Hugging Face's logo

mlfoundations-dev
/
mistral_7b_0-3_oh-dcft-v3.1-llama-3.1-70b

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
gsmyrnis commited on
Commit
ff44ce4
·
verified ·
1 Parent(s): ad7c99a

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 +48 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49c8598964f73b81d1193567553d6589147d71a91b75804e19eb20445c9f81aa
3
  size 4949453792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52fc98c43906faab05c1813e058c87fd219fea801456c4e76953508aacba20bb
3
  size 4949453792
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64aa3c733c601ba9b65d1d45571e19ff1284f79531fb7bde822f591d03ace24d
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68a024292cde277d36cc83965b268b68fa1244aae0d59b667d9afa9aa2bd3ea
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3d455f1466a6e3e55a56ab6b3576973c7be761b6de18e2dff651f02d805a2fc
3
  size 4546807800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035a6b88018731b0495043d2dcbbf3cb07256ba56b758c65ac172bb95207e490
3
  size 4546807800
trainer_log.jsonl CHANGED
@@ -49,3 +49,51 @@
49
  {"current_steps": 480, "total_steps": 1419, "loss": 0.2656, "lr": 4.052926668808791e-06, "epoch": 1.014799154334038, "percentage": 33.83, "elapsed_time": "0:47:56", "remaining_time": "1:33:46"}
50
  {"current_steps": 490, "total_steps": 1419, "loss": 0.2439, "lr": 4.009825847318922e-06, "epoch": 1.0359408033826638, "percentage": 34.53, "elapsed_time": "0:48:56", "remaining_time": "1:32:46"}
51
  {"current_steps": 500, "total_steps": 1419, "loss": 0.2422, "lr": 3.966040782112451e-06, "epoch": 1.0570824524312896, "percentage": 35.24, "elapsed_time": "0:49:55", "remaining_time": "1:31:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  {"current_steps": 480, "total_steps": 1419, "loss": 0.2656, "lr": 4.052926668808791e-06, "epoch": 1.014799154334038, "percentage": 33.83, "elapsed_time": "0:47:56", "remaining_time": "1:33:46"}
50
  {"current_steps": 490, "total_steps": 1419, "loss": 0.2439, "lr": 4.009825847318922e-06, "epoch": 1.0359408033826638, "percentage": 34.53, "elapsed_time": "0:48:56", "remaining_time": "1:32:46"}
51
  {"current_steps": 500, "total_steps": 1419, "loss": 0.2422, "lr": 3.966040782112451e-06, "epoch": 1.0570824524312896, "percentage": 35.24, "elapsed_time": "0:49:55", "remaining_time": "1:31:45"}
52
+ {"current_steps": 510, "total_steps": 1419, "loss": 0.2425, "lr": 3.921595253980836e-06, "epoch": 1.0782241014799154, "percentage": 35.94, "elapsed_time": "0:50:54", "remaining_time": "1:30:44"}
53
+ {"current_steps": 520, "total_steps": 1419, "loss": 0.2431, "lr": 3.876513402429883e-06, "epoch": 1.0993657505285412, "percentage": 36.65, "elapsed_time": "0:51:54", "remaining_time": "1:29:43"}
54
+ {"current_steps": 530, "total_steps": 1419, "loss": 0.2413, "lr": 3.83081971256896e-06, "epoch": 1.120507399577167, "percentage": 37.35, "elapsed_time": "0:52:53", "remaining_time": "1:28:42"}
55
+ {"current_steps": 540, "total_steps": 1419, "loss": 0.2454, "lr": 3.7845390018125065e-06, "epoch": 1.1416490486257929, "percentage": 38.05, "elapsed_time": "0:53:52", "remaining_time": "1:27:41"}
56
+ {"current_steps": 550, "total_steps": 1419, "loss": 0.2394, "lr": 3.737696406401062e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "0:54:52", "remaining_time": "1:26:41"}
57
+ {"current_steps": 560, "total_steps": 1419, "loss": 0.2448, "lr": 3.6903173677491266e-06, "epoch": 1.1839323467230445, "percentage": 39.46, "elapsed_time": "0:55:51", "remaining_time": "1:25:41"}
58
+ {"current_steps": 570, "total_steps": 1419, "loss": 0.2437, "lr": 3.642427618627277e-06, "epoch": 1.20507399577167, "percentage": 40.17, "elapsed_time": "0:56:50", "remaining_time": "1:24:40"}
59
+ {"current_steps": 580, "total_steps": 1419, "loss": 0.2428, "lr": 3.5940531691860405e-06, "epoch": 1.226215644820296, "percentage": 40.87, "elapsed_time": "0:57:50", "remaining_time": "1:23:40"}
60
