Hugging Face's logo

mlfoundations-dev
/
mistral_7b_0-3_oh-dcft-v3.1-gpt-4o-2024-11-20

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
dd04709
·
verified ·
1 Parent(s): 528f21f

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 +53 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5f9db2bdf0c6aae5692a445fb103b542d481f915177f82995ecac0ab8f53c9e
3
  size 4949453792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409e10628f075e7a728f4f707a0b12bb1d8c8885e30a3292b12aa69a03789f5c
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:cb0b7025e9ee99bc70f0fa2c08c2d136104c8a83be1b18a8ca1f5c54b77ff9b0
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde077bef7eabaf0c170e66e265b77a4295440a5d5d0845997bd72a7d9fafa29
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:a982da7efd195f07fca05b6ba4bc361008775a35cd8dc4c66b42bb517c240715
3
  size 4546807800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc977eaba717c2df9d7976feafc8c1d4ae7a2050f8901f1a993911cadddab99
3
  size 4546807800
trainer_log.jsonl CHANGED
@@ -54,3 +54,56 @@
54
  {"current_steps": 530, "total_steps": 1578, "loss": 0.5901, "lr": 4.067552485346939e-06, "epoch": 1.0076045627376427, "percentage": 33.59, "elapsed_time": "0:53:56", "remaining_time": "1:46:39"}
55
  {"current_steps": 540, "total_steps": 1578, "loss": 0.546, "lr": 4.029041101540122e-06, "epoch": 1.026615969581749, "percentage": 34.22, "elapsed_time": "0:54:58", "remaining_time": "1:45:41"}
56
  {"current_steps": 550, "total_steps": 1578, "loss": 0.5434, "lr": 3.989967939272569e-06, "epoch": 1.0456273764258555, "percentage": 34.85, "elapsed_time": "0:55:59", "remaining_time": "1:44:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  {"current_steps": 530, "total_steps": 1578, "loss": 0.5901, "lr": 4.067552485346939e-06, "epoch": 1.0076045627376427, "percentage": 33.59, "elapsed_time": "0:53:56", "remaining_time": "1:46:39"}
55
  {"current_steps": 540, "total_steps": 1578, "loss": 0.546, "lr": 4.029041101540122e-06, "epoch": 1.026615969581749, "percentage": 34.22, "elapsed_time": "0:54:58", "remaining_time": "1:45:41"}
56
  {"current_steps": 550, "total_steps": 1578, "loss": 0.5434, "lr": 3.989967939272569e-06, "epoch": 1.0456273764258555, "percentage": 34.85, "elapsed_time": "0:55:59", "remaining_time": "1:44:38"}
57
+ {"current_steps": 560, "total_steps": 1578, "loss": 0.5365, "lr": 3.950350160198373e-06, "epoch": 1.064638783269962, "percentage": 35.49, "elapsed_time": "0:56:59", "remaining_time": "1:43:35"}
58
+ {"current_steps": 570, "total_steps": 1578, "loss": 0.5394, "lr": 3.91020516517738e-06, "epoch": 1.0836501901140685, "percentage": 36.12, "elapsed_time": "0:57:59", "remaining_time": "1:42:32"}
59
+ {"current_steps": 580, "total_steps": 1578, "loss": 0.5454, "lr": 3.869550586632413e-06, "epoch": 1.102661596958175, "percentage": 36.76, "elapsed_time": "0:59:01", "remaining_time": "1:41:33"}
60
+ {"current_steps": 590, "total_steps": 1578, "loss": 0.5437, "lr": 3.828404280804782e-06, "epoch": 1.1216730038022813, "percentage": 37.39, "elapsed_time": "1:00:01", "remaining_time": "1:40:31"}
61
+ {"current_steps": 600, "total_steps": 1578, "loss": 0.545, "lr": 3.7867843199114996e-06, "epoch": 1.1406844106463878, "percentage": 38.02, "elapsed_time": "1:01:01", "remaining_time": "1:39:29"}
