Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_evol_instruct_x8

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
efccbb2
·
verified ·
1 Parent(s): e784074

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 +40 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdb19656907c5225a875be54b033aa66fec1b4d1ca18d173e688bbf44ae09312
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e090ffccf5ee5b79886f917c8b6b6761d998bb5cc37ae24fe6aac31c89f1d29
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31a8b6df2460b8b85f343677be79a57fa1d4a800d2ce5cd8171ae76508a9ecf6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e4030c698ace9aaa3fb556374a8426791586dd4314b1952b5235de787c4b90
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cac513412996112a59538d9d73489fbef049f67b3b8d5c2aec97347125c9de9
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20da08d6509ebfe61764ecd03241c42f90dd686de34d2aee1c36da787fd0cd2d
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:ff59925a65c5736d47057608839f0d5db18d085b1fef73b8d971103e83f7c7ce
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f7f66b98d493cc32ebc56e55c406a2ba93542222467cfcb06436e48a290df3
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -80,3 +80,43 @@
80
  {"current_steps": 790, "total_steps": 1200, "loss": 0.771, "lr": 5e-06, "epoch": 1.975, "percentage": 65.83, "elapsed_time": "7:15:21", "remaining_time": "3:45:56"}
81
  {"current_steps": 800, "total_steps": 1200, "loss": 0.7753, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:20:47", "remaining_time": "3:40:23"}
82
  {"current_steps": 800, "total_steps": 1200, "eval_loss": 0.8092445731163025, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:25:26", "remaining_time": "3:42:43"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  {"current_steps": 790, "total_steps": 1200, "loss": 0.771, "lr": 5e-06, "epoch": 1.975, "percentage": 65.83, "elapsed_time": "7:15:21", "remaining_time": "3:45:56"}
81
  {"current_steps": 800, "total_steps": 1200, "loss": 0.7753, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:20:47", "remaining_time": "3:40:23"}
82
  {"current_steps": 800, "total_steps": 1200, "eval_loss": 0.8092445731163025, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "7:25:26", "remaining_time": "3:42:43"}
83
+ {"current_steps": 810, "total_steps": 1200, "loss": 0.731, "lr": 5e-06, "epoch": 2.025, "percentage": 67.5, "elapsed_time": "7:32:09", "remaining_time": "3:37:42"}
84
+ {"current_steps": 820, "total_steps": 1200, "loss": 0.7254, "lr": 5e-06, "epoch": 2.05, "percentage": 68.33, "elapsed_time": "7:37:36", "remaining_time": "3:32:03"}
85
+ {"current_steps": 830, "total_steps": 1200, "loss": 0.722, "lr": 5e-06, "epoch": 2.075, "percentage": 69.17, "elapsed_time": "7:43:02", "remaining_time": "3:26:25"}
86
+ {"current_steps": 840, "total_steps": 1200, "loss": 0.7251, "lr": 5e-06, "epoch": 2.1, "percentage": 70.0, "elapsed_time": "7:48:30", "remaining_time": "3:20:47"}
87
+ {"current_steps": 850, "total_steps": 1200, "loss": 0.7329, "lr": 5e-06, "epoch": 2.125, "percentage": 70.83, "elapsed_time": "7:53:56", "remaining_time": "3:15:08"}
88
+ {"current_steps": 860, "total_steps": 1200, "loss": 0.7282, "lr": 5e-06, "epoch": 2.15, "percentage": 71.67, "elapsed_time": "7:59:23", "remaining_time": "3:09:31"}
89
+ {"current_steps": 870, "total_steps": 1200, "loss": 0.7283, "lr": 5e-06, "epoch": 2.175, "percentage": 72.5, "elapsed_time": "8:04:49", "remaining_time": "3:03:53"}
90
+ {"current_steps": 880, "total_steps": 1200, "loss": 0.7333, "lr": 5e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "8:10:13", "remaining_time": "2:58:15"}
91
+ {"current_steps": 890, "total_steps": 1200, "loss": 0.7307, "lr": 5e-06, "epoch": 2.225, "percentage": 74.17, "elapsed_time": "8:15:38", "remaining_time": "2:52:38"}
92
+ {"current_steps": 900, "total_steps": 1200, "loss": 0.7276, "lr": 5e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "8:21:02", "remaining_time": "2:47:00"}
93
+ {"current_steps": 910, "total_steps": 1200, "loss": 0.7284, "lr": 5e-06, "epoch": 2.275, "percentage": 75.83, "elapsed_time": "8:26:27", "remaining_time": "2:41:23"}
94
+ {"current_steps": 920, "total_steps": 1200, "loss": 0.7287, "lr": 5e-06, "epoch": 2.3, "percentage": 76.67, "elapsed_time": "8:31:53", "remaining_time": "2:35:47"}
95
+ {"current_steps": 930, "total_steps": 1200, "loss": 0.7272, "lr": 5e-06, "epoch": 2.325, "percentage": 77.5, "elapsed_time": "8:37:20", "remaining_time": "2:30:11"}
96