+ {"current_steps": 590, "total_steps": 1419, "loss": 0.2403, "lr": 3.545220292829113e-06, "epoch": 1.2473572938689217, "percentage": 41.58, "elapsed_time": "0:58:51", "remaining_time": "1:22:41"}
61
+ {"current_steps": 600, "total_steps": 1419, "loss": 0.2425, "lr": 3.4959555119436033e-06, "epoch": 1.2684989429175475, "percentage": 42.28, "elapsed_time": "0:59:50", "remaining_time": "1:21:41"}
62
+ {"current_steps": 610, "total_steps": 1419, "loss": 0.2419, "lr": 3.446285583495041e-06, "epoch": 1.2896405919661733, "percentage": 42.99, "elapsed_time": "1:00:50", "remaining_time": "1:20:41"}
63
+ {"current_steps": 620, "total_steps": 1419, "loss": 0.2434, "lr": 3.396237484494985e-06, "epoch": 1.3107822410147991, "percentage": 43.69, "elapsed_time": "1:01:49", "remaining_time": "1:19:40"}
64
+ {"current_steps": 630, "total_steps": 1419, "loss": 0.2413, "lr": 3.345838397349115e-06, "epoch": 1.331923890063425, "percentage": 44.4, "elapsed_time": "1:02:49", "remaining_time": "1:18:40"}
65
+ {"current_steps": 640, "total_steps": 1419, "loss": 0.243, "lr": 3.2951156950937728e-06, "epoch": 1.3530655391120507, "percentage": 45.1, "elapsed_time": "1:03:47", "remaining_time": "1:17:39"}
66
+ {"current_steps": 650, "total_steps": 1419, "loss": 0.2421, "lr": 3.2440969265289624e-06, "epoch": 1.3742071881606766, "percentage": 45.81, "elapsed_time": "1:04:46", "remaining_time": "1:16:37"}
67
+ {"current_steps": 660, "total_steps": 1419, "loss": 0.244, "lr": 3.1928098012558895e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:05:44", "remaining_time": "1:15:36"}
68
+ {"current_steps": 670, "total_steps": 1419, "loss": 0.2439, "lr": 3.1412821746271693e-06, "epoch": 1.4164904862579282, "percentage": 47.22, "elapsed_time": "1:06:42", "remaining_time": "1:14:34"}
69
+ {"current_steps": 680, "total_steps": 1419, "loss": 0.2408, "lr": 3.0895420326178705e-06, "epoch": 1.437632135306554, "percentage": 47.92, "elapsed_time": "1:07:42", "remaining_time": "1:13:34"}
70
+ {"current_steps": 690, "total_steps": 1419, "loss": 0.2423, "lr": 3.03761747662561e-06, "epoch": 1.4587737843551798, "percentage": 48.63, "elapsed_time": "1:08:42", "remaining_time": "1:12:35"}
71
+ {"current_steps": 700, "total_steps": 1419, "loss": 0.2401, "lr": 2.985536708207971e-06, "epoch": 1.4799154334038054, "percentage": 49.33, "elapsed_time": "1:09:41", "remaining_time": "1:11:35"}
72
+ {"current_steps": 710, "total_steps": 1419, "loss": 0.2449, "lr": 2.933328013765505e-06, "epoch": 1.5010570824524314, "percentage": 50.04, "elapsed_time": "1:10:40", "remaining_time": "1:10:34"}
73
+ {"current_steps": 720, "total_steps": 1419, "loss": 0.2431, "lr": 2.8810197491786714e-06, "epoch": 1.522198731501057, "percentage": 50.74, "elapsed_time": "1:11:40", "remaining_time": "1:09:34"}
74
+ {"current_steps": 730, "total_steps": 1419, "loss": 0.2414, "lr": 2.8286403244070252e-06, "epoch": 1.543340380549683, "percentage": 51.44, "elapsed_time": "1:12:39", "remaining_time": "1:08:34"}
75
+ {"current_steps": 740, "total_steps": 1419, "loss": 0.2415, "lr": 2.7762181880590442e-06, "epoch": 1.5644820295983086, "percentage": 52.15, "elapsed_time": "1:13:38", "remaining_time": "1:07:33"}
76
+ {"current_steps": 750, "total_steps": 1419, "loss": 0.2431, "lr": 2.723781811940956e-06, "epoch": 1.5856236786469344, "percentage": 52.85, "elapsed_time": "1:14:37", "remaining_time": "1:06:33"}
77
+ {"current_steps": 760, "total_steps": 1419, "loss": 0.2417, "lr": 2.6713596755929755e-06, "epoch": 1.6067653276955602, "percentage": 53.56, "elapsed_time": "1:15:37", "remaining_time": "1:05:34"}
78
+ {"current_steps": 770, "total_steps": 1419, "loss": 0.2391, "lr": 2.6189802508213297e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:16:35", "remaining_time": "1:04:33"}
79
+ {"current_steps": 780, "total_steps": 1419, "loss": 0.2445, "lr": 2.5666719862344957e-06, "epoch": 1.6490486257928119, "percentage": 54.97, "elapsed_time": "1:17:35", "remaining_time": "1:03:34"}
