Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_dcft_v1_wo_unnatural_instructions

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
9468a88
·
verified ·
1 Parent(s): 01f4dcc

Training in progress, epoch 2

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 sha256:6814266fc92022b92da98ce8b394242e4f43759d21311148252f4bfb1ea19a0e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604556d485dc5afc157d039f94c40846350c83fc8e3388c46a42973fbfb94c62
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:d138d452d39e5aa7454650c13204477ae95ab0a86a448c882e97d48d046c1034
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65a5b58a27586165880b98db3d71e507f4afe4c6dabac884d4aa95392a0e5a2
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:024e1d71a93d9648d15b7a58f2a3d256c5e429bd4ef565835f0f8d3c8f4fa7a2
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642764ab1db041e6dd72b4ddee86e501e6de624835e78f56eaed9225b28a3cce
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:263965f19e0d9cb6085072c36ef9362e1b6e64eab294d46d8ef5fa6cfebabb9e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67dd416633b0d40f20f5e83d3c96726fbce914fec63b0f1458ece3920dbbc4f1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -41,3 +41,43 @@
41
  {"current_steps": 400, "total_steps": 1179, "loss": 0.5446, "learning_rate": 5e-06, "epoch": 1.0178117048346056, "percentage": 33.93, "elapsed_time": "0:45:46", "remaining_time": "1:29:09"}
42
  {"current_steps": 410, "total_steps": 1179, "loss": 0.5287, "learning_rate": 5e-06, "epoch": 1.0432569974554706, "percentage": 34.78, "elapsed_time": "0:46:49", "remaining_time": "1:27:48"}
43
  {"current_steps": 420, "total_steps": 1179, "loss": 0.528, "learning_rate": 5e-06, "epoch": 1.0687022900763359, "percentage": 35.62, "elapsed_time": "0:47:51", "remaining_time": "1:26:28"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  {"current_steps": 400, "total_steps": 1179, "loss": 0.5446, "learning_rate": 5e-06, "epoch": 1.0178117048346056, "percentage": 33.93, "elapsed_time": "0:45:46", "remaining_time": "1:29:09"}
42
  {"current_steps": 410, "total_steps": 1179, "loss": 0.5287, "learning_rate": 5e-06, "epoch": 1.0432569974554706, "percentage": 34.78, "elapsed_time": "0:46:49", "remaining_time": "1:27:48"}
43
  {"current_steps": 420, "total_steps": 1179, "loss": 0.528, "learning_rate": 5e-06, "epoch": 1.0687022900763359, "percentage": 35.62, "elapsed_time": "0:47:51", "remaining_time": "1:26:28"}
44
+ {"current_steps": 430, "total_steps": 1179, "loss": 0.5275, "learning_rate": 5e-06, "epoch": 1.094147582697201, "percentage": 36.47, "elapsed_time": "0:48:53", "remaining_time": "1:25:09"}
45
+ {"current_steps": 440, "total_steps": 1179, "loss": 0.5317, "learning_rate": 5e-06, "epoch": 1.1195928753180662, "percentage": 37.32, "elapsed_time": "0:49:55", "remaining_time": "1:23:51"}
46
+ {"current_steps": 450, "total_steps": 1179, "loss": 0.5279, "learning_rate": 5e-06, "epoch": 1.1450381679389312, "percentage": 38.17, "elapsed_time": "0:50:58", "remaining_time": "1:22:34"}
47
+ {"current_steps": 460, "total_steps": 1179, "loss": 0.5323, "learning_rate": 5e-06, "epoch": 1.1704834605597965, "percentage": 39.02, "elapsed_time": "0:52:00", "remaining_time": "1:21:17"}
48
+ {"current_steps": 470, "total_steps": 1179, "loss": 0.5221, "learning_rate": 5e-06, "epoch": 1.1959287531806615, "percentage": 39.86, "elapsed_time": "0:53:02", "remaining_time": "1:20:01"}
