Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_v3.1_wo_evolinstruct

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
86b8b24
•
1 Parent(s): 05e881d

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:ff7ef0f3c7f0fd3b0c92bc2e8d51ed993adab4df25b3c18a48c873cd3eb5b9c1
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abc28d26f1d3cd9da19a5020c3d09c6e1a7d2010d2a921fd6fd0cc5c7005fde3
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:a76bbca7a01b137d3244b227bdaeaf0d7ccb69109eb4cb300324cd18c1f721ae
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f408f7003878dc219f716828a8a3df6dedf96150541491006c8fa1f26e77a8
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d7a012d84cc51ca4336748f137daaf53eb6eeed595cba05803356e9485e3917
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ca496697764c0eb732355ef7cf7d6bdcb303e1b4d793a8ba9506752fd58c71
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36c0205f7172e2f54b6a7f421177695f17aa6b9a2a2c66bd2cd31d5313efa081
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30daaa75319dce6896fe520e8ddf974003a7d1229ff778a85590404be8ef2202
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -80,3 +80,42 @@
80
  {"current_steps": 782, "total_steps": 1173, "eval_loss": 0.6335848569869995, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:19:47", "remaining_time": "0:39:53"}
81
  {"current_steps": 790, "total_steps": 1173, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.020460358056266, "percentage": 67.35, "elapsed_time": "1:22:06", "remaining_time": "0:39:48"}
82
  {"current_steps": 800, "total_steps": 1173, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 2.0460358056265986, "percentage": 68.2, "elapsed_time": "1:23:05", "remaining_time": "0:38:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  {"current_steps": 782, "total_steps": 1173, "eval_loss": 0.6335848569869995, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:19:47", "remaining_time": "0:39:53"}
81
  {"current_steps": 790, "total_steps": 1173, "loss": 0.5672, "learning_rate": 5e-06, "epoch": 2.020460358056266, "percentage": 67.35, "elapsed_time": "1:22:06", "remaining_time": "0:39:48"}
82
  {"current_steps": 800, "total_steps": 1173, "loss": 0.5592, "learning_rate": 5e-06, "epoch": 2.0460358056265986, "percentage": 68.2, "elapsed_time": "1:23:05", "remaining_time": "0:38:44"}
83
+ {"current_steps": 810, "total_steps": 1173, "loss": 0.5431, "learning_rate": 5e-06, "epoch": 2.071611253196931, "percentage": 69.05, "elapsed_time": "1:24:04", "remaining_time": "0:37:40"}
84
+ {"current_steps": 820, "total_steps": 1173, "loss": 0.5558, "learning_rate": 5e-06, "epoch": 2.0971867007672635, "percentage": 69.91, "elapsed_time": "1:25:03", "remaining_time": "0:36:36"}
85
+ {"current_steps": 830, "total_steps": 1173, "loss": 0.549, "learning_rate": 5e-06, "epoch": 2.122762148337596, "percentage": 70.76, "elapsed_time": "1:26:01", "remaining_time": "0:35:33"}
86
+ {"current_steps": 840, "total_steps": 1173, "loss": 0.5595, "learning_rate": 5e-06, "epoch": 2.1483375959079285, "percentage": 71.61, "elapsed_time": "1:27:00", "remaining_time": "0:34:29"}
87
+ {"current_steps": 850, "total_steps": 1173, "loss": 0.5584, "learning_rate": 5e-06, "epoch": 2.1739130434782608, "percentage": 72.46, "elapsed_time": "1:27:58", "remaining_time": "0:33:25"}
