Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_dcft_v1_wo_camel_chemistry_gpt-4o-mini

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
097f626
·
verified ·
1 Parent(s): 8ba75f4

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:e4dcc352452339368631510eb585a4b54b07df75d797460d956a08a629458bd3
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a1b21aabea5268cd3ac16974f315ee3db56c86563ecbf2fd1575c57e10fd20
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a646a368530dd5df91959a1472fd61d0e7d5951be7a0668ea27b14ae0d6d3c0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472ba41c999747e7ee26f92805828d748ce924ab0562a12d9a8e8205bbedff8d
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:587ddcf24a09fb312483ebd10f830965fa40364a18b19dfbdcd3df20e42dea1d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4968182b2eb09b8f8a8795ef6feb173e381d6802b2c125e1a45409eaff03c85e
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:615a4f3672f5d99663fa05e05f5b9e33bae4f17efb935438b90d5228d911faac
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454c63db601b9275d8965b5a6538330f0cb81b48a965a448ef12e41aca901d78
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -40,3 +40,43 @@
40
  {"current_steps": 390, "total_steps": 1167, "loss": 0.5767, "learning_rate": 5e-06, "epoch": 1.0025706940874035, "percentage": 33.42, "elapsed_time": "0:45:19", "remaining_time": "1:30:18"}
41
  {"current_steps": 400, "total_steps": 1167, "loss": 0.546, "learning_rate": 5e-06, "epoch": 1.0282776349614395, "percentage": 34.28, "elapsed_time": "0:46:21", "remaining_time": "1:28:54"}
42
  {"current_steps": 410, "total_steps": 1167, "loss": 0.5478, "learning_rate": 5e-06, "epoch": 1.0539845758354756, "percentage": 35.13, "elapsed_time": "0:47:24", "remaining_time": "1:27:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  {"current_steps": 390, "total_steps": 1167, "loss": 0.5767, "learning_rate": 5e-06, "epoch": 1.0025706940874035, "percentage": 33.42, "elapsed_time": "0:45:19", "remaining_time": "1:30:18"}
41
  {"current_steps": 400, "total_steps": 1167, "loss": 0.546, "learning_rate": 5e-06, "epoch": 1.0282776349614395, "percentage": 34.28, "elapsed_time": "0:46:21", "remaining_time": "1:28:54"}
42
  {"current_steps": 410, "total_steps": 1167, "loss": 0.5478, "learning_rate": 5e-06, "epoch": 1.0539845758354756, "percentage": 35.13, "elapsed_time": "0:47:24", "remaining_time": "1:27:31"}
43
+ {"current_steps": 420, "total_steps": 1167, "loss": 0.5436, "learning_rate": 5e-06, "epoch": 1.0796915167095116, "percentage": 35.99, "elapsed_time": "0:48:26", "remaining_time": "1:26:09"}
44
+ {"current_steps": 430, "total_steps": 1167, "loss": 0.5406, "learning_rate": 5e-06, "epoch": 1.1053984575835476, "percentage": 36.85, "elapsed_time": "0:49:29", "remaining_time": "1:24:49"}
45
+ {"current_steps": 440, "total_steps": 1167, "loss": 0.5446, "learning_rate": 5e-06, "epoch": 1.1311053984575836, "percentage": 37.7, "elapsed_time": "0:50:31", "remaining_time": "1:23:28"}
46
+ {"current_steps": 450, "total_steps": 1167, "loss": 0.545, "learning_rate": 5e-06, "epoch": 1.1568123393316196, "percentage": 38.56, "elapsed_time": "0:51:34", "remaining_time": "1:22:09"}
47
+ {"current_steps": 460, "total_steps": 1167, "loss": 0.5405, "learning_rate": 5e-06, "epoch": 1.1825192802056554, "percentage": 39.42, "elapsed_time": "0:52:36", "remaining_time": "1:20:51"}
48
