Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v3.1-llama-3.1-405b

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
4d8ef13
•
1 Parent(s): 7b70ef0

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 +43 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3b2643a9eb1be5d9d6ed698c63451a1cb4a925447c9da4d7ff21ab8bf78113c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2f1ddded1d2396006b280219cdf6742ae611a284028001ff9e1234e2b00c60
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:d5c7c2316c9e3996058244751e2ca9eadac42f4ab0060b35374ce3f434990545
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d2d5db3ea39ebad270e00b28eb4cf1d8edd6d6d945a06f8748feb33a46a337
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33829044af1c1bba93fe844931e0768531dae29177c3dc8f03bca65ebd29163a
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8013eaf77d81598fe97415aa42849412a1ee397f6dc4500f72e1078d28e2b68a
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:a50ccb7879dd675d09388cd12f5613f5a721f4b70bb159b4f940ff7fbe5a6dc7
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6012b5aed8766f14025f784803bb19a36652bb6f0ee1486a0e293dd32cb2ffb6
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -44,3 +44,46 @@
44
  {"current_steps": 430, "total_steps": 1266, "loss": 0.287, "lr": 5e-06, "epoch": 1.018957345971564, "percentage": 33.97, "elapsed_time": "0:44:35", "remaining_time": "1:26:42"}
45
  {"current_steps": 440, "total_steps": 1266, "loss": 0.2762, "lr": 5e-06, "epoch": 1.042654028436019, "percentage": 34.76, "elapsed_time": "0:45:34", "remaining_time": "1:25:33"}
46
  {"current_steps": 450, "total_steps": 1266, "loss": 0.2734, "lr": 5e-06, "epoch": 1.066350710900474, "percentage": 35.55, "elapsed_time": "0:46:32", "remaining_time": "1:24:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  {"current_steps": 430, "total_steps": 1266, "loss": 0.287, "lr": 5e-06, "epoch": 1.018957345971564, "percentage": 33.97, "elapsed_time": "0:44:35", "remaining_time": "1:26:42"}
45
  {"current_steps": 440, "total_steps": 1266, "loss": 0.2762, "lr": 5e-06, "epoch": 1.042654028436019, "percentage": 34.76, "elapsed_time": "0:45:34", "remaining_time": "1:25:33"}
46
  {"current_steps": 450, "total_steps": 1266, "loss": 0.2734, "lr": 5e-06, "epoch": 1.066350710900474, "percentage": 35.55, "elapsed_time": "0:46:32", "remaining_time": "1:24:24"}
47
+ {"current_steps": 460, "total_steps": 1266, "loss": 0.2769, "lr": 5e-06, "epoch": 1.0900473933649288, "percentage": 36.33, "elapsed_time": "0:47:30", "remaining_time": "1:23:15"}
48
+ {"current_steps": 470, "total_steps": 1266, "loss": 0.273, "lr": 5e-06, "epoch": 1.113744075829384, "percentage": 37.12, "elapsed_time": "0:48:29", "remaining_time": "1:22:07"}
49
+ {"current_steps": 480, "total_steps": 1266, "loss": 0.2763, "lr": 5e-06, "epoch": 1.1374407582938388, "percentage": 37.91, "elapsed_time": "0:49:28", "remaining_time": "1:21:00"}
50
+ {"current_steps": 490, "total_steps": 1266, "loss": 0.2779, "lr": 5e-06, "epoch": 1.161137440758294, "percentage": 38.7, "elapsed_time": "0:50:27", "remaining_time": "1:19:54"}
51
+ {"current_steps": 500, "total_steps": 1266, "loss": 0.2745, "lr": 5e-06, "epoch": 1.1848341232227488, "percentage": 39.49, "elapsed_time": "0:51:27", "remaining_time": "1:18:50"}
52
+ {"current_steps": 510, "total_steps": 1266, "loss": 0.2754, "lr": 5e-06, "epoch": 1.2085308056872037, "percentage": 40.28, "elapsed_time": "0:52:25", "remaining_time": "1:17:43"}
