Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_oh_dcft_v1_wo_camel_math_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
a988832
·
verified ·
1 Parent(s): f24c3b0

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 +36 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa835fe013b53a908a7d0f45f51e8146face30871ca237a244a37be23888b62c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a26006a4041b7368747f667d37a5194137db70e317c7dd54e7404bedce4df9
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1423f467a0e73adce60181a3745faf080f0bf17fe50ca87a0cd2d29ba916292b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372bca6ee0f5ee70d597799eff86d582fa2c66bd0047d65bb71f330359bac647
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:e25e93148bd60d9a296350a1db427141aaf581026ee41ea1350ec44a07b22944
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4615f2f6ffe2297a114d858f40219ee70c94736da22d097c322569a9e28cdc6
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ebb045e48dbd0b49d1b47c426c0ec763ca2115e7037a3bd163f172ace0cc3e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc5d8dcb2930fa0f233994caffdf07c5bb72ce96705e4acdf6a9402df5dc330
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -75,3 +75,39 @@
75
  {"current_steps": 730, "total_steps": 1092, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.0054945054945055, "percentage": 66.85, "elapsed_time": "1:24:38", "remaining_time": "0:41:58"}
76
  {"current_steps": 740, "total_steps": 1092, "loss": 0.5343, "learning_rate": 5e-06, "epoch": 2.032967032967033, "percentage": 67.77, "elapsed_time": "1:25:40", "remaining_time": "0:40:45"}
77
  {"current_steps": 750, "total_steps": 1092, "loss": 0.5346, "learning_rate": 5e-06, "epoch": 2.0604395604395602, "percentage": 68.68, "elapsed_time": "1:26:42", "remaining_time": "0:39:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  {"current_steps": 730, "total_steps": 1092, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.0054945054945055, "percentage": 66.85, "elapsed_time": "1:24:38", "remaining_time": "0:41:58"}
76
  {"current_steps": 740, "total_steps": 1092, "loss": 0.5343, "learning_rate": 5e-06, "epoch": 2.032967032967033, "percentage": 67.77, "elapsed_time": "1:25:40", "remaining_time": "0:40:45"}
77
  {"current_steps": 750, "total_steps": 1092, "loss": 0.5346, "learning_rate": 5e-06, "epoch": 2.0604395604395602, "percentage": 68.68, "elapsed_time": "1:26:42", "remaining_time": "0:39:32"}
78
+ {"current_steps": 760, "total_steps": 1092, "loss": 0.5386, "learning_rate": 5e-06, "epoch": 2.087912087912088, "percentage": 69.6, "elapsed_time": "1:27:44", "remaining_time": "0:38:19"}
79
+ {"current_steps": 770, "total_steps": 1092, "loss": 0.5364, "learning_rate": 5e-06, "epoch": 2.1153846153846154, "percentage": 70.51, "elapsed_time": "1:28:47", "remaining_time": "0:37:07"}
80
+ {"current_steps": 780, "total_steps": 1092, "loss": 0.5357, "learning_rate": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "1:29:49", "remaining_time": "0:35:55"}
81
+ {"current_steps": 790, "total_steps": 1092, "loss": 0.532, "learning_rate": 5e-06, "epoch": 2.17032967032967, "percentage": 72.34, "elapsed_time": "1:30:51", "remaining_time": "0:34:44"}
82
+ {"current_steps": 800, "total_steps": 1092, "loss": 0.5389, "learning_rate": 5e-06, "epoch": 2.197802197802198, "percentage": 73.26, "elapsed_time": "1:31:53", "remaining_time": "0:33:32"}
83
+ {"current_steps": 810, "total_steps": 1092, "loss": 0.5323, "learning_rate": 5e-06, "epoch": 2.2252747252747254, "percentage": 74.18, "elapsed_time": "1:32:56", "remaining_time": "0:32:21"}
84
+ {"current_steps": 820, "total_steps": 1092, "loss": 0.5325, "learning_rate": 5e-06, "epoch": 2.2527472527472527, "percentage": 75.09, "elapsed_time": "1:33:58", "remaining_time": "0:31:10"}
85
+ {"current_steps": 830, "total_steps": 1092, "loss": 0.5305, "learning_rate": 5e-06, "epoch": 2.28021978021978, "percentage": 76.01, "elapsed_time": "1:35:00", "remaining_time": "0:29:59"}
86
+ {"current_steps": 840, "total_steps": 1092, "loss": 0.5336, "learning_rate": 5e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "1:36:03", "remaining_time": "0:28:48"}
87
+ {"current_steps": 850, "total_steps": 1092, "loss": 0.5299, "learning_rate": 5e-06, "epoch": 2.3351648351648353, "percentage": 77.84, "elapsed_time": "1:37:05", "remaining_time": "0:27:38"}
88
+ {"current_steps": 860, "total_steps": 1092, "loss": 0.5352, "learning_rate": 5e-06, "epoch": 2.3626373626373627, "percentage": 78.75, "elapsed_time": "1:38:07", "remaining_time": "0:26:28"}
89