88
+ {"current_steps": 860, "total_steps": 1173, "loss": 0.5556, "learning_rate": 5e-06, "epoch": 2.1994884910485935, "percentage": 73.32, "elapsed_time": "1:28:56", "remaining_time": "0:32:22"}
89
+ {"current_steps": 870, "total_steps": 1173, "loss": 0.5595, "learning_rate": 5e-06, "epoch": 2.2250639386189257, "percentage": 74.17, "elapsed_time": "1:29:55", "remaining_time": "0:31:19"}
90
+ {"current_steps": 880, "total_steps": 1173, "loss": 0.5541, "learning_rate": 5e-06, "epoch": 2.2506393861892584, "percentage": 75.02, "elapsed_time": "1:30:55", "remaining_time": "0:30:16"}
91
+ {"current_steps": 890, "total_steps": 1173, "loss": 0.5597, "learning_rate": 5e-06, "epoch": 2.2762148337595907, "percentage": 75.87, "elapsed_time": "1:31:53", "remaining_time": "0:29:13"}
92
+ {"current_steps": 900, "total_steps": 1173, "loss": 0.5585, "learning_rate": 5e-06, "epoch": 2.3017902813299234, "percentage": 76.73, "elapsed_time": "1:32:52", "remaining_time": "0:28:10"}
93
+ {"current_steps": 910, "total_steps": 1173, "loss": 0.553, "learning_rate": 5e-06, "epoch": 2.3273657289002556, "percentage": 77.58, "elapsed_time": "1:33:51", "remaining_time": "0:27:07"}
94
+ {"current_steps": 920, "total_steps": 1173, "loss": 0.5555, "learning_rate": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "1:34:50", "remaining_time": "0:26:04"}
95
+ {"current_steps": 930, "total_steps": 1173, "loss": 0.5539, "learning_rate": 5e-06, "epoch": 2.3785166240409206, "percentage": 79.28, "elapsed_time": "1:35:48", "remaining_time": "0:25:02"}
96
+ {"current_steps": 940, "total_steps": 1173, "loss": 0.5596, "learning_rate": 5e-06, "epoch": 2.4040920716112533, "percentage": 80.14, "elapsed_time": "1:36:46", "remaining_time": "0:23:59"}
97
+ {"current_steps": 950, "total_steps": 1173, "loss": 0.5575, "learning_rate": 5e-06, "epoch": 2.4296675191815855, "percentage": 80.99, "elapsed_time": "1:37:45", "remaining_time": "0:22:56"}
98
+ {"current_steps": 960, "total_steps": 1173, "loss": 0.562, "learning_rate": 5e-06, "epoch": 2.455242966751918, "percentage": 81.84, "elapsed_time": "1:38:43", "remaining_time": "0:21:54"}
99
+ {"current_steps": 970, "total_steps": 1173, "loss": 0.5555, "learning_rate": 5e-06, "epoch": 2.4808184143222505, "percentage": 82.69, "elapsed_time": "1:39:42", "remaining_time": "0:20:51"}
100
+ {"current_steps": 980, "total_steps": 1173, "loss": 0.5586, "learning_rate": 5e-06, "epoch": 2.506393861892583, "percentage": 83.55, "elapsed_time": "1:40:41", "remaining_time": "0:19:49"}
101
+ {"current_steps": 990, "total_steps": 1173, "loss": 0.5573, "learning_rate": 5e-06, "epoch": 2.531969309462916, "percentage": 84.4, "elapsed_time": "1:41:39", "remaining_time": "0:18:47"}
102
+ {"current_steps": 1000, "total_steps": 1173, "loss": 0.559, "learning_rate": 5e-06, "epoch": 2.557544757033248, "percentage": 85.25, "elapsed_time": "1:42:39", "remaining_time": "0:17:45"}
103
+ {"current_steps": 1010, "total_steps": 1173, "loss": 0.5663, "learning_rate": 5e-06, "epoch": 2.5831202046035804, "percentage": 86.1, "elapsed_time": "1:43:38", "remaining_time": "0:16:43"}
104
+ {"current_steps": 1020, "total_steps": 1173, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.608695652173913, "percentage": 86.96, "elapsed_time": "1:44:37", "remaining_time": "0:15:41"}