53
+ {"current_steps": 520, "total_steps": 1266, "loss": 0.2731, "lr": 5e-06, "epoch": 1.2322274881516588, "percentage": 41.07, "elapsed_time": "0:53:24", "remaining_time": "1:16:37"}
54
+ {"current_steps": 530, "total_steps": 1266, "loss": 0.2739, "lr": 5e-06, "epoch": 1.2559241706161137, "percentage": 41.86, "elapsed_time": "0:54:23", "remaining_time": "1:15:31"}
55
+ {"current_steps": 540, "total_steps": 1266, "loss": 0.2714, "lr": 5e-06, "epoch": 1.2796208530805688, "percentage": 42.65, "elapsed_time": "0:55:22", "remaining_time": "1:14:26"}
56
+ {"current_steps": 550, "total_steps": 1266, "loss": 0.2737, "lr": 5e-06, "epoch": 1.3033175355450237, "percentage": 43.44, "elapsed_time": "0:56:20", "remaining_time": "1:13:20"}
57
+ {"current_steps": 560, "total_steps": 1266, "loss": 0.2751, "lr": 5e-06, "epoch": 1.3270142180094786, "percentage": 44.23, "elapsed_time": "0:57:18", "remaining_time": "1:12:15"}
58
+ {"current_steps": 570, "total_steps": 1266, "loss": 0.2745, "lr": 5e-06, "epoch": 1.3507109004739337, "percentage": 45.02, "elapsed_time": "0:58:16", "remaining_time": "1:11:09"}
59
+ {"current_steps": 580, "total_steps": 1266, "loss": 0.2734, "lr": 5e-06, "epoch": 1.3744075829383886, "percentage": 45.81, "elapsed_time": "0:59:15", "remaining_time": "1:10:05"}
60
+ {"current_steps": 590, "total_steps": 1266, "loss": 0.2738, "lr": 5e-06, "epoch": 1.3981042654028437, "percentage": 46.6, "elapsed_time": "1:00:13", "remaining_time": "1:09:00"}
61
+ {"current_steps": 600, "total_steps": 1266, "loss": 0.2744, "lr": 5e-06, "epoch": 1.4218009478672986, "percentage": 47.39, "elapsed_time": "1:01:12", "remaining_time": "1:07:56"}
62
+ {"current_steps": 610, "total_steps": 1266, "loss": 0.2721, "lr": 5e-06, "epoch": 1.4454976303317535, "percentage": 48.18, "elapsed_time": "1:02:12", "remaining_time": "1:06:53"}
63
+ {"current_steps": 620, "total_steps": 1266, "loss": 0.2732, "lr": 5e-06, "epoch": 1.4691943127962086, "percentage": 48.97, "elapsed_time": "1:03:11", "remaining_time": "1:05:50"}
64
+ {"current_steps": 630, "total_steps": 1266, "loss": 0.2725, "lr": 5e-06, "epoch": 1.4928909952606635, "percentage": 49.76, "elapsed_time": "1:04:10", "remaining_time": "1:04:47"}
65
+ {"current_steps": 640, "total_steps": 1266, "loss": 0.2665, "lr": 5e-06, "epoch": 1.5165876777251186, "percentage": 50.55, "elapsed_time": "1:05:10", "remaining_time": "1:03:45"}
66
+ {"current_steps": 650, "total_steps": 1266, "loss": 0.2697, "lr": 5e-06, "epoch": 1.5402843601895735, "percentage": 51.34, "elapsed_time": "1:06:08", "remaining_time": "1:02:41"}
67
+ {"current_steps": 660, "total_steps": 1266, "loss": 0.2673, "lr": 5e-06, "epoch": 1.5639810426540284, "percentage": 52.13, "elapsed_time": "1:07:08", "remaining_time": "1:01:39"}
68
+ {"current_steps": 670, "total_steps": 1266, "loss": 0.274, "lr": 5e-06, "epoch": 1.5876777251184833, "percentage": 52.92, "elapsed_time": "1:08:08", "remaining_time": "1:00:36"}
69
+ {"current_steps": 680, "total_steps": 1266, "loss": 0.2702, "lr": 5e-06, "epoch": 1.6113744075829384, "percentage": 53.71, "elapsed_time": "1:09:06", "remaining_time": "0:59:33"}
70
+ {"current_steps": 690, "total_steps": 1266, "loss": 0.2695, "lr": 5e-06, "epoch": 1.6350710900473935, "percentage": 54.5, "elapsed_time": "1:10:05", "remaining_time": "0:58:30"}
71