62
+ {"current_steps": 610, "total_steps": 1578, "loss": 0.5401, "lr": 3.7447089842076238e-06, "epoch": 1.1596958174904943, "percentage": 38.66, "elapsed_time": "1:02:02", "remaining_time": "1:38:26"}
63
+ {"current_steps": 620, "total_steps": 1578, "loss": 0.5451, "lr": 3.7021967539572343e-06, "epoch": 1.1787072243346008, "percentage": 39.29, "elapsed_time": "1:03:02", "remaining_time": "1:37:25"}
64
+ {"current_steps": 630, "total_steps": 1578, "loss": 0.5413, "lr": 3.6592663013165636e-06, "epoch": 1.1977186311787071, "percentage": 39.92, "elapsed_time": "1:04:04", "remaining_time": "1:36:25"}
65
+ {"current_steps": 640, "total_steps": 1578, "loss": 0.5531, "lr": 3.6159364821328325e-06, "epoch": 1.2167300380228137, "percentage": 40.56, "elapsed_time": "1:05:04", "remaining_time": "1:35:22"}
66
+ {"current_steps": 650, "total_steps": 1578, "loss": 0.5481, "lr": 3.572226327662423e-06, "epoch": 1.2357414448669202, "percentage": 41.19, "elapsed_time": "1:06:04", "remaining_time": "1:34:20"}
67
+ {"current_steps": 660, "total_steps": 1578, "loss": 0.5402, "lr": 3.528155036211995e-06, "epoch": 1.2547528517110267, "percentage": 41.83, "elapsed_time": "1:07:04", "remaining_time": "1:33:17"}
68
+ {"current_steps": 670, "total_steps": 1578, "loss": 0.5452, "lr": 3.4837419647062344e-06, "epoch": 1.2737642585551332, "percentage": 42.46, "elapsed_time": "1:08:03", "remaining_time": "1:32:14"}
69
+ {"current_steps": 680, "total_steps": 1578, "loss": 0.5376, "lr": 3.4390066201859355e-06, "epoch": 1.2927756653992395, "percentage": 43.09, "elapsed_time": "1:09:03", "remaining_time": "1:31:11"}
70
+ {"current_steps": 690, "total_steps": 1578, "loss": 0.5442, "lr": 3.393968651240153e-06, "epoch": 1.311787072243346, "percentage": 43.73, "elapsed_time": "1:10:03", "remaining_time": "1:30:09"}
71
+ {"current_steps": 700, "total_steps": 1578, "loss": 0.5449, "lr": 3.3486478393761707e-06, "epoch": 1.3307984790874525, "percentage": 44.36, "elapsed_time": "1:11:04", "remaining_time": "1:29:09"}
72
+ {"current_steps": 710, "total_steps": 1578, "loss": 0.537, "lr": 3.303064090331106e-06, "epoch": 1.3498098859315588, "percentage": 44.99, "elapsed_time": "1:12:04", "remaining_time": "1:28:07"}
73
+ {"current_steps": 720, "total_steps": 1578, "loss": 0.5525, "lr": 3.2572374253289385e-06, "epoch": 1.3688212927756653, "percentage": 45.63, "elapsed_time": "1:13:04", "remaining_time": "1:27:05"}
74
+ {"current_steps": 730, "total_steps": 1578, "loss": 0.5513, "lr": 3.2111879722868204e-06, "epoch": 1.3878326996197718, "percentage": 46.26, "elapsed_time": "1:14:04", "remaining_time": "1:26:03"}
75
+ {"current_steps": 740, "total_steps": 1578, "loss": 0.5428, "lr": 3.164935956974522e-06, "epoch": 1.4068441064638784, "percentage": 46.89, "elapsed_time": "1:15:04", "remaining_time": "1:25:01"}
76
+ {"current_steps": 750, "total_steps": 1578, "loss": 0.5443, "lr": 3.1185016941309033e-06, "epoch": 1.4258555133079849, "percentage": 47.53, "elapsed_time": "1:16:06", "remaining_time": "1:24:01"}
77
+ {"current_steps": 760, "total_steps": 1578, "loss": 0.55, "lr": 3.071905578541304e-06, "epoch": 1.4448669201520912, "percentage": 48.16, "elapsed_time": "1:17:07", "remaining_time": "1:23:00"}