80
+ {"current_steps": 790, "total_steps": 1419, "loss": 0.2409, "lr": 2.51446329179203e-06, "epoch": 1.6701902748414377, "percentage": 55.67, "elapsed_time": "1:18:34", "remaining_time": "1:02:33"}
81
+ {"current_steps": 800, "total_steps": 1419, "loss": 0.241, "lr": 2.4623825233743896e-06, "epoch": 1.6913319238900635, "percentage": 56.38, "elapsed_time": "1:19:33", "remaining_time": "1:01:33"}
82
+ {"current_steps": 810, "total_steps": 1419, "loss": 0.2434, "lr": 2.4104579673821297e-06, "epoch": 1.712473572938689, "percentage": 57.08, "elapsed_time": "1:20:33", "remaining_time": "1:00:33"}
83
+ {"current_steps": 820, "total_steps": 1419, "loss": 0.2413, "lr": 2.358717825372831e-06, "epoch": 1.733615221987315, "percentage": 57.79, "elapsed_time": "1:21:31", "remaining_time": "0:59:33"}
84
+ {"current_steps": 830, "total_steps": 1419, "loss": 0.2385, "lr": 2.3071901987441116e-06, "epoch": 1.7547568710359407, "percentage": 58.49, "elapsed_time": "1:22:32", "remaining_time": "0:58:34"}
85
+ {"current_steps": 840, "total_steps": 1419, "loss": 0.2386, "lr": 2.2559030734710396e-06, "epoch": 1.7758985200845667, "percentage": 59.2, "elapsed_time": "1:23:31", "remaining_time": "0:57:34"}
86
+ {"current_steps": 850, "total_steps": 1419, "loss": 0.2398, "lr": 2.2048843049062275e-06, "epoch": 1.7970401691331923, "percentage": 59.9, "elapsed_time": "1:24:30", "remaining_time": "0:56:34"}
87
+ {"current_steps": 860, "total_steps": 1419, "loss": 0.2413, "lr": 2.1541616026508854e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "1:25:29", "remaining_time": "0:55:34"}
88
+ {"current_steps": 870, "total_steps": 1419, "loss": 0.2417, "lr": 2.103762515505016e-06, "epoch": 1.839323467230444, "percentage": 61.31, "elapsed_time": "1:26:28", "remaining_time": "0:54:34"}
89
+ {"current_steps": 880, "total_steps": 1419, "loss": 0.236, "lr": 2.0537144165049597e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:27:28", "remaining_time": "0:53:34"}
90
+ {"current_steps": 890, "total_steps": 1419, "loss": 0.2396, "lr": 2.0040444880563974e-06, "epoch": 1.8816067653276956, "percentage": 62.72, "elapsed_time": "1:28:27", "remaining_time": "0:52:34"}
91
+ {"current_steps": 900, "total_steps": 1419, "loss": 0.2402, "lr": 1.9547797071708873e-06, "epoch": 1.9027484143763214, "percentage": 63.42, "elapsed_time": "1:29:26", "remaining_time": "0:51:34"}
92
+ {"current_steps": 910, "total_steps": 1419, "loss": 0.2454, "lr": 1.90594683081396e-06, "epoch": 1.9238900634249472, "percentage": 64.13, "elapsed_time": "1:30:26", "remaining_time": "0:50:35"}
93
+ {"current_steps": 920, "total_steps": 1419, "loss": 0.241, "lr": 1.8575723813727234e-06, "epoch": 1.945031712473573, "percentage": 64.83, "elapsed_time": "1:31:25", "remaining_time": "0:49:35"}
94
+ {"current_steps": 930, "total_steps": 1419, "loss": 0.2377, "lr": 1.8096826322508745e-06, "epoch": 1.9661733615221988, "percentage": 65.54, "elapsed_time": "1:32:24", "remaining_time": "0:48:35"}
95
+ {"current_steps": 940, "total_steps": 1419, "loss": 0.2363, "lr": 1.7623035935989388e-06, "epoch": 1.9873150105708244, "percentage": 66.24, "elapsed_time": "1:33:24", "remaining_time": "0:47:35"}
96
+ {"current_steps": 946, "total_steps": 1419, "eval_loss": 0.3176339268684387, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:34:46", "remaining_time": "0:47:23"}
97
+ {"current_steps": 950, "total_steps": 1419, "loss": 0.2124, "lr": 1.7154609981874945e-06, "epoch": 2.0084566596194504, "percentage": 66.95, "elapsed_time": "1:36:23", "remaining_time": "0:47:35"}
98
+ {"current_steps": 960, "total_steps": 1419, "loss": 0.1655, "lr": 1.6691802874310402e-06, "epoch": 2.029598308668076, "percentage": 67.65, "elapsed_time": "1:37:24", "remaining_time": "0:46:34"}
99
+ {"current_steps": 970, "total_steps": 1419, "loss": 0.1695, "lr": 1.6234865975701169e-06, "epoch": 2.050739957716702, "percentage": 68.36, "elapsed_time": "1:38:23", "remaining_time": "0:45:32"}