+ {"current_steps": 700, "total_steps": 1266, "loss": 0.2686, "lr": 5e-06, "epoch": 1.6587677725118484, "percentage": 55.29, "elapsed_time": "1:11:03", "remaining_time": "0:57:27"}
72
+ {"current_steps": 710, "total_steps": 1266, "loss": 0.2707, "lr": 5e-06, "epoch": 1.6824644549763033, "percentage": 56.08, "elapsed_time": "1:12:01", "remaining_time": "0:56:24"}
73
+ {"current_steps": 720, "total_steps": 1266, "loss": 0.2669, "lr": 5e-06, "epoch": 1.7061611374407581, "percentage": 56.87, "elapsed_time": "1:13:00", "remaining_time": "0:55:21"}
74
+ {"current_steps": 730, "total_steps": 1266, "loss": 0.2658, "lr": 5e-06, "epoch": 1.7298578199052133, "percentage": 57.66, "elapsed_time": "1:13:58", "remaining_time": "0:54:19"}
75
+ {"current_steps": 740, "total_steps": 1266, "loss": 0.2687, "lr": 5e-06, "epoch": 1.7535545023696684, "percentage": 58.45, "elapsed_time": "1:14:57", "remaining_time": "0:53:16"}
76
+ {"current_steps": 750, "total_steps": 1266, "loss": 0.2704, "lr": 5e-06, "epoch": 1.7772511848341233, "percentage": 59.24, "elapsed_time": "1:15:55", "remaining_time": "0:52:14"}
77
+ {"current_steps": 760, "total_steps": 1266, "loss": 0.2673, "lr": 5e-06, "epoch": 1.8009478672985781, "percentage": 60.03, "elapsed_time": "1:16:55", "remaining_time": "0:51:13"}
78
+ {"current_steps": 770, "total_steps": 1266, "loss": 0.2693, "lr": 5e-06, "epoch": 1.824644549763033, "percentage": 60.82, "elapsed_time": "1:17:54", "remaining_time": "0:50:11"}
79
+ {"current_steps": 780, "total_steps": 1266, "loss": 0.2652, "lr": 5e-06, "epoch": 1.8483412322274881, "percentage": 61.61, "elapsed_time": "1:18:53", "remaining_time": "0:49:09"}
80
+ {"current_steps": 790, "total_steps": 1266, "loss": 0.264, "lr": 5e-06, "epoch": 1.8720379146919433, "percentage": 62.4, "elapsed_time": "1:19:52", "remaining_time": "0:48:07"}
81
+ {"current_steps": 800, "total_steps": 1266, "loss": 0.2707, "lr": 5e-06, "epoch": 1.8957345971563981, "percentage": 63.19, "elapsed_time": "1:20:50", "remaining_time": "0:47:05"}
82
+ {"current_steps": 810, "total_steps": 1266, "loss": 0.2645, "lr": 5e-06, "epoch": 1.919431279620853, "percentage": 63.98, "elapsed_time": "1:21:48", "remaining_time": "0:46:03"}
83
+ {"current_steps": 820, "total_steps": 1266, "loss": 0.2627, "lr": 5e-06, "epoch": 1.943127962085308, "percentage": 64.77, "elapsed_time": "1:22:47", "remaining_time": "0:45:01"}
84
+ {"current_steps": 830, "total_steps": 1266, "loss": 0.2663, "lr": 5e-06, "epoch": 1.966824644549763, "percentage": 65.56, "elapsed_time": "1:23:45", "remaining_time": "0:43:59"}
85
+ {"current_steps": 840, "total_steps": 1266, "loss": 0.2676, "lr": 5e-06, "epoch": 1.9905213270142181, "percentage": 66.35, "elapsed_time": "1:24:44", "remaining_time": "0:42:58"}
86
+ {"current_steps": 844, "total_steps": 1266, "eval_loss": 0.30145883560180664, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:25:50", "remaining_time": "0:42:55"}
87
+ {"current_steps": 850, "total_steps": 1266, "loss": 0.2369, "lr": 5e-06, "epoch": 2.014218009478673, "percentage": 67.14, "elapsed_time": "1:28:00", "remaining_time": "0:43:04"}
88
+ {"current_steps": 860, "total_steps": 1266, "loss": 0.2195, "lr": 5e-06, "epoch": 2.037914691943128, "percentage": 67.93, "elapsed_time": "1:28:58", "remaining_time": "0:42:00"}
89
+ {"current_steps": 870, "total_steps": 1266, "loss": 0.2199, "lr": 5e-06, "epoch": 2.061611374407583, "percentage": 68.72, "elapsed_time": "1:29:59", "remaining_time": "0:40:57"}