78
+ {"current_steps": 770, "total_steps": 1578, "loss": 0.5512, "lr": 3.0251680760797737e-06, "epoch": 1.4638783269961977, "percentage": 48.8, "elapsed_time": "1:18:07", "remaining_time": "1:21:58"}
79
+ {"current_steps": 780, "total_steps": 1578, "loss": 0.5457, "lr": 2.978309714720092e-06, "epoch": 1.4828897338403042, "percentage": 49.43, "elapsed_time": "1:19:07", "remaining_time": "1:20:57"}
80
+ {"current_steps": 790, "total_steps": 1578, "loss": 0.5472, "lr": 2.931351075519494e-06, "epoch": 1.5019011406844105, "percentage": 50.06, "elapsed_time": "1:20:09", "remaining_time": "1:19:56"}
81
+ {"current_steps": 800, "total_steps": 1578, "loss": 0.5467, "lr": 2.8843127835790922e-06, "epoch": 1.5209125475285172, "percentage": 50.7, "elapsed_time": "1:21:09", "remaining_time": "1:18:56"}
82
+ {"current_steps": 810, "total_steps": 1578, "loss": 0.5423, "lr": 2.837215498984956e-06, "epoch": 1.5399239543726235, "percentage": 51.33, "elapsed_time": "1:22:10", "remaining_time": "1:17:54"}
83
+ {"current_steps": 820, "total_steps": 1578, "loss": 0.5377, "lr": 2.7900799077338137e-06, "epoch": 1.55893536121673, "percentage": 51.96, "elapsed_time": "1:23:10", "remaining_time": "1:16:53"}
84
+ {"current_steps": 830, "total_steps": 1578, "loss": 0.5422, "lr": 2.742926712647389e-06, "epoch": 1.5779467680608366, "percentage": 52.6, "elapsed_time": "1:24:10", "remaining_time": "1:15:51"}
85
+ {"current_steps": 840, "total_steps": 1578, "loss": 0.5548, "lr": 2.6957766242793286e-06, "epoch": 1.5969581749049429, "percentage": 53.23, "elapsed_time": "1:25:12", "remaining_time": "1:14:51"}
86
+ {"current_steps": 850, "total_steps": 1578, "loss": 0.5396, "lr": 2.648650351818758e-06, "epoch": 1.6159695817490496, "percentage": 53.87, "elapsed_time": "1:26:13", "remaining_time": "1:13:50"}
87
+ {"current_steps": 860, "total_steps": 1578, "loss": 0.5443, "lr": 2.6015685939944113e-06, "epoch": 1.6349809885931559, "percentage": 54.5, "elapsed_time": "1:27:13", "remaining_time": "1:12:49"}
88
+ {"current_steps": 870, "total_steps": 1578, "loss": 0.5404, "lr": 2.554552029983375e-06, "epoch": 1.6539923954372624, "percentage": 55.13, "elapsed_time": "1:28:13", "remaining_time": "1:11:48"}
89
+ {"current_steps": 880, "total_steps": 1578, "loss": 0.5443, "lr": 2.5076213103284107e-06, "epoch": 1.673003802281369, "percentage": 55.77, "elapsed_time": "1:29:15", "remaining_time": "1:10:48"}
90
+ {"current_steps": 890, "total_steps": 1578, "loss": 0.5464, "lr": 2.4607970478678515e-06, "epoch": 1.6920152091254752, "percentage": 56.4, "elapsed_time": "1:30:16", "remaining_time": "1:09:47"}
91
+ {"current_steps": 900, "total_steps": 1578, "loss": 0.5447, "lr": 2.4140998086820665e-06, "epoch": 1.7110266159695817, "percentage": 57.03, "elapsed_time": "1:31:16", "remaining_time": "1:08:45"}
92
+ {"current_steps": 910, "total_steps": 1578, "loss": 0.5475, "lr": 2.367550103060459e-06, "epoch": 1.7300380228136882, "percentage": 57.67, "elapsed_time": "1:32:17", "remaining_time": "1:07:44"}
93
+ {"current_steps": 920, "total_steps": 1578, "loss": 0.5484, "lr": 2.3211683764929664e-06, "epoch": 1.7490494296577945, "percentage": 58.3, "elapsed_time": "1:33:19", "remaining_time": "1:06:44"}