+ {"current_steps": 470, "total_steps": 1167, "loss": 0.5434, "learning_rate": 5e-06, "epoch": 1.2082262210796915, "percentage": 40.27, "elapsed_time": "0:53:38", "remaining_time": "1:19:33"}
49
+ {"current_steps": 480, "total_steps": 1167, "loss": 0.5458, "learning_rate": 5e-06, "epoch": 1.2339331619537275, "percentage": 41.13, "elapsed_time": "0:54:41", "remaining_time": "1:18:16"}
50
+ {"current_steps": 490, "total_steps": 1167, "loss": 0.5419, "learning_rate": 5e-06, "epoch": 1.2596401028277635, "percentage": 41.99, "elapsed_time": "0:55:44", "remaining_time": "1:17:00"}
51
+ {"current_steps": 500, "total_steps": 1167, "loss": 0.5399, "learning_rate": 5e-06, "epoch": 1.2853470437017995, "percentage": 42.84, "elapsed_time": "0:56:46", "remaining_time": "1:15:44"}
52
+ {"current_steps": 510, "total_steps": 1167, "loss": 0.5429, "learning_rate": 5e-06, "epoch": 1.3110539845758356, "percentage": 43.7, "elapsed_time": "0:57:49", "remaining_time": "1:14:29"}
53
+ {"current_steps": 520, "total_steps": 1167, "loss": 0.5372, "learning_rate": 5e-06, "epoch": 1.3367609254498714, "percentage": 44.56, "elapsed_time": "0:58:51", "remaining_time": "1:13:14"}
54
+ {"current_steps": 530, "total_steps": 1167, "loss": 0.5335, "learning_rate": 5e-06, "epoch": 1.3624678663239074, "percentage": 45.42, "elapsed_time": "0:59:54", "remaining_time": "1:12:00"}
55
+ {"current_steps": 540, "total_steps": 1167, "loss": 0.5361, "learning_rate": 5e-06, "epoch": 1.3881748071979434, "percentage": 46.27, "elapsed_time": "1:00:57", "remaining_time": "1:10:46"}
56
+ {"current_steps": 550, "total_steps": 1167, "loss": 0.5399, "learning_rate": 5e-06, "epoch": 1.4138817480719794, "percentage": 47.13, "elapsed_time": "1:01:59", "remaining_time": "1:09:32"}
57
+ {"current_steps": 560, "total_steps": 1167, "loss": 0.5426, "learning_rate": 5e-06, "epoch": 1.4395886889460154, "percentage": 47.99, "elapsed_time": "1:03:02", "remaining_time": "1:08:19"}
58
+ {"current_steps": 570, "total_steps": 1167, "loss": 0.5392, "learning_rate": 5e-06, "epoch": 1.4652956298200515, "percentage": 48.84, "elapsed_time": "1:04:04", "remaining_time": "1:07:06"}
59
+ {"current_steps": 580, "total_steps": 1167, "loss": 0.5355, "learning_rate": 5e-06, "epoch": 1.4910025706940875, "percentage": 49.7, "elapsed_time": "1:05:07", "remaining_time": "1:05:54"}
60
+ {"current_steps": 590, "total_steps": 1167, "loss": 0.5388, "learning_rate": 5e-06, "epoch": 1.5167095115681235, "percentage": 50.56, "elapsed_time": "1:06:10", "remaining_time": "1:04:42"}
61
+ {"current_steps": 600, "total_steps": 1167, "loss": 0.5351, "learning_rate": 5e-06, "epoch": 1.5424164524421595, "percentage": 51.41, "elapsed_time": "1:07:13", "remaining_time": "1:03:31"}
62
+ {"current_steps": 610, "total_steps": 1167, "loss": 0.5368, "learning_rate": 5e-06, "epoch": 1.5681233933161953, "percentage": 52.27, "elapsed_time": "1:08:16", "remaining_time": "1:02:20"}
63
+ {"current_steps": 620, "total_steps": 1167, "loss": 0.5274, "learning_rate": 5e-06, "epoch": 1.5938303341902313, "percentage": 53.13, "elapsed_time": "1:09:18", "remaining_time": "1:01:09"}
64
+ {"current_steps": 630, "total_steps": 1167, "loss": 0.5335, "learning_rate": 5e-06, "epoch": 1.6195372750642674, "percentage": 53.98, "elapsed_time": "1:10:21", "remaining_time": "0:59:58"}
65
