Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_metamath

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
gsmyrnis commited on
Commit
c2d49d3
·
verified ·
1 Parent(s): 02884b2

Training in progress, epoch 3

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 +31 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0adbbdef13651036220cb072964e4011f695acc7ca4026c0f9db6794febe96f7
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6837a297f8a499b3d692e160c8a610228fe1a8ba5d3fe4df0c57d1a276286c2
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:e1509b4853fb0bb0a13bb6b33732150ceebceb1e891ba2967e15dd1a7e746238
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094f8411ef099d3f3209da6de4b260985dd638ce289680ae85215fdfe64d5ec0
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79e1cf7f37fa577eaa20b164b69220ab285f8e99c3adebb903cd4264c55e5796
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694b4430a780957dc2a93fb912a157bbffef2e635e14c93c31533d92d9b3eecf
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:c385d7fefa7f5f9814c0ad230d64d44cabdbde1b2dd3e5d18ef4767b5fadd7e6
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edae4f20248348b59c1360350c48943904ddf068d9f496df4d0d2a5148c490c3
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -65,3 +65,34 @@
65
  {"current_steps": 630, "total_steps": 942, "loss": 0.6157, "learning_rate": 5e-06, "epoch": 2.0063694267515926, "percentage": 66.88, "elapsed_time": "1:04:56", "remaining_time": "0:32:09"}
66
  {"current_steps": 640, "total_steps": 942, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.038216560509554, "percentage": 67.94, "elapsed_time": "1:05:55", "remaining_time": "0:31:06"}
67
  {"current_steps": 650, "total_steps": 942, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.070063694267516, "percentage": 69.0, "elapsed_time": "1:06:53", "remaining_time": "0:30:02"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  {"current_steps": 630, "total_steps": 942, "loss": 0.6157, "learning_rate": 5e-06, "epoch": 2.0063694267515926, "percentage": 66.88, "elapsed_time": "1:04:56", "remaining_time": "0:32:09"}
66
  {"current_steps": 640, "total_steps": 942, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.038216560509554, "percentage": 67.94, "elapsed_time": "1:05:55", "remaining_time": "0:31:06"}
67
  {"current_steps": 650, "total_steps": 942, "loss": 0.5778, "learning_rate": 5e-06, "epoch": 2.070063694267516, "percentage": 69.0, "elapsed_time": "1:06:53", "remaining_time": "0:30:02"}
68
+ {"current_steps": 660, "total_steps": 942, "loss": 0.5784, "learning_rate": 5e-06, "epoch": 2.1019108280254777, "percentage": 70.06, "elapsed_time": "1:07:51", "remaining_time": "0:28:59"}
69
+ {"current_steps": 670, "total_steps": 942, "loss": 0.5751, "learning_rate": 5e-06, "epoch": 2.1337579617834397, "percentage": 71.13, "elapsed_time": "1:08:49", "remaining_time": "0:27:56"}
70
+ {"current_steps": 680, "total_steps": 942, "loss": 0.5766, "learning_rate": 5e-06, "epoch": 2.1656050955414012, "percentage": 72.19, "elapsed_time": "1:09:47", "remaining_time": "0:26:53"}
71
+ {"current_steps": 690, "total_steps": 942, "loss": 0.5798, "learning_rate": 5e-06, "epoch": 2.1974522292993632, "percentage": 73.25, "elapsed_time": "1:10:46", "remaining_time": "0:25:50"}
72
+ {"current_steps": 700, "total_steps": 942, "loss": 0.5767, "learning_rate": 5e-06, "epoch": 2.229299363057325, "percentage": 74.31, "elapsed_time": "1:11:44", "remaining_time": "0:24:48"}
73
+ {"current_steps": 710, "total_steps": 942, "loss": 0.5773, "learning_rate": 5e-06, "epoch": 2.261146496815287, "percentage": 75.37, "elapsed_time": "1:12:42", "remaining_time": "0:23:45"}
74
+ {"current_steps": 720, "total_steps": 942, "loss": 0.579, "learning_rate": 5e-06, "epoch": 2.2929936305732483, "percentage": 76.43, "elapsed_time": "1:13:40", "remaining_time": "0:22:42"}
75
+ {"current_steps": 730, "total_steps": 942, "loss": 0.5796, "learning_rate": 5e-06, "epoch": 2.3248407643312103, "percentage": 77.49, "elapsed_time": "1:14:38", "remaining_time": "0:21:40"}
76
+ {"current_steps": 740, "total_steps": 942, "loss": 0.5748, "learning_rate": 5e-06, "epoch": 2.356687898089172, "percentage": 78.56, "elapsed_time": "1:15:36", "remaining_time": "0:20:38"}
