Hugging Face's logo

mlfoundations-dev
/
mistral_7b_0-3_oh-dcft-v3.1-gemini-1.5-flash

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
c26c9e4
•
1 Parent(s): 8db3889

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 +51 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e61fd624ddcf57b2001d3b87b5b17b0c5deab51b834e2c36b3b7488219a3b164
3
  size 4949453792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198b562de944d58b60212015e94e50e599aad1c495ed658034048a5bacad9379
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:f5324eb885da58b69a352f6bae2921cf388b2c145fb282481425cc2c545b224d
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67dde8b394c8f09bf910a56066bc55d16c001528d973f6ec049a957203411c0
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fc748ad638e710465b49abd4a361470a6325161c2aa5ecbf5ca95437e7892a6
3
  size 4546807800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7698c6f6938a74cdbadbbd2deb1e2d21a65b8edd6f905c117293f2db82808489
3
  size 4546807800
trainer_log.jsonl CHANGED
@@ -51,3 +51,54 @@
51
  {"current_steps": 500, "total_steps": 1497, "loss": 0.4942, "lr": 4.078942976815581e-06, "epoch": 1.002004008016032, "percentage": 33.4, "elapsed_time": "0:50:59", "remaining_time": "1:41:39"}
52
  {"current_steps": 510, "total_steps": 1497, "loss": 0.418, "lr": 4.038510243839396e-06, "epoch": 1.0220440881763526, "percentage": 34.07, "elapsed_time": "0:51:58", "remaining_time": "1:40:35"}
53
  {"current_steps": 520, "total_steps": 1497, "loss": 0.4136, "lr": 3.997448626547613e-06, "epoch": 1.0420841683366733, "percentage": 34.74, "elapsed_time": "0:52:58", "remaining_time": "1:39:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  {"current_steps": 500, "total_steps": 1497, "loss": 0.4942, "lr": 4.078942976815581e-06, "epoch": 1.002004008016032, "percentage": 33.4, "elapsed_time": "0:50:59", "remaining_time": "1:41:39"}
52
  {"current_steps": 510, "total_steps": 1497, "loss": 0.418, "lr": 4.038510243839396e-06, "epoch": 1.0220440881763526, "percentage": 34.07, "elapsed_time": "0:51:58", "remaining_time": "1:40:35"}
53
  {"current_steps": 520, "total_steps": 1497, "loss": 0.4136, "lr": 3.997448626547613e-06, "epoch": 1.0420841683366733, "percentage": 34.74, "elapsed_time": "0:52:58", "remaining_time": "1:39:31"}
54
+ {"current_steps": 530, "total_steps": 1497, "loss": 0.4131, "lr": 3.955778165919502e-06, "epoch": 1.062124248496994, "percentage": 35.4, "elapsed_time": "0:53:58", "remaining_time": "1:38:29"}
55
+ {"current_steps": 540, "total_steps": 1497, "loss": 0.412, "lr": 3.913519200093035e-06, "epoch": 1.0821643286573146, "percentage": 36.07, "elapsed_time": "0:54:59", "remaining_time": "1:37:27"}
56
+ {"current_steps": 550, "total_steps": 1497, "loss": 0.4142, "lr": 3.870692354438423e-06, "epoch": 1.1022044088176353, "percentage": 36.74, "elapsed_time": "0:56:00", "remaining_time": "1:36:25"}
57
+ {"current_steps": 560, "total_steps": 1497, "loss": 0.4115, "lr": 3.827318531491478e-06, "epoch": 1.122244488977956, "percentage": 37.41, "elapsed_time": "0:57:01", "remaining_time": "1:35:24"}
58
