Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v3.1-llama-3.2-1b

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
6e79f7f
·
verified ·
1 Parent(s): ac23571

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 +38 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f116415de32ca7d8af31fb795bfb0d9fd2cfbc3293007d26515dfe179976c085
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec89692a818ad439916e22c1eff80e73d815962c5a3e3e8037c000021c3fe804
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:d23cf57ab0550eba3451f6609a1de5a0e384da5deb1f6bd421726d3806816264
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9f951e5e74f68af24346bf8596298573129bbd76ff8483159a022eab81a276
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:863c5af0ed7ff91be57420dcf47fefea0afc2bd14dcd1e7485bfa90b5d9e6eb3
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2afed67938a4ce85df8163657d48ca549d23c811372484b6369c9044286ef05
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:863b0226220ccbbcede4d605438c50790ba965abd7d241279d15ebc54ecd6f33
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1a3f51edb5a10ed40b50da52f0743de34cb10f236739b907f4e67fbc4016f8
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -79,3 +79,41 @@
79
  {"current_steps": 770, "total_steps": 1152, "loss": 0.2117, "learning_rate": 5e-06, "epoch": 2.0052083333333335, "percentage": 66.84, "elapsed_time": "1:19:19", "remaining_time": "0:39:21"}
80
  {"current_steps": 780, "total_steps": 1152, "loss": 0.1945, "learning_rate": 5e-06, "epoch": 2.03125, "percentage": 67.71, "elapsed_time": "1:20:18", "remaining_time": "0:38:17"}
81
  {"current_steps": 790, "total_steps": 1152, "loss": 0.1941, "learning_rate": 5e-06, "epoch": 2.0572916666666665, "percentage": 68.58, "elapsed_time": "1:21:16", "remaining_time": "0:37:14"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  {"current_steps": 770, "total_steps": 1152, "loss": 0.2117, "learning_rate": 5e-06, "epoch": 2.0052083333333335, "percentage": 66.84, "elapsed_time": "1:19:19", "remaining_time": "0:39:21"}
80
  {"current_steps": 780, "total_steps": 1152, "loss": 0.1945, "learning_rate": 5e-06, "epoch": 2.03125, "percentage": 67.71, "elapsed_time": "1:20:18", "remaining_time": "0:38:17"}
81
  {"current_steps": 790, "total_steps": 1152, "loss": 0.1941, "learning_rate": 5e-06, "epoch": 2.0572916666666665, "percentage": 68.58, "elapsed_time": "1:21:16", "remaining_time": "0:37:14"}
82
+ {"current_steps": 800, "total_steps": 1152, "loss": 0.1957, "learning_rate": 5e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "1:22:14", "remaining_time": "0:36:11"}
83
+ {"current_steps": 810, "total_steps": 1152, "loss": 0.1955, "learning_rate": 5e-06, "epoch": 2.109375, "percentage": 70.31, "elapsed_time": "1:23:12", "remaining_time": "0:35:08"}
84
+ {"current_steps": 820, "total_steps": 1152, "loss": 0.1918, "learning_rate": 5e-06, "epoch": 2.1354166666666665, "percentage": 71.18, "elapsed_time": "1:24:11", "remaining_time": "0:34:05"}
85
+ {"current_steps": 830, "total_steps": 1152, "loss": 0.1938, "learning_rate": 5e-06, "epoch": 2.1614583333333335, "percentage": 72.05, "elapsed_time": "1:25:09", "remaining_time": "0:33:02"}
86
+ {"current_steps": 840, "total_steps": 1152, "loss": 0.1951, "learning_rate": 5e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "1:26:07", "remaining_time": "0:31:59"}
87
+ {"current_steps": 850, "total_steps": 1152, "loss": 0.1967, "learning_rate": 5e-06, "epoch": 2.2135416666666665, "percentage": 73.78, "elapsed_time": "1:27:05", "remaining_time": "0:30:56"}
88
+ {"current_steps": 860, "total_steps": 1152, "loss": 0.1941, "learning_rate": 5e-06, "epoch": 2.2395833333333335, "percentage": 74.65, "elapsed_time": "1:28:03", "remaining_time": "0:29:54"}
89
+ {"current_steps": 870, "total_steps": 1152, "loss": 0.1949, "learning_rate": 5e-06, "epoch": 2.265625, "percentage": 75.52, "elapsed_time": "1:29:02", "remaining_time": "0:28:51"}
90
+ {"current_steps": 880, "total_steps": 1152, "loss": 0.1964, "learning_rate": 5e-06, "epoch": 2.2916666666666665, "percentage": 76.39, "elapsed_time": "1:30:00", "remaining_time": "0:27:49"}
91
+ {"current_steps": 890, "total_steps": 1152, "loss": 0.1959, "learning_rate": 5e-06, "epoch": 2.3177083333333335, "percentage": 77.26, "elapsed_time": "1:30:58", "remaining_time": "0:26:46"}
92
+ {"current_steps": 900, "total_steps": 1152, "loss": 0.1929, "learning_rate": 5e-06, "epoch": 2.34375, "percentage": 78.12, "elapsed_time": "1:31:56", "remaining_time": "0:25:44"}
93
+ {"current_steps": 910, "total_steps": 1152, "loss": 0.193, "learning_rate": 5e-06, "epoch": 2.3697916666666665, "percentage": 78.99, "elapsed_time": "1:32:54", "remaining_time": "0:24:42"}
94