77
+ {"current_steps": 750, "total_steps": 942, "loss": 0.5834, "learning_rate": 5e-06, "epoch": 2.388535031847134, "percentage": 79.62, "elapsed_time": "1:16:34", "remaining_time": "0:19:36"}
78
+ {"current_steps": 760, "total_steps": 942, "loss": 0.5758, "learning_rate": 5e-06, "epoch": 2.4203821656050954, "percentage": 80.68, "elapsed_time": "1:17:32", "remaining_time": "0:18:34"}
79
+ {"current_steps": 770, "total_steps": 942, "loss": 0.5856, "learning_rate": 5e-06, "epoch": 2.4522292993630574, "percentage": 81.74, "elapsed_time": "1:18:31", "remaining_time": "0:17:32"}
80
+ {"current_steps": 780, "total_steps": 942, "loss": 0.5786, "learning_rate": 5e-06, "epoch": 2.484076433121019, "percentage": 82.8, "elapsed_time": "1:19:29", "remaining_time": "0:16:30"}
81
+ {"current_steps": 790, "total_steps": 942, "loss": 0.577, "learning_rate": 5e-06, "epoch": 2.515923566878981, "percentage": 83.86, "elapsed_time": "1:20:27", "remaining_time": "0:15:28"}
82
+ {"current_steps": 800, "total_steps": 942, "loss": 0.581, "learning_rate": 5e-06, "epoch": 2.5477707006369426, "percentage": 84.93, "elapsed_time": "1:21:25", "remaining_time": "0:14:27"}
83
+ {"current_steps": 810, "total_steps": 942, "loss": 0.5809, "learning_rate": 5e-06, "epoch": 2.5796178343949046, "percentage": 85.99, "elapsed_time": "1:22:23", "remaining_time": "0:13:25"}
84
+ {"current_steps": 820, "total_steps": 942, "loss": 0.5845, "learning_rate": 5e-06, "epoch": 2.611464968152866, "percentage": 87.05, "elapsed_time": "1:23:21", "remaining_time": "0:12:24"}
85
+ {"current_steps": 830, "total_steps": 942, "loss": 0.5837, "learning_rate": 5e-06, "epoch": 2.643312101910828, "percentage": 88.11, "elapsed_time": "1:24:20", "remaining_time": "0:11:22"}
86
+ {"current_steps": 840, "total_steps": 942, "loss": 0.5871, "learning_rate": 5e-06, "epoch": 2.6751592356687897, "percentage": 89.17, "elapsed_time": "1:25:18", "remaining_time": "0:10:21"}
87
+ {"current_steps": 850, "total_steps": 942, "loss": 0.5797, "learning_rate": 5e-06, "epoch": 2.7070063694267517, "percentage": 90.23, "elapsed_time": "1:26:16", "remaining_time": "0:09:20"}
88
+ {"current_steps": 860, "total_steps": 942, "loss": 0.5814, "learning_rate": 5e-06, "epoch": 2.738853503184713, "percentage": 91.3, "elapsed_time": "1:27:14", "remaining_time": "0:08:19"}
89
+ {"current_steps": 870, "total_steps": 942, "loss": 0.585, "learning_rate": 5e-06, "epoch": 2.770700636942675, "percentage": 92.36, "elapsed_time": "1:28:12", "remaining_time": "0:07:18"}
90
+ {"current_steps": 880, "total_steps": 942, "loss": 0.5813, "learning_rate": 5e-06, "epoch": 2.802547770700637, "percentage": 93.42, "elapsed_time": "1:29:10", "remaining_time": "0:06:16"}
91
+ {"current_steps": 890, "total_steps": 942, "loss": 0.5823, "learning_rate": 5e-06, "epoch": 2.8343949044585988, "percentage": 94.48, "elapsed_time": "1:30:08", "remaining_time": "0:05:16"}
92
+ {"current_steps": 900, "total_steps": 942, "loss": 0.5799, "learning_rate": 5e-06, "epoch": 2.8662420382165603, "percentage": 95.54, "elapsed_time": "1:31:07", "remaining_time": "0:04:15"}
93
+ {"current_steps": 910, "total_steps": 942, "loss": 0.583, "learning_rate": 5e-06, "epoch": 2.8980891719745223, "percentage": 96.6, "elapsed_time": "1:32:05", "remaining_time": "0:03:14"}
94
+ {"current_steps": 920, "total_steps": 942, "loss": 0.5816, "learning_rate": 5e-06, "epoch": 2.9299363057324843, "percentage": 97.66, "elapsed_time": "1:33:03", "remaining_time": "0:02:13"}
95
+ {"current_steps": 930, "total_steps": 942, "loss": 0.585, "learning_rate": 5e-06, "epoch": 2.961783439490446, "percentage": 98.73, "elapsed_time": "1:34:02", "remaining_time": "0:01:12"}
96
+ {"current_steps": 940, "total_steps": 942, "loss": 0.5826, "learning_rate": 5e-06, "epoch": 2.9936305732484074, "percentage": 99.79, "elapsed_time": "1:35:00", "remaining_time": "0:00:12"}
97
+ {"current_steps": 942, "total_steps": 942, "eval_loss": 0.6691574454307556, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:37:04", "remaining_time": "0:00:00"}
98
+ {"current_steps": 942, "total_steps": 942, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:38:31", "remaining_time": "0:00:00"}