+ {"current_steps": 570, "total_steps": 1497, "loss": 0.4108, "lr": 3.7834189007517002e-06, "epoch": 1.1422845691382766, "percentage": 38.08, "elapsed_time": "0:58:01", "remaining_time": "1:34:21"}
59
+ {"current_steps": 580, "total_steps": 1497, "loss": 0.4116, "lr": 3.739014888350053e-06, "epoch": 1.1623246492985972, "percentage": 38.74, "elapsed_time": "0:59:01", "remaining_time": "1:33:18"}
60
+ {"current_steps": 590, "total_steps": 1497, "loss": 0.4136, "lr": 3.694128166591494e-06, "epoch": 1.182364729458918, "percentage": 39.41, "elapsed_time": "1:00:01", "remaining_time": "1:32:16"}
61
+ {"current_steps": 600, "total_steps": 1497, "loss": 0.4134, "lr": 3.6487806433773615e-06, "epoch": 1.2024048096192386, "percentage": 40.08, "elapsed_time": "1:01:01", "remaining_time": "1:31:14"}
62
+ {"current_steps": 610, "total_steps": 1497, "loss": 0.4091, "lr": 3.6029944515127585e-06, "epoch": 1.2224448897795592, "percentage": 40.75, "elapsed_time": "1:02:03", "remaining_time": "1:30:13"}
63
+ {"current_steps": 620, "total_steps": 1497, "loss": 0.4142, "lr": 3.5567919379041783e-06, "epoch": 1.2424849699398797, "percentage": 41.42, "elapsed_time": "1:03:03", "remaining_time": "1:29:12"}
64
+ {"current_steps": 630, "total_steps": 1497, "loss": 0.4161, "lr": 3.510195652652629e-06, "epoch": 1.2625250501002003, "percentage": 42.08, "elapsed_time": "1:04:04", "remaining_time": "1:28:10"}
65
+ {"current_steps": 640, "total_steps": 1497, "loss": 0.4059, "lr": 3.463228338047589e-06, "epoch": 1.282565130260521, "percentage": 42.75, "elapsed_time": "1:05:04", "remaining_time": "1:27:08"}
66
+ {"current_steps": 650, "total_steps": 1497, "loss": 0.4065, "lr": 3.4159129174671534e-06, "epoch": 1.3026052104208417, "percentage": 43.42, "elapsed_time": "1:06:05", "remaining_time": "1:26:06"}
67
+ {"current_steps": 660, "total_steps": 1497, "loss": 0.4108, "lr": 3.3682724841898067e-06, "epoch": 1.3226452905811623, "percentage": 44.09, "elapsed_time": "1:07:06", "remaining_time": "1:25:06"}
68
+ {"current_steps": 670, "total_steps": 1497, "loss": 0.4103, "lr": 3.320330290123261e-06, "epoch": 1.342685370741483, "percentage": 44.76, "elapsed_time": "1:08:06", "remaining_time": "1:24:04"}
69
+ {"current_steps": 680, "total_steps": 1497, "loss": 0.4133, "lr": 3.2721097344558794e-06, "epoch": 1.3627254509018036, "percentage": 45.42, "elapsed_time": "1:09:06", "remaining_time": "1:23:02"}
70
+ {"current_steps": 690, "total_steps": 1497, "loss": 0.4103, "lr": 3.223634352236213e-06, "epoch": 1.3827655310621243, "percentage": 46.09, "elapsed_time": "1:10:06", "remaining_time": "1:22:00"}
71
+ {"current_steps": 700, "total_steps": 1497, "loss": 0.4078, "lr": 3.1749278028862325e-06, "epoch": 1.402805611222445, "percentage": 46.76, "elapsed_time": "1:11:07", "remaining_time": "1:20:58"}
72
+ {"current_steps": 710, "total_steps": 1497, "loss": 0.4108, "lr": 3.1260138586538483e-06, "epoch": 1.4228456913827654, "percentage": 47.43, "elapsed_time": "1:12:07", "remaining_time": "1:19:57"}
73
+ {"current_steps": 720, "total_steps": 1497, "loss": 0.4091, "lr": 3.076916393010373e-06, "epoch": 1.4428857715430863, "percentage": 48.1, "elapsed_time": "1:13:07", "remaining_time": "1:18:55"}