+ {"current_steps": 940, "total_steps": 1200, "loss": 0.7301, "lr": 5e-06, "epoch": 2.35, "percentage": 78.33, "elapsed_time": "8:42:47", "remaining_time": "2:24:36"}
97
+ {"current_steps": 950, "total_steps": 1200, "loss": 0.7333, "lr": 5e-06, "epoch": 2.375, "percentage": 79.17, "elapsed_time": "8:48:14", "remaining_time": "2:19:00"}
98
+ {"current_steps": 960, "total_steps": 1200, "loss": 0.7279, "lr": 5e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "8:53:42", "remaining_time": "2:13:25"}
99
+ {"current_steps": 970, "total_steps": 1200, "loss": 0.7307, "lr": 5e-06, "epoch": 2.425, "percentage": 80.83, "elapsed_time": "8:59:10", "remaining_time": "2:07:50"}
100
+ {"current_steps": 980, "total_steps": 1200, "loss": 0.727, "lr": 5e-06, "epoch": 2.45, "percentage": 81.67, "elapsed_time": "9:04:36", "remaining_time": "2:02:15"}
101
+ {"current_steps": 990, "total_steps": 1200, "loss": 0.7315, "lr": 5e-06, "epoch": 2.475, "percentage": 82.5, "elapsed_time": "9:10:02", "remaining_time": "1:56:40"}
102
+ {"current_steps": 1000, "total_steps": 1200, "loss": 0.732, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "9:15:29", "remaining_time": "1:51:05"}
103
+ {"current_steps": 1010, "total_steps": 1200, "loss": 0.7301, "lr": 5e-06, "epoch": 2.525, "percentage": 84.17, "elapsed_time": "9:20:55", "remaining_time": "1:45:31"}
104
+ {"current_steps": 1020, "total_steps": 1200, "loss": 0.727, "lr": 5e-06, "epoch": 2.55, "percentage": 85.0, "elapsed_time": "9:26:22", "remaining_time": "1:39:56"}
105
+ {"current_steps": 1030, "total_steps": 1200, "loss": 0.732, "lr": 5e-06, "epoch": 2.575, "percentage": 85.83, "elapsed_time": "9:31:49", "remaining_time": "1:34:22"}
106
+ {"current_steps": 1040, "total_steps": 1200, "loss": 0.7304, "lr": 5e-06, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "9:37:16", "remaining_time": "1:28:48"}
107
+ {"current_steps": 1050, "total_steps": 1200, "loss": 0.7301, "lr": 5e-06, "epoch": 2.625, "percentage": 87.5, "elapsed_time": "9:42:43", "remaining_time": "1:23:14"}
108
+ {"current_steps": 1060, "total_steps": 1200, "loss": 0.7303, "lr": 5e-06, "epoch": 2.65, "percentage": 88.33, "elapsed_time": "9:48:10", "remaining_time": "1:17:40"}
109
+ {"current_steps": 1070, "total_steps": 1200, "loss": 0.7352, "lr": 5e-06, "epoch": 2.675, "percentage": 89.17, "elapsed_time": "9:53:35", "remaining_time": "1:12:07"}
110
+ {"current_steps": 1080, "total_steps": 1200, "loss": 0.7325, "lr": 5e-06, "epoch": 2.7, "percentage": 90.0, "elapsed_time": "9:59:01", "remaining_time": "1:06:33"}
111
+ {"current_steps": 1090, "total_steps": 1200, "loss": 0.7297, "lr": 5e-06, "epoch": 2.725, "percentage": 90.83, "elapsed_time": "10:04:28", "remaining_time": "1:01:00"}
112
+ {"current_steps": 1100, "total_steps": 1200, "loss": 0.7302, "lr": 5e-06, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "10:09:54", "remaining_time": "0:55:26"}
113
+ {"current_steps": 1110, "total_steps": 1200, "loss": 0.7338, "lr": 5e-06, "epoch": 2.775, "percentage": 92.5, "elapsed_time": "10:15:22", "remaining_time": "0:49:53"}
114
+ {"current_steps": 1120, "total_steps": 1200, "loss": 0.7333, "lr": 5e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "10:20:49", "remaining_time": "0:44:20"}
115
+ {"current_steps": 1130, "total_steps": 1200, "loss": 0.7368, "lr": 5e-06, "epoch": 2.825, "percentage": 94.17, "elapsed_time": "10:26:17", "remaining_time": "0:38:47"}
116
+ {"current_steps": 1140, "total_steps": 1200, "loss": 0.7315, "lr": 5e-06, "epoch": 2.85, "percentage": 95.0, "elapsed_time": "10:31:44", "remaining_time": "0:33:14"}
117
+ {"current_steps": 1150, "total_steps": 1200, "loss": 0.7328, "lr": 5e-06, "epoch": 2.875, "percentage": 95.83, "elapsed_time": "10:37:11", "remaining_time": "0:27:42"}
118
+ {"current_steps": 1160, "total_steps": 1200, "loss": 0.7335, "lr": 5e-06, "epoch": 2.9, "percentage": 96.67, "elapsed_time": "10:42:37", "remaining_time": "0:22:09"}
119
+ {"current_steps": 1170, "total_steps": 1200, "loss": 0.7296, "lr": 5e-06, "epoch": 2.925, "percentage": 97.5, "elapsed_time": "10:48:03", "remaining_time": "0:16:37"}
120
+ {"current_steps": 1180, "total_steps": 1200, "loss": 0.7336, "lr": 5e-06, "epoch": 2.95, "percentage": 98.33, "elapsed_time": "10:53:30", "remaining_time": "0:11:04"}
121
+ {"current_steps": 1190, "total_steps": 1200, "loss": 0.7316, "lr": 5e-06, "epoch": 2.975, "percentage": 99.17, "elapsed_time": "10:58:57", "remaining_time": "0:05:32"}
122
+ {"current_steps": 1200, "total_steps": 1200, "loss": 0.7331, "lr": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "11:04:21", "remaining_time": "0:00:00"}