49
+ {"current_steps": 480, "total_steps": 1179, "loss": 0.5296, "learning_rate": 5e-06, "epoch": 1.2213740458015268, "percentage": 40.71, "elapsed_time": "0:54:05", "remaining_time": "1:18:45"}
50
+ {"current_steps": 490, "total_steps": 1179, "loss": 0.5236, "learning_rate": 5e-06, "epoch": 1.2468193384223918, "percentage": 41.56, "elapsed_time": "0:55:07", "remaining_time": "1:17:30"}
51
+ {"current_steps": 500, "total_steps": 1179, "loss": 0.5274, "learning_rate": 5e-06, "epoch": 1.272264631043257, "percentage": 42.41, "elapsed_time": "0:56:09", "remaining_time": "1:16:15"}
52
+ {"current_steps": 510, "total_steps": 1179, "loss": 0.5234, "learning_rate": 5e-06, "epoch": 1.297709923664122, "percentage": 43.26, "elapsed_time": "0:57:11", "remaining_time": "1:15:01"}
53
+ {"current_steps": 520, "total_steps": 1179, "loss": 0.5191, "learning_rate": 5e-06, "epoch": 1.3231552162849873, "percentage": 44.11, "elapsed_time": "0:58:14", "remaining_time": "1:13:48"}
54
+ {"current_steps": 530, "total_steps": 1179, "loss": 0.5274, "learning_rate": 5e-06, "epoch": 1.3486005089058524, "percentage": 44.95, "elapsed_time": "0:59:16", "remaining_time": "1:12:34"}
55
+ {"current_steps": 540, "total_steps": 1179, "loss": 0.5271, "learning_rate": 5e-06, "epoch": 1.3740458015267176, "percentage": 45.8, "elapsed_time": "1:00:18", "remaining_time": "1:11:22"}
56
+ {"current_steps": 550, "total_steps": 1179, "loss": 0.5239, "learning_rate": 5e-06, "epoch": 1.3994910941475827, "percentage": 46.65, "elapsed_time": "1:01:20", "remaining_time": "1:10:09"}
57
+ {"current_steps": 560, "total_steps": 1179, "loss": 0.5212, "learning_rate": 5e-06, "epoch": 1.424936386768448, "percentage": 47.5, "elapsed_time": "1:02:23", "remaining_time": "1:08:57"}
58
+ {"current_steps": 570, "total_steps": 1179, "loss": 0.5147, "learning_rate": 5e-06, "epoch": 1.450381679389313, "percentage": 48.35, "elapsed_time": "1:03:25", "remaining_time": "1:07:45"}
59
+ {"current_steps": 580, "total_steps": 1179, "loss": 0.5238, "learning_rate": 5e-06, "epoch": 1.4758269720101782, "percentage": 49.19, "elapsed_time": "1:04:27", "remaining_time": "1:06:34"}
60
+ {"current_steps": 590, "total_steps": 1179, "loss": 0.5226, "learning_rate": 5e-06, "epoch": 1.5012722646310432, "percentage": 50.04, "elapsed_time": "1:05:30", "remaining_time": "1:05:23"}
61
+ {"current_steps": 600, "total_steps": 1179, "loss": 0.5161, "learning_rate": 5e-06, "epoch": 1.5267175572519083, "percentage": 50.89, "elapsed_time": "1:06:32", "remaining_time": "1:04:12"}
62
+ {"current_steps": 610, "total_steps": 1179, "loss": 0.5157, "learning_rate": 5e-06, "epoch": 1.5521628498727735, "percentage": 51.74, "elapsed_time": "1:07:34", "remaining_time": "1:03:02"}
63
+ {"current_steps": 620, "total_steps": 1179, "loss": 0.5173, "learning_rate": 5e-06, "epoch": 1.5776081424936388, "percentage": 52.59, "elapsed_time": "1:08:37", "remaining_time": "1:01:51"}
64
+ {"current_steps": 630, "total_steps": 1179, "loss": 0.518, "learning_rate": 5e-06, "epoch": 1.6030534351145038, "percentage": 53.44, "elapsed_time": "1:09:39", "remaining_time": "1:00:41"}
65
+ {"current_steps": 640, "total_steps": 1179, "loss": 0.5136, "learning_rate": 5e-06, "epoch": 1.6284987277353689, "percentage": 54.28, "elapsed_time": "1:10:41", "remaining_time": "0:59:32"}
66