74
+ {"current_steps": 730, "total_steps": 1497, "loss": 0.4056, "lr": 3.0276593689985737e-06, "epoch": 1.4629258517034067, "percentage": 48.76, "elapsed_time": "1:14:07", "remaining_time": "1:17:52"}
75
+ {"current_steps": 740, "total_steps": 1497, "loss": 0.4139, "lr": 2.9782668275370095e-06, "epoch": 1.4829659318637274, "percentage": 49.43, "elapsed_time": "1:15:07", "remaining_time": "1:16:51"}
76
+ {"current_steps": 750, "total_steps": 1497, "loss": 0.4109, "lr": 2.928762875686358e-06, "epoch": 1.503006012024048, "percentage": 50.1, "elapsed_time": "1:16:07", "remaining_time": "1:15:49"}
77
+ {"current_steps": 760, "total_steps": 1497, "loss": 0.4103, "lr": 2.879171674883462e-06, "epoch": 1.5230460921843687, "percentage": 50.77, "elapsed_time": "1:17:07", "remaining_time": "1:14:47"}
78
+ {"current_steps": 770, "total_steps": 1497, "loss": 0.4109, "lr": 2.8295174291488383e-06, "epoch": 1.5430861723446894, "percentage": 51.44, "elapsed_time": "1:18:07", "remaining_time": "1:13:46"}
79
+ {"current_steps": 780, "total_steps": 1497, "loss": 0.4118, "lr": 2.779824373273397e-06, "epoch": 1.56312625250501, "percentage": 52.1, "elapsed_time": "1:19:08", "remaining_time": "1:12:45"}
80
+ {"current_steps": 790, "total_steps": 1497, "loss": 0.4135, "lr": 2.7301167609901474e-06, "epoch": 1.5831663326653307, "percentage": 52.77, "elapsed_time": "1:20:09", "remaining_time": "1:11:44"}
81
+ {"current_steps": 800, "total_steps": 1497, "loss": 0.4095, "lr": 2.680418853136659e-06, "epoch": 1.6032064128256514, "percentage": 53.44, "elapsed_time": "1:21:09", "remaining_time": "1:10:42"}
82
+ {"current_steps": 810, "total_steps": 1497, "loss": 0.4079, "lr": 2.630754905814048e-06, "epoch": 1.623246492985972, "percentage": 54.11, "elapsed_time": "1:22:09", "remaining_time": "1:09:40"}
83
+ {"current_steps": 820, "total_steps": 1497, "loss": 0.4083, "lr": 2.58114915854829e-06, "epoch": 1.6432865731462925, "percentage": 54.78, "elapsed_time": "1:23:09", "remaining_time": "1:08:39"}
84
+ {"current_steps": 830, "total_steps": 1497, "loss": 0.4087, "lr": 2.531625822459603e-06, "epoch": 1.6633266533066133, "percentage": 55.44, "elapsed_time": "1:24:09", "remaining_time": "1:07:38"}
85
+ {"current_steps": 840, "total_steps": 1497, "loss": 0.4113, "lr": 2.4822090684457147e-06, "epoch": 1.6833667334669338, "percentage": 56.11, "elapsed_time": "1:25:10", "remaining_time": "1:06:37"}
86
+ {"current_steps": 850, "total_steps": 1497, "loss": 0.4047, "lr": 2.432923015384743e-06, "epoch": 1.7034068136272547, "percentage": 56.78, "elapsed_time": "1:26:10", "remaining_time": "1:05:35"}
87
+ {"current_steps": 860, "total_steps": 1497, "loss": 0.4085, "lr": 2.3837917183634815e-06, "epoch": 1.723446893787575, "percentage": 57.45, "elapsed_time": "1:27:10", "remaining_time": "1:04:34"}
88
+ {"current_steps": 870, "total_steps": 1497, "loss": 0.411, "lr": 2.3348391569368064e-06, "epoch": 1.7434869739478958, "percentage": 58.12, "elapsed_time": "1:28:10", "remaining_time": "1:03:32"}
89
