps": 1269, "loss": 0.5692, "learning_rate": 5e-06, "epoch": 2.482269503546099, "percentage": 82.74, "elapsed_time": "1:45:48", "remaining_time": "0:22:04"}
108
+ {"current_steps": 1060, "total_steps": 1269, "loss": 0.5667, "learning_rate": 5e-06, "epoch": 2.5059101654846336, "percentage": 83.53, "elapsed_time": "1:46:46", "remaining_time": "0:21:03"}
109
+ {"current_steps": 1070, "total_steps": 1269, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.5295508274231677, "percentage": 84.32, "elapsed_time": "1:47:44", "remaining_time": "0:20:02"}
110
+ {"current_steps": 1080, "total_steps": 1269, "loss": 0.574, "learning_rate": 5e-06, "epoch": 2.5531914893617023, "percentage": 85.11, "elapsed_time": "1:48:41", "remaining_time": "0:19:01"}
111
+ {"current_steps": 1090, "total_steps": 1269, "loss": 0.572, "learning_rate": 5e-06, "epoch": 2.5768321513002364, "percentage": 85.89, "elapsed_time": "1:49:39", "remaining_time": "0:18:00"}
112
+ {"current_steps": 1100, "total_steps": 1269, "loss": 0.5732, "learning_rate": 5e-06, "epoch": 2.6004728132387704, "percentage": 86.68, "elapsed_time": "1:50:37", "remaining_time": "0:16:59"}
113
+ {"current_steps": 1110, "total_steps": 1269, "loss": 0.571, "learning_rate": 5e-06, "epoch": 2.624113475177305, "percentage": 87.47, "elapsed_time": "1:51:35", "remaining_time": "0:15:59"}
114
+ {"current_steps": 1120, "total_steps": 1269, "loss": 0.5734, "learning_rate": 5e-06, "epoch": 2.6477541371158395, "percentage": 88.26, "elapsed_time": "1:52:33", "remaining_time": "0:14:58"}
115
+ {"current_steps": 1130, "total_steps": 1269, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.6713947990543736, "percentage": 89.05, "elapsed_time": "1:53:31", "remaining_time": "0:13:57"}
116
+ {"current_steps": 1140, "total_steps": 1269, "loss": 0.5646, "learning_rate": 5e-06, "epoch": 2.6950354609929077, "percentage": 89.83, "elapsed_time": "1:54:29", "remaining_time": "0:12:57"}
117
+ {"current_steps": 1150, "total_steps": 1269, "loss": 0.5723, "learning_rate": 5e-06, "epoch": 2.7186761229314422, "percentage": 90.62, "elapsed_time": "1:55:27", "remaining_time": "0:11:56"}
118
+ {"current_steps": 1160, "total_steps": 1269, "loss": 0.5683, "learning_rate": 5e-06, "epoch": 2.7423167848699763, "percentage": 91.41, "elapsed_time": "1:56:25", "remaining_time": "0:10:56"}
119
+ {"current_steps": 1170, "total_steps": 1269, "loss": 0.5786, "learning_rate": 5e-06, "epoch": 2.7659574468085104, "percentage": 92.2, "elapsed_time": "1:57:23", "remaining_time": "0:09:55"}
120
+ {"current_steps": 1180, "total_steps": 1269, "loss": 0.5741, "learning_rate": 5e-06, "epoch": 2.789598108747045, "percentage": 92.99, "elapsed_time": "1:58:20", "remaining_time": "0:08:55"}
121
+ {"current_steps": 1190, "total_steps": 1269, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.813238770685579, "percentage": 93.77, "elapsed_time": "1:59:18", "remaining_time": "0:07:55"}
122
+ {"current_steps": 1200, "total_steps": 1269, "loss": 0.569, "learning_rate": 5e-06, "epoch": 2.8368794326241136, "percentage": 94.56, "elapsed_time": "2:00:16", "remaining_time": "0:06:54"}
123
+ {"current_steps": 1210, "total_steps": 1269, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.8605200945626477, "percentage": 95.35, "elapsed_time": "2:01:14", "remaining_time": "0:05:54"}
124
+ {"current_steps": 1220, "total_steps": 1269, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.884160756501182, "percentage": 96.14, "elapsed_time": "2:02:12", "remaining_time": "0:04:54"}
125
+ {"current_steps": 1230, "total_steps": 1269, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.9078014184397163, "percentage": 96.93, "elapsed_time": "2:03:10", "remaining_time": "0:03:54"}
126
+ {"current_steps": 1240, "total_steps": 1269, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.9314420803782504, "percentage": 97.71, "elapsed_time": "2:04:08", "remaining_time": "0:02:54"}
127
+ {"current_steps": 1250, "total_steps": 1269, "loss": 0.5663, "learning_rate": 5e-06, "epoch": 2.955082742316785, "percentage": 98.5, "elapsed_time": "2:05:06", "remaining_time": "0:01:54"}
128
+ {"current_steps": 1260, "total_steps": 1269, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.978723404255319, "percentage": 99.29, "elapsed_time": "2:06:04", "remaining_time": "0:00:54"}
129
+ {"current_steps": 1269, "total_steps": 1269, "eval_loss": 0.6408979892730713, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:09:07", "remaining_time": "0:00:00"}
130
+ {"current_steps": 1269, "total_steps": 1269, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:10:37", "remaining_time": "0:00:00"}