94
+ {"current_steps": 930, "total_steps": 1578, "loss": 0.5431, "lr": 2.2749750006900263e-06, "epoch": 1.7680608365019013, "percentage": 58.94, "elapsed_time": "1:34:19", "remaining_time": "1:05:43"}
95
+ {"current_steps": 940, "total_steps": 1578, "loss": 0.5425, "lr": 2.2289902646349423e-06, "epoch": 1.7870722433460076, "percentage": 59.57, "elapsed_time": "1:35:20", "remaining_time": "1:04:42"}
96
+ {"current_steps": 950, "total_steps": 1578, "loss": 0.5459, "lr": 2.1832343656725918e-06, "epoch": 1.806083650190114, "percentage": 60.2, "elapsed_time": "1:36:21", "remaining_time": "1:03:41"}
97
+ {"current_steps": 960, "total_steps": 1578, "loss": 0.5394, "lr": 2.1377274006383737e-06, "epoch": 1.8250950570342206, "percentage": 60.84, "elapsed_time": "1:37:23", "remaining_time": "1:02:41"}
98
+ {"current_steps": 970, "total_steps": 1578, "loss": 0.5447, "lr": 2.092489357031315e-06, "epoch": 1.8441064638783269, "percentage": 61.47, "elapsed_time": "1:38:23", "remaining_time": "1:01:40"}
99
+ {"current_steps": 980, "total_steps": 1578, "loss": 0.5305, "lr": 2.0475401042351843e-06, "epoch": 1.8631178707224336, "percentage": 62.1, "elapsed_time": "1:39:23", "remaining_time": "1:00:38"}
100
+ {"current_steps": 990, "total_steps": 1578, "loss": 0.5395, "lr": 2.0028993847914966e-06, "epoch": 1.88212927756654, "percentage": 62.74, "elapsed_time": "1:40:24", "remaining_time": "0:59:38"}
101
+ {"current_steps": 1000, "total_steps": 1578, "loss": 0.5406, "lr": 1.9585868057282256e-06, "epoch": 1.9011406844106464, "percentage": 63.37, "elapsed_time": "1:41:25", "remaining_time": "0:58:37"}
102
+ {"current_steps": 1010, "total_steps": 1578, "loss": 0.5476, "lr": 1.9146218299480303e-06, "epoch": 1.920152091254753, "percentage": 64.01, "elapsed_time": "1:42:26", "remaining_time": "0:57:36"}
103
+ {"current_steps": 1020, "total_steps": 1578, "loss": 0.5429, "lr": 1.8710237676797923e-06, "epoch": 1.9391634980988592, "percentage": 64.64, "elapsed_time": "1:43:26", "remaining_time": "0:56:35"}
104
+ {"current_steps": 1030, "total_steps": 1578, "loss": 0.5419, "lr": 1.827811767997207e-06, "epoch": 1.9581749049429658, "percentage": 65.27, "elapsed_time": "1:44:26", "remaining_time": "0:55:34"}
105
+ {"current_steps": 1040, "total_steps": 1578, "loss": 0.5369, "lr": 1.7850048104081555e-06, "epoch": 1.9771863117870723, "percentage": 65.91, "elapsed_time": "1:45:28", "remaining_time": "0:54:33"}
106
+ {"current_steps": 1050, "total_steps": 1578, "loss": 0.5371, "lr": 1.742621696518555e-06, "epoch": 1.9961977186311786, "percentage": 66.54, "elapsed_time": "1:46:28", "remaining_time": "0:53:32"}
107
+ {"current_steps": 1052, "total_steps": 1578, "eval_loss": 0.6316379308700562, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:47:34", "remaining_time": "0:53:47"}
108
+ {"current_steps": 1060, "total_steps": 1578, "loss": 0.4716, "lr": 1.7006810417743453e-06, "epoch": 2.0152091254752853, "percentage": 67.17, "elapsed_time": "1:49:29", "remaining_time": "0:53:30"}
109
+ {"current_steps": 1070, "total_steps": 1578, "loss": 0.4592, "lr": 1.6592012672852462e-06, "epoch": 2.0342205323193916, "percentage": 67.81, "elapsed_time": "1:50:30", "remaining_time": "0:52:27"}