+ {"current_steps": 880, "total_steps": 1497, "loss": 0.4145, "lr": 2.2860892234239565e-06, "epoch": 1.7635270541082164, "percentage": 58.78, "elapsed_time": "1:29:10", "remaining_time": "1:02:31"}
90
+ {"current_steps": 890, "total_steps": 1497, "loss": 0.4109, "lr": 2.237565711247391e-06, "epoch": 1.783567134268537, "percentage": 59.45, "elapsed_time": "1:30:10", "remaining_time": "1:01:30"}
91
+ {"current_steps": 900, "total_steps": 1497, "loss": 0.4078, "lr": 2.1892923033199075e-06, "epoch": 1.8036072144288577, "percentage": 60.12, "elapsed_time": "1:31:11", "remaining_time": "1:00:29"}
92
+ {"current_steps": 910, "total_steps": 1497, "loss": 0.4064, "lr": 2.141292560485708e-06, "epoch": 1.8236472945891784, "percentage": 60.79, "elapsed_time": "1:32:11", "remaining_time": "0:59:28"}
93
+ {"current_steps": 920, "total_steps": 1497, "loss": 0.4059, "lr": 2.0935899100210316e-06, "epoch": 1.843687374749499, "percentage": 61.46, "elapsed_time": "1:33:11", "remaining_time": "0:58:26"}
94
+ {"current_steps": 930, "total_steps": 1497, "loss": 0.405, "lr": 2.046207634199989e-06, "epoch": 1.8637274549098195, "percentage": 62.12, "elapsed_time": "1:34:11", "remaining_time": "0:57:25"}
95
+ {"current_steps": 940, "total_steps": 1497, "loss": 0.4067, "lr": 1.9991688589311575e-06, "epoch": 1.8837675350701404, "percentage": 62.79, "elapsed_time": "1:35:12", "remaining_time": "0:56:24"}
96
+ {"current_steps": 950, "total_steps": 1497, "loss": 0.4024, "lr": 1.9524965424705026e-06, "epoch": 1.9038076152304608, "percentage": 63.46, "elapsed_time": "1:36:12", "remaining_time": "0:55:23"}
97
+ {"current_steps": 960, "total_steps": 1497, "loss": 0.4091, "lr": 1.9062134642161198e-06, "epoch": 1.9238476953907817, "percentage": 64.13, "elapsed_time": "1:37:13", "remaining_time": "0:54:22"}
98
+ {"current_steps": 970, "total_steps": 1497, "loss": 0.4057, "lr": 1.8603422135902737e-06, "epoch": 1.9438877755511021, "percentage": 64.8, "elapsed_time": "1:38:14", "remaining_time": "0:53:22"}
99
+ {"current_steps": 980, "total_steps": 1497, "loss": 0.4066, "lr": 1.8149051790141628e-06, "epoch": 1.9639278557114228, "percentage": 65.46, "elapsed_time": "1:39:14", "remaining_time": "0:52:21"}
100
+ {"current_steps": 990, "total_steps": 1497, "loss": 0.4045, "lr": 1.7699245369807778e-06, "epoch": 1.9839679358717435, "percentage": 66.13, "elapsed_time": "1:40:15", "remaining_time": "0:51:20"}
101
+ {"current_steps": 998, "total_steps": 1497, "eval_loss": 0.4974905848503113, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:41:53", "remaining_time": "0:50:56"}
102
+ {"current_steps": 1000, "total_steps": 1497, "loss": 0.3859, "lr": 1.725422241231205e-06, "epoch": 2.004008016032064, "percentage": 66.8, "elapsed_time": "1:43:16", "remaining_time": "0:51:19"}
103
+ {"current_steps": 1010, "total_steps": 1497, "loss": 0.3244, "lr": 1.6814200120396438e-06, "epoch": 2.024048096192385, "percentage": 67.47, "elapsed_time": "1:44:15", "remaining_time": "0:50:16"}
104
+ {"current_steps": 1020, "total_steps": 1497, "loss": 0.3211, "lr": 1.6379393256123737e-06, "epoch": 2.0440881763527052, "percentage": 68.14, "elapsed_time": "1:45:15", "remaining_time": "0:49:13"}