Hugging Face's logo

mlfoundations-dev
/
llama2_oh_teknium_scaling_down_random_0.9

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
d5b45f5
·
verified ·
1 Parent(s): a38e9f1

Training in progress, epoch 2

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +34 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a634cdfafc0be85869fdc4e4b1e1bdb28a04b2b37745d204ab6caeb38ab0007b
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402bd27bce10dcee961c8e95f40b4ccca63b63f2c00601fe1817b0cb0f0c8041
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab59334d4f41e68e463df7b8d361ce73f976691cb759408580c21b84e766713
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74510d5c3ded87de264dfe99467f8c0883e51169053a9cecf07ee393eb2f6cbc
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:856d174537367591cdcc393c624feb7f7ea4a2a0e025675187000bd67942c42a
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725c19465f284e585b4d20c2af795da372b99d7df4c19692587540273b45e386
3
  size 3590488816
trainer_log.jsonl CHANGED
@@ -68,3 +68,37 @@
68
  {"current_steps": 670, "total_steps": 1020, "loss": 0.566, "lr": 5e-06, "epoch": 1.9677182685253118, "percentage": 65.69, "elapsed_time": "10:17:03", "remaining_time": "5:22:20"}
69
  {"current_steps": 680, "total_steps": 1020, "loss": 0.5587, "lr": 5e-06, "epoch": 1.9970652971386649, "percentage": 66.67, "elapsed_time": "10:26:07", "remaining_time": "5:13:03"}
70
  {"current_steps": 680, "total_steps": 1020, "eval_loss": 0.5877389907836914, "epoch": 1.9970652971386649, "percentage": 66.67, "elapsed_time": "10:32:18", "remaining_time": "5:16:09"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  {"current_steps": 670, "total_steps": 1020, "loss": 0.566, "lr": 5e-06, "epoch": 1.9677182685253118, "percentage": 65.69, "elapsed_time": "10:17:03", "remaining_time": "5:22:20"}
69
  {"current_steps": 680, "total_steps": 1020, "loss": 0.5587, "lr": 5e-06, "epoch": 1.9970652971386649, "percentage": 66.67, "elapsed_time": "10:26:07", "remaining_time": "5:13:03"}
70
  {"current_steps": 680, "total_steps": 1020, "eval_loss": 0.5877389907836914, "epoch": 1.9970652971386649, "percentage": 66.67, "elapsed_time": "10:32:18", "remaining_time": "5:16:09"}
71
+ {"current_steps": 690, "total_steps": 1020, "loss": 0.578, "lr": 5e-06, "epoch": 2.0278796771826855, "percentage": 67.65, "elapsed_time": "10:42:04", "remaining_time": "5:07:04"}
72
+ {"current_steps": 700, "total_steps": 1020, "loss": 0.5283, "lr": 5e-06, "epoch": 2.057226705796038, "percentage": 68.63, "elapsed_time": "10:51:10", "remaining_time": "4:57:40"}
73
+ {"current_steps": 710, "total_steps": 1020, "loss": 0.531, "lr": 5e-06, "epoch": 2.086573734409391, "percentage": 69.61, "elapsed_time": "11:00:16", "remaining_time": "4:48:17"}
74
+ {"current_steps": 720, "total_steps": 1020, "loss": 0.5334, "lr": 5e-06, "epoch": 2.115920763022744, "percentage": 70.59, "elapsed_time": "11:09:23", "remaining_time": "4:38:54"}
75
+ {"current_steps": 730, "total_steps": 1020, "loss": 0.5297, "lr": 5e-06, "epoch": 2.1452677916360967, "percentage": 71.57, "elapsed_time": "11:18:30", "remaining_time": "4:29:32"}
76
+ {"current_steps": 740, "total_steps": 1020, "loss": 0.5337, "lr": 5e-06, "epoch": 2.1746148202494497, "percentage": 72.55, "elapsed_time": "11:27:36", "remaining_time": "4:20:10"}
77
+ {"current_steps": 750, "total_steps": 1020, "loss": 0.5312, "lr": 5e-06, "epoch": 2.2039618488628028, "percentage": 73.53, "elapsed_time": "11:36:43", "remaining_time": "4:10:49"}
78
+ {"current_steps": 760, "total_steps": 1020, "loss": 0.5356, "lr": 5e-06, "epoch": 2.2333088774761554, "percentage": 74.51, "elapsed_time": "11:45:51", "remaining_time": "4:01:28"}
79
+ {"current_steps": 770, "total_steps": 1020, "loss": 0.5306, "lr": 5e-06, "epoch": 2.2626559060895084, "percentage": 75.49, "elapsed_time": "11:54:58", "remaining_time": "3:52:07"}
80
+ {"current_steps": 780, "total_steps": 1020, "loss": 0.529, "lr": 5e-06, "epoch": 2.2920029347028614, "percentage": 76.47, "elapsed_time": "12:04:05", "remaining_time": "3:42:47"}
81
+ {"current_steps": 790, "total_steps": 1020, "loss": 0.5269, "lr": 5e-06, "epoch": 2.321349963316214, "percentage": 77.45, "elapsed_time": "12:13:13", "remaining_time": "3:33:28"}
82