+ {"current_steps": 640, "total_steps": 1167, "loss": 0.5282, "learning_rate": 5e-06, "epoch": 1.6452442159383034, "percentage": 54.84, "elapsed_time": "1:11:25", "remaining_time": "0:58:48"}
66
+ {"current_steps": 650, "total_steps": 1167, "loss": 0.5357, "learning_rate": 5e-06, "epoch": 1.6709511568123392, "percentage": 55.7, "elapsed_time": "1:12:30", "remaining_time": "0:57:40"}
67
+ {"current_steps": 660, "total_steps": 1167, "loss": 0.5281, "learning_rate": 5e-06, "epoch": 1.6966580976863752, "percentage": 56.56, "elapsed_time": "1:13:32", "remaining_time": "0:56:29"}
68
+ {"current_steps": 670, "total_steps": 1167, "loss": 0.532, "learning_rate": 5e-06, "epoch": 1.7223650385604112, "percentage": 57.41, "elapsed_time": "1:14:35", "remaining_time": "0:55:19"}
69
+ {"current_steps": 680, "total_steps": 1167, "loss": 0.5356, "learning_rate": 5e-06, "epoch": 1.7480719794344473, "percentage": 58.27, "elapsed_time": "1:15:38", "remaining_time": "0:54:10"}
70
+ {"current_steps": 690, "total_steps": 1167, "loss": 0.5275, "learning_rate": 5e-06, "epoch": 1.7737789203084833, "percentage": 59.13, "elapsed_time": "1:16:41", "remaining_time": "0:53:00"}
71
+ {"current_steps": 700, "total_steps": 1167, "loss": 0.5357, "learning_rate": 5e-06, "epoch": 1.7994858611825193, "percentage": 59.98, "elapsed_time": "1:17:43", "remaining_time": "0:51:51"}
72
+ {"current_steps": 710, "total_steps": 1167, "loss": 0.5279, "learning_rate": 5e-06, "epoch": 1.8251928020565553, "percentage": 60.84, "elapsed_time": "1:18:45", "remaining_time": "0:50:41"}
73
+ {"current_steps": 720, "total_steps": 1167, "loss": 0.5288, "learning_rate": 5e-06, "epoch": 1.8508997429305913, "percentage": 61.7, "elapsed_time": "1:19:48", "remaining_time": "0:49:32"}
74
+ {"current_steps": 730, "total_steps": 1167, "loss": 0.5292, "learning_rate": 5e-06, "epoch": 1.8766066838046274, "percentage": 62.55, "elapsed_time": "1:20:51", "remaining_time": "0:48:24"}
75
+ {"current_steps": 740, "total_steps": 1167, "loss": 0.5271, "learning_rate": 5e-06, "epoch": 1.9023136246786634, "percentage": 63.41, "elapsed_time": "1:21:53", "remaining_time": "0:47:15"}
76
+ {"current_steps": 750, "total_steps": 1167, "loss": 0.5277, "learning_rate": 5e-06, "epoch": 1.9280205655526992, "percentage": 64.27, "elapsed_time": "1:22:56", "remaining_time": "0:46:06"}
77
+ {"current_steps": 760, "total_steps": 1167, "loss": 0.5268, "learning_rate": 5e-06, "epoch": 1.9537275064267352, "percentage": 65.12, "elapsed_time": "1:24:00", "remaining_time": "0:44:59"}
78
+ {"current_steps": 770, "total_steps": 1167, "loss": 0.5297, "learning_rate": 5e-06, "epoch": 1.9794344473007712, "percentage": 65.98, "elapsed_time": "1:25:06", "remaining_time": "0:43:52"}
79
+ {"current_steps": 778, "total_steps": 1167, "eval_loss": 0.5520427227020264, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:26:35", "remaining_time": "0:43:17"}
80
+ {"current_steps": 780, "total_steps": 1167, "loss": 0.5175, "learning_rate": 5e-06, "epoch": 2.005141388174807, "percentage": 66.84, "elapsed_time": "1:30:44", "remaining_time": "0:45:01"}
81
+ {"current_steps": 790, "total_steps": 1167, "loss": 0.4906, "learning_rate": 5e-06, "epoch": 2.030848329048843, "percentage": 67.69, "elapsed_time": "1:31:46", "remaining_time": "0:43:47"}
82
+ {"current_steps": 800, "total_steps": 1167, "loss": 0.4893, "learning_rate": 5e-06, "epoch": 2.056555269922879, "percentage": 68.55, "elapsed_time": "1:32:48", "remaining_time": "0:42:34"}