105
+ {"current_steps": 1030, "total_steps": 1173, "loss": 0.5605, "learning_rate": 5e-06, "epoch": 2.634271099744246, "percentage": 87.81, "elapsed_time": "1:45:36", "remaining_time": "0:14:39"}
106
+ {"current_steps": 1040, "total_steps": 1173, "loss": 0.5629, "learning_rate": 5e-06, "epoch": 2.659846547314578, "percentage": 88.66, "elapsed_time": "1:46:36", "remaining_time": "0:13:37"}
107
+ {"current_steps": 1050, "total_steps": 1173, "loss": 0.5559, "learning_rate": 5e-06, "epoch": 2.6854219948849103, "percentage": 89.51, "elapsed_time": "1:47:35", "remaining_time": "0:12:36"}
108
+ {"current_steps": 1060, "total_steps": 1173, "loss": 0.5602, "learning_rate": 5e-06, "epoch": 2.710997442455243, "percentage": 90.37, "elapsed_time": "1:48:34", "remaining_time": "0:11:34"}
109
+ {"current_steps": 1070, "total_steps": 1173, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.7365728900255757, "percentage": 91.22, "elapsed_time": "1:49:33", "remaining_time": "0:10:32"}
110
+ {"current_steps": 1080, "total_steps": 1173, "loss": 0.5561, "learning_rate": 5e-06, "epoch": 2.762148337595908, "percentage": 92.07, "elapsed_time": "1:50:32", "remaining_time": "0:09:31"}
111
+ {"current_steps": 1090, "total_steps": 1173, "loss": 0.5536, "learning_rate": 5e-06, "epoch": 2.78772378516624, "percentage": 92.92, "elapsed_time": "1:51:31", "remaining_time": "0:08:29"}
112
+ {"current_steps": 1100, "total_steps": 1173, "loss": 0.5579, "learning_rate": 5e-06, "epoch": 2.813299232736573, "percentage": 93.78, "elapsed_time": "1:52:29", "remaining_time": "0:07:27"}
113
+ {"current_steps": 1110, "total_steps": 1173, "loss": 0.5629, "learning_rate": 5e-06, "epoch": 2.8388746803069056, "percentage": 94.63, "elapsed_time": "1:53:27", "remaining_time": "0:06:26"}
114
+ {"current_steps": 1120, "total_steps": 1173, "loss": 0.5662, "learning_rate": 5e-06, "epoch": 2.864450127877238, "percentage": 95.48, "elapsed_time": "1:54:26", "remaining_time": "0:05:24"}
115
+ {"current_steps": 1130, "total_steps": 1173, "loss": 0.5622, "learning_rate": 5e-06, "epoch": 2.89002557544757, "percentage": 96.33, "elapsed_time": "1:55:24", "remaining_time": "0:04:23"}
116
+ {"current_steps": 1140, "total_steps": 1173, "loss": 0.5613, "learning_rate": 5e-06, "epoch": 2.915601023017903, "percentage": 97.19, "elapsed_time": "1:56:23", "remaining_time": "0:03:22"}
117
+ {"current_steps": 1150, "total_steps": 1173, "loss": 0.5634, "learning_rate": 5e-06, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "1:57:21", "remaining_time": "0:02:20"}
118
+ {"current_steps": 1160, "total_steps": 1173, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 2.9667519181585678, "percentage": 98.89, "elapsed_time": "1:58:21", "remaining_time": "0:01:19"}
119
+ {"current_steps": 1170, "total_steps": 1173, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 2.9923273657289, "percentage": 99.74, "elapsed_time": "1:59:20", "remaining_time": "0:00:18"}
120
+ {"current_steps": 1173, "total_steps": 1173, "eval_loss": 0.6347914934158325, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:01:49", "remaining_time": "0:00:00"}
121
+ {"current_steps": 1173, "total_steps": 1173, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:03:18", "remaining_time": "0:00:00"}