+ {"current_steps": 800, "total_steps": 1020, "loss": 0.5293, "lr": 5e-06, "epoch": 2.350696991929567, "percentage": 78.43, "elapsed_time": "12:22:20", "remaining_time": "3:24:08"}
83
+ {"current_steps": 810, "total_steps": 1020, "loss": 0.5327, "lr": 5e-06, "epoch": 2.38004402054292, "percentage": 79.41, "elapsed_time": "12:31:29", "remaining_time": "3:14:49"}
84
+ {"current_steps": 820, "total_steps": 1020, "loss": 0.5355, "lr": 5e-06, "epoch": 2.409391049156273, "percentage": 80.39, "elapsed_time": "12:40:37", "remaining_time": "3:05:31"}
85
+ {"current_steps": 830, "total_steps": 1020, "loss": 0.5293, "lr": 5e-06, "epoch": 2.4387380777696257, "percentage": 81.37, "elapsed_time": "12:49:43", "remaining_time": "2:56:12"}
86
+ {"current_steps": 840, "total_steps": 1020, "loss": 0.5352, "lr": 5e-06, "epoch": 2.4680851063829787, "percentage": 82.35, "elapsed_time": "12:58:51", "remaining_time": "2:46:53"}
87
+ {"current_steps": 850, "total_steps": 1020, "loss": 0.5291, "lr": 5e-06, "epoch": 2.4974321349963318, "percentage": 83.33, "elapsed_time": "13:07:58", "remaining_time": "2:37:35"}
88
+ {"current_steps": 860, "total_steps": 1020, "loss": 0.5354, "lr": 5e-06, "epoch": 2.5267791636096844, "percentage": 84.31, "elapsed_time": "13:17:05", "remaining_time": "2:28:17"}
89
+ {"current_steps": 870, "total_steps": 1020, "loss": 0.5212, "lr": 5e-06, "epoch": 2.5561261922230374, "percentage": 85.29, "elapsed_time": "13:26:12", "remaining_time": "2:19:00"}
90
+ {"current_steps": 880, "total_steps": 1020, "loss": 0.5347, "lr": 5e-06, "epoch": 2.5854732208363904, "percentage": 86.27, "elapsed_time": "13:35:18", "remaining_time": "2:09:42"}
91
+ {"current_steps": 890, "total_steps": 1020, "loss": 0.5349, "lr": 5e-06, "epoch": 2.6148202494497435, "percentage": 87.25, "elapsed_time": "13:44:26", "remaining_time": "2:00:25"}
92
+ {"current_steps": 900, "total_steps": 1020, "loss": 0.5234, "lr": 5e-06, "epoch": 2.644167278063096, "percentage": 88.24, "elapsed_time": "13:53:32", "remaining_time": "1:51:08"}
93
+ {"current_steps": 910, "total_steps": 1020, "loss": 0.5309, "lr": 5e-06, "epoch": 2.673514306676449, "percentage": 89.22, "elapsed_time": "14:02:39", "remaining_time": "1:41:51"}
94
+ {"current_steps": 920, "total_steps": 1020, "loss": 0.5293, "lr": 5e-06, "epoch": 2.7028613352898017, "percentage": 90.2, "elapsed_time": "14:11:45", "remaining_time": "1:32:34"}
95
+ {"current_steps": 930, "total_steps": 1020, "loss": 0.5267, "lr": 5e-06, "epoch": 2.7322083639031547, "percentage": 91.18, "elapsed_time": "14:20:52", "remaining_time": "1:23:18"}
96
+ {"current_steps": 940, "total_steps": 1020, "loss": 0.5284, "lr": 5e-06, "epoch": 2.7615553925165077, "percentage": 92.16, "elapsed_time": "14:29:58", "remaining_time": "1:14:02"}
97
+ {"current_steps": 950, "total_steps": 1020, "loss": 0.5341, "lr": 5e-06, "epoch": 2.7909024211298608, "percentage": 93.14, "elapsed_time": "14:39:03", "remaining_time": "1:04:46"}
98
+ {"current_steps": 960, "total_steps": 1020, "loss": 0.5323, "lr": 5e-06, "epoch": 2.8202494497432133, "percentage": 94.12, "elapsed_time": "14:48:07", "remaining_time": "0:55:30"}
99
+ {"current_steps": 970, "total_steps": 1020, "loss": 0.5333, "lr": 5e-06, "epoch": 2.8495964783565664, "percentage": 95.1, "elapsed_time": "14:57:16", "remaining_time": "0:46:15"}
100
+ {"current_steps": 980, "total_steps": 1020, "loss": 0.5221, "lr": 5e-06, "epoch": 2.8789435069699194, "percentage": 96.08, "elapsed_time": "15:06:23", "remaining_time": "0:36:59"}
101
+ {"current_steps": 990, "total_steps": 1020, "loss": 0.5283, "lr": 5e-06, "epoch": 2.908290535583272, "percentage": 97.06, "elapsed_time": "15:15:30", "remaining_time": "0:27:44"}
102
+ {"current_steps": 1000, "total_steps": 1020, "loss": 0.5357, "lr": 5e-06, "epoch": 2.937637564196625, "percentage": 98.04, "elapsed_time": "15:24:39", "remaining_time": "0:18:29"}
103
+ {"current_steps": 1010, "total_steps": 1020, "loss": 0.5289, "lr": 5e-06, "epoch": 2.966984592809978, "percentage": 99.02, "elapsed_time": "15:33:47", "remaining_time": "0:09:14"}
104
+ {"current_steps": 1020, "total_steps": 1020, "loss": 0.528, "lr": 5e-06, "epoch": 2.996331621423331, "percentage": 100.0, "elapsed_time": "15:42:54", "remaining_time": "0:00:00"}