+ {"current_steps": 870, "total_steps": 1092, "loss": 0.534, "learning_rate": 5e-06, "epoch": 2.39010989010989, "percentage": 79.67, "elapsed_time": "1:39:10", "remaining_time": "0:25:18"}
90
+ {"current_steps": 880, "total_steps": 1092, "loss": 0.5317, "learning_rate": 5e-06, "epoch": 2.4175824175824174, "percentage": 80.59, "elapsed_time": "1:40:12", "remaining_time": "0:24:08"}
91
+ {"current_steps": 890, "total_steps": 1092, "loss": 0.5381, "learning_rate": 5e-06, "epoch": 2.4450549450549453, "percentage": 81.5, "elapsed_time": "1:41:14", "remaining_time": "0:22:58"}
92
+ {"current_steps": 900, "total_steps": 1092, "loss": 0.5381, "learning_rate": 5e-06, "epoch": 2.4725274725274726, "percentage": 82.42, "elapsed_time": "1:42:17", "remaining_time": "0:21:49"}
93
+ {"current_steps": 910, "total_steps": 1092, "loss": 0.5316, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:43:19", "remaining_time": "0:20:39"}
94
+ {"current_steps": 920, "total_steps": 1092, "loss": 0.5368, "learning_rate": 5e-06, "epoch": 2.5274725274725274, "percentage": 84.25, "elapsed_time": "1:44:21", "remaining_time": "0:19:30"}
95
+ {"current_steps": 930, "total_steps": 1092, "loss": 0.5402, "learning_rate": 5e-06, "epoch": 2.5549450549450547, "percentage": 85.16, "elapsed_time": "1:45:24", "remaining_time": "0:18:21"}
96
+ {"current_steps": 940, "total_steps": 1092, "loss": 0.5382, "learning_rate": 5e-06, "epoch": 2.5824175824175826, "percentage": 86.08, "elapsed_time": "1:46:26", "remaining_time": "0:17:12"}
97
+ {"current_steps": 950, "total_steps": 1092, "loss": 0.539, "learning_rate": 5e-06, "epoch": 2.60989010989011, "percentage": 87.0, "elapsed_time": "1:47:28", "remaining_time": "0:16:03"}
98
+ {"current_steps": 960, "total_steps": 1092, "loss": 0.5335, "learning_rate": 5e-06, "epoch": 2.6373626373626373, "percentage": 87.91, "elapsed_time": "1:48:31", "remaining_time": "0:14:55"}
99
+ {"current_steps": 970, "total_steps": 1092, "loss": 0.5341, "learning_rate": 5e-06, "epoch": 2.6648351648351647, "percentage": 88.83, "elapsed_time": "1:49:33", "remaining_time": "0:13:46"}
100
+ {"current_steps": 980, "total_steps": 1092, "loss": 0.5301, "learning_rate": 5e-06, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "1:50:35", "remaining_time": "0:12:38"}
101
+ {"current_steps": 990, "total_steps": 1092, "loss": 0.537, "learning_rate": 5e-06, "epoch": 2.71978021978022, "percentage": 90.66, "elapsed_time": "1:51:37", "remaining_time": "0:11:30"}
102
+ {"current_steps": 1000, "total_steps": 1092, "loss": 0.5333, "learning_rate": 5e-06, "epoch": 2.7472527472527473, "percentage": 91.58, "elapsed_time": "1:52:40", "remaining_time": "0:10:21"}
103
+ {"current_steps": 1010, "total_steps": 1092, "loss": 0.5352, "learning_rate": 5e-06, "epoch": 2.7747252747252746, "percentage": 92.49, "elapsed_time": "1:53:42", "remaining_time": "0:09:13"}
104
+ {"current_steps": 1020, "total_steps": 1092, "loss": 0.5389, "learning_rate": 5e-06, "epoch": 2.802197802197802, "percentage": 93.41, "elapsed_time": "1:54:44", "remaining_time": "0:08:05"}
105
+ {"current_steps": 1030, "total_steps": 1092, "loss": 0.5346, "learning_rate": 5e-06, "epoch": 2.82967032967033, "percentage": 94.32, "elapsed_time": "1:55:47", "remaining_time": "0:06:58"}
106
+ {"current_steps": 1040, "total_steps": 1092, "loss": 0.5331, "learning_rate": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:56:49", "remaining_time": "0:05:50"}
107
+ {"current_steps": 1050, "total_steps": 1092, "loss": 0.53, "learning_rate": 5e-06, "epoch": 2.8846153846153846, "percentage": 96.15, "elapsed_time": "1:57:51", "remaining_time": "0:04:42"}
108
+ {"current_steps": 1060, "total_steps": 1092, "loss": 0.5291, "learning_rate": 5e-06, "epoch": 2.912087912087912, "percentage": 97.07, "elapsed_time": "1:58:53", "remaining_time": "0:03:35"}
109
+ {"current_steps": 1070, "total_steps": 1092, "loss": 0.5326, "learning_rate": 5e-06, "epoch": 2.9395604395604398, "percentage": 97.99, "elapsed_time": "1:59:56", "remaining_time": "0:02:27"}
110
+ {"current_steps": 1080, "total_steps": 1092, "loss": 0.5314, "learning_rate": 5e-06, "epoch": 2.967032967032967, "percentage": 98.9, "elapsed_time": "2:00:58", "remaining_time": "0:01:20"}
111
+ {"current_steps": 1090, "total_steps": 1092, "loss": 0.5347, "learning_rate": 5e-06, "epoch": 2.9945054945054945, "percentage": 99.82, "elapsed_time": "2:02:00", "remaining_time": "0:00:13"}
112
+ {"current_steps": 1092, "total_steps": 1092, "eval_loss": 0.5989904403686523, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:06:17", "remaining_time": "0:00:00"}
113
+ {"current_steps": 1092, "total_steps": 1092, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:09:32", "remaining_time": "0:00:00"}