+ {"current_steps": 920, "total_steps": 1152, "loss": 0.1961, "learning_rate": 5e-06, "epoch": 2.3958333333333335, "percentage": 79.86, "elapsed_time": "1:33:53", "remaining_time": "0:23:40"}
95
+ {"current_steps": 930, "total_steps": 1152, "loss": 0.1955, "learning_rate": 5e-06, "epoch": 2.421875, "percentage": 80.73, "elapsed_time": "1:34:51", "remaining_time": "0:22:38"}
96
+ {"current_steps": 940, "total_steps": 1152, "loss": 0.1971, "learning_rate": 5e-06, "epoch": 2.4479166666666665, "percentage": 81.6, "elapsed_time": "1:35:49", "remaining_time": "0:21:36"}
97
+ {"current_steps": 950, "total_steps": 1152, "loss": 0.1942, "learning_rate": 5e-06, "epoch": 2.4739583333333335, "percentage": 82.47, "elapsed_time": "1:36:48", "remaining_time": "0:20:34"}
98
+ {"current_steps": 960, "total_steps": 1152, "loss": 0.1949, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:37:46", "remaining_time": "0:19:33"}
99
+ {"current_steps": 970, "total_steps": 1152, "loss": 0.1941, "learning_rate": 5e-06, "epoch": 2.5260416666666665, "percentage": 84.2, "elapsed_time": "1:38:44", "remaining_time": "0:18:31"}
100
+ {"current_steps": 980, "total_steps": 1152, "loss": 0.1935, "learning_rate": 5e-06, "epoch": 2.5520833333333335, "percentage": 85.07, "elapsed_time": "1:39:42", "remaining_time": "0:17:30"}
101
+ {"current_steps": 990, "total_steps": 1152, "loss": 0.1936, "learning_rate": 5e-06, "epoch": 2.578125, "percentage": 85.94, "elapsed_time": "1:40:40", "remaining_time": "0:16:28"}
102
+ {"current_steps": 1000, "total_steps": 1152, "loss": 0.1931, "learning_rate": 5e-06, "epoch": 2.6041666666666665, "percentage": 86.81, "elapsed_time": "1:41:39", "remaining_time": "0:15:27"}
103
+ {"current_steps": 1010, "total_steps": 1152, "loss": 0.1942, "learning_rate": 5e-06, "epoch": 2.6302083333333335, "percentage": 87.67, "elapsed_time": "1:42:37", "remaining_time": "0:14:25"}
104
+ {"current_steps": 1020, "total_steps": 1152, "loss": 0.1913, "learning_rate": 5e-06, "epoch": 2.65625, "percentage": 88.54, "elapsed_time": "1:43:35", "remaining_time": "0:13:24"}
105
+ {"current_steps": 1030, "total_steps": 1152, "loss": 0.1925, "learning_rate": 5e-06, "epoch": 2.6822916666666665, "percentage": 89.41, "elapsed_time": "1:44:34", "remaining_time": "0:12:23"}
106
+ {"current_steps": 1040, "total_steps": 1152, "loss": 0.1953, "learning_rate": 5e-06, "epoch": 2.7083333333333335, "percentage": 90.28, "elapsed_time": "1:45:32", "remaining_time": "0:11:21"}
107
+ {"current_steps": 1050, "total_steps": 1152, "loss": 0.192, "learning_rate": 5e-06, "epoch": 2.734375, "percentage": 91.15, "elapsed_time": "1:46:30", "remaining_time": "0:10:20"}
108
+ {"current_steps": 1060, "total_steps": 1152, "loss": 0.1958, "learning_rate": 5e-06, "epoch": 2.7604166666666665, "percentage": 92.01, "elapsed_time": "1:47:28", "remaining_time": "0:09:19"}
109
+ {"current_steps": 1070, "total_steps": 1152, "loss": 0.1921, "learning_rate": 5e-06, "epoch": 2.7864583333333335, "percentage": 92.88, "elapsed_time": "1:48:26", "remaining_time": "0:08:18"}
110
+ {"current_steps": 1080, "total_steps": 1152, "loss": 0.1926, "learning_rate": 5e-06, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "1:49:24", "remaining_time": "0:07:17"}
111
+ {"current_steps": 1090, "total_steps": 1152, "loss": 0.1953, "learning_rate": 5e-06, "epoch": 2.8385416666666665, "percentage": 94.62, "elapsed_time": "1:50:23", "remaining_time": "0:06:16"}
112
+ {"current_steps": 1100, "total_steps": 1152, "loss": 0.1951, "learning_rate": 5e-06, "epoch": 2.8645833333333335, "percentage": 95.49, "elapsed_time": "1:51:21", "remaining_time": "0:05:15"}
113
+ {"current_steps": 1110, "total_steps": 1152, "loss": 0.1901, "learning_rate": 5e-06, "epoch": 2.890625, "percentage": 96.35, "elapsed_time": "1:52:19", "remaining_time": "0:04:15"}
114
+ {"current_steps": 1120, "total_steps": 1152, "loss": 0.194, "learning_rate": 5e-06, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "1:53:17", "remaining_time": "0:03:14"}
115
+ {"current_steps": 1130, "total_steps": 1152, "loss": 0.1933, "learning_rate": 5e-06, "epoch": 2.9427083333333335, "percentage": 98.09, "elapsed_time": "1:54:16", "remaining_time": "0:02:13"}
116
+ {"current_steps": 1140, "total_steps": 1152, "loss": 0.1902, "learning_rate": 5e-06, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "1:55:14", "remaining_time": "0:01:12"}
117
+ {"current_steps": 1150, "total_steps": 1152, "loss": 0.1929, "learning_rate": 5e-06, "epoch": 2.9947916666666665, "percentage": 99.83, "elapsed_time": "1:56:12", "remaining_time": "0:00:12"}
118
+ {"current_steps": 1152, "total_steps": 1152, "eval_loss": 0.22828711569309235, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:58:41", "remaining_time": "0:00:00"}
119
+ {"current_steps": 1152, "total_steps": 1152, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:00:26", "remaining_time": "0:00:00"}