+ {"current_steps": 650, "total_steps": 1179, "loss": 0.5175, "learning_rate": 5e-06, "epoch": 1.6539440203562341, "percentage": 55.13, "elapsed_time": "1:11:43", "remaining_time": "0:58:22"}
67
+ {"current_steps": 660, "total_steps": 1179, "loss": 0.5211, "learning_rate": 5e-06, "epoch": 1.6793893129770994, "percentage": 55.98, "elapsed_time": "1:12:46", "remaining_time": "0:57:13"}
68
+ {"current_steps": 670, "total_steps": 1179, "loss": 0.5228, "learning_rate": 5e-06, "epoch": 1.7048346055979644, "percentage": 56.83, "elapsed_time": "1:13:48", "remaining_time": "0:56:04"}
69
+ {"current_steps": 680, "total_steps": 1179, "loss": 0.5177, "learning_rate": 5e-06, "epoch": 1.7302798982188294, "percentage": 57.68, "elapsed_time": "1:14:50", "remaining_time": "0:54:55"}
70
+ {"current_steps": 690, "total_steps": 1179, "loss": 0.5147, "learning_rate": 5e-06, "epoch": 1.7557251908396947, "percentage": 58.52, "elapsed_time": "1:15:53", "remaining_time": "0:53:46"}
71
+ {"current_steps": 700, "total_steps": 1179, "loss": 0.5167, "learning_rate": 5e-06, "epoch": 1.78117048346056, "percentage": 59.37, "elapsed_time": "1:16:55", "remaining_time": "0:52:38"}
72
+ {"current_steps": 710, "total_steps": 1179, "loss": 0.5116, "learning_rate": 5e-06, "epoch": 1.806615776081425, "percentage": 60.22, "elapsed_time": "1:17:57", "remaining_time": "0:51:29"}
73
+ {"current_steps": 720, "total_steps": 1179, "loss": 0.5125, "learning_rate": 5e-06, "epoch": 1.83206106870229, "percentage": 61.07, "elapsed_time": "1:18:59", "remaining_time": "0:50:21"}
74
+ {"current_steps": 730, "total_steps": 1179, "loss": 0.5134, "learning_rate": 5e-06, "epoch": 1.8575063613231553, "percentage": 61.92, "elapsed_time": "1:20:02", "remaining_time": "0:49:13"}
75
+ {"current_steps": 740, "total_steps": 1179, "loss": 0.5111, "learning_rate": 5e-06, "epoch": 1.8829516539440203, "percentage": 62.77, "elapsed_time": "1:21:04", "remaining_time": "0:48:05"}
76
+ {"current_steps": 750, "total_steps": 1179, "loss": 0.5147, "learning_rate": 5e-06, "epoch": 1.9083969465648853, "percentage": 63.61, "elapsed_time": "1:22:06", "remaining_time": "0:46:58"}
77
+ {"current_steps": 760, "total_steps": 1179, "loss": 0.5092, "learning_rate": 5e-06, "epoch": 1.9338422391857506, "percentage": 64.46, "elapsed_time": "1:23:09", "remaining_time": "0:45:50"}
78
+ {"current_steps": 770, "total_steps": 1179, "loss": 0.5092, "learning_rate": 5e-06, "epoch": 1.9592875318066159, "percentage": 65.31, "elapsed_time": "1:24:11", "remaining_time": "0:44:43"}
79
+ {"current_steps": 780, "total_steps": 1179, "loss": 0.5093, "learning_rate": 5e-06, "epoch": 1.984732824427481, "percentage": 66.16, "elapsed_time": "1:25:13", "remaining_time": "0:43:35"}
80
+ {"current_steps": 786, "total_steps": 1179, "eval_loss": 0.5446056127548218, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:26:25", "remaining_time": "0:43:12"}
81
+ {"current_steps": 790, "total_steps": 1179, "loss": 0.4964, "learning_rate": 5e-06, "epoch": 2.010178117048346, "percentage": 67.01, "elapsed_time": "1:30:31", "remaining_time": "0:44:34"}
82
+ {"current_steps": 800, "total_steps": 1179, "loss": 0.4699, "learning_rate": 5e-06, "epoch": 2.035623409669211, "percentage": 67.85, "elapsed_time": "1:31:34", "remaining_time": "0:43:22"}
83
+ {"current_steps": 810, "total_steps": 1179, "loss": 0.4747, "learning_rate": 5e-06, "epoch": 2.0610687022900764, "percentage": 68.7, "elapsed_time": "1:32:36", "remaining_time": "0:42:11"}