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
Model card Files
xet
 Community
gsmyrnis commited on
Commit
ac23571
·
verified ·
1 Parent(s): ba19b85

Training in progress, epoch 2

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 +39 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d762541b5185d8a4ee2197659df5c3aa3c173d19e28c14be16b234abf0ef9070
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f116415de32ca7d8af31fb795bfb0d9fd2cfbc3293007d26515dfe179976c085
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09282ab5325724f4b8d8a7fd2a389cc182cbd2bc963cb546c325ba347907bd88
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23cf57ab0550eba3451f6609a1de5a0e384da5deb1f6bd421726d3806816264
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:b3b79e6c69997d53a0da4c9cb982d0c7e98f1f6a45943df3ac2aa8b2236efe74
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863c5af0ed7ff91be57420dcf47fefea0afc2bd14dcd1e7485bfa90b5d9e6eb3
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:caada3f1bd83fd8c834b5f000630d6d5979765bcd527e69a1d82697099d2d410
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863b0226220ccbbcede4d605438c50790ba965abd7d241279d15ebc54ecd6f33
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -40,3 +40,42 @@
40
  {"current_steps": 390, "total_steps": 1152, "loss": 0.2381, "learning_rate": 5e-06, "epoch": 1.015625, "percentage": 33.85, "elapsed_time": "0:40:03", "remaining_time": "1:18:15"}
41
  {"current_steps": 400, "total_steps": 1152, "loss": 0.2299, "learning_rate": 5e-06, "epoch": 1.0416666666666667, "percentage": 34.72, "elapsed_time": "0:41:02", "remaining_time": "1:17:08"}
42
  {"current_steps": 410, "total_steps": 1152, "loss": 0.2249, "learning_rate": 5e-06, "epoch": 1.0677083333333333, "percentage": 35.59, "elapsed_time": "0:42:01", "remaining_time": "1:16:03"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  {"current_steps": 390, "total_steps": 1152, "loss": 0.2381, "learning_rate": 5e-06, "epoch": 1.015625, "percentage": 33.85, "elapsed_time": "0:40:03", "remaining_time": "1:18:15"}
41
  {"current_steps": 400, "total_steps": 1152, "loss": 0.2299, "learning_rate": 5e-06, "epoch": 1.0416666666666667, "percentage": 34.72, "elapsed_time": "0:41:02", "remaining_time": "1:17:08"}
42
  {"current_steps": 410, "total_steps": 1152, "loss": 0.2249, "learning_rate": 5e-06, "epoch": 1.0677083333333333, "percentage": 35.59, "elapsed_time": "0:42:01", "remaining_time": "1:16:03"}
43
+ {"current_steps": 420, "total_steps": 1152, "loss": 0.2296, "learning_rate": 5e-06, "epoch": 1.09375, "percentage": 36.46, "elapsed_time": "0:43:01", "remaining_time": "1:14:58"}
44
+ {"current_steps": 430, "total_steps": 1152, "loss": 0.2299, "learning_rate": 5e-06, "epoch": 1.1197916666666667, "percentage": 37.33, "elapsed_time": "0:44:00", "remaining_time": "1:13:53"}
45
+ {"current_steps": 440, "total_steps": 1152, "loss": 0.2265, "learning_rate": 5e-06, "epoch": 1.1458333333333333, "percentage": 38.19, "elapsed_time": "0:44:58", "remaining_time": "1:12:47"}
46
+ {"current_steps": 450, "total_steps": 1152, "loss": 0.2286, "learning_rate": 5e-06, "epoch": 1.171875, "percentage": 39.06, "elapsed_time": "0:45:56", "remaining_time": "1:11:40"}
47
+ {"current_steps": 460, "total_steps": 1152, "loss": 0.2273, "learning_rate": 5e-06, "epoch": 1.1979166666666667, "percentage": 39.93, "elapsed_time": "0:46:55", "remaining_time": "1:10:34"}
48
+ {"current_steps": 470, "total_steps": 1152, "loss": 0.2296, "learning_rate": 5e-06, "epoch": 1.2239583333333333, "percentage": 40.8, "elapsed_time": "0:47:53", "remaining_time": "1:09:29"}
49
+ {"current_steps": 480, "total_steps": 1152, "loss": 0.2274, "learning_rate": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:48:51", "remaining_time": "1:08:24"}
50
+ {"current_steps": 490, "total_steps": 1152, "loss": 0.2277, "learning_rate": 5e-06, "epoch": 1.2760416666666667, "percentage": 42.53, "elapsed_time": "0:49:49", "remaining_time": "1:07:19"}
51
+ {"current_steps": 500, "total_steps": 1152, "loss": 0.2217, "learning_rate": 5e-06, "epoch": 1.3020833333333333, "percentage": 43.4, "elapsed_time": "0:50:47", "remaining_time": "1:06:14"}
52
+ {"current_steps": 510, "total_steps": 1152, "loss": 0.2258, "learning_rate": 5e-06, "epoch": 1.328125, "percentage": 44.27, "elapsed_time": "0:51:45", "remaining_time": "1:05:09"}
53
+ {"current_steps": 520, "total_steps": 1152, "loss": 0.2245, "learning_rate": 5e-06, "epoch": 1.3541666666666667, "percentage": 45.14, "elapsed_time": "0:52:44", "remaining_time": "1:04:05"}
54
+ {"current_steps": 530, "total_steps": 1152, "loss": 0.2245, "learning_rate": 5e-06, "epoch": 1.3802083333333333, "percentage": 46.01, "elapsed_time": "0:53:42", "remaining_time": "1:03:01"}
55
+ {"current_steps": 540, "total_steps": 1152, "loss": 0.2222, "learning_rate": 5e-06, "epoch": 1.40625, "percentage": 46.88, "elapsed_time": "0:54:40", "remaining_time": "1:01:57"}
56
+ {"current_steps": 550, "total_steps": 1152, "loss": 0.2254, "learning_rate": 5e-06, "epoch": 1.4322916666666667, "percentage": 47.74, "elapsed_time": "0:55:39", "remaining_time": "1:00:54"}
57
+ {"current_steps": 560, "total_steps": 1152, "loss": 0.2225, "learning_rate": 5e-06, "epoch": 1.4583333333333333, "percentage": 48.61, "elapsed_time": "0:56:37", "remaining_time": "0:59:51"}
58
+ {"current_steps": 570, "total_steps": 1152, "loss": 0.2228, "learning_rate": 5e-06, "epoch": 1.484375, "percentage": 49.48, "elapsed_time": "0:57:35", "remaining_time": "0:58:48"}
59
+ {"current_steps": 580, "total_steps": 1152, "loss": 0.2232, "learning_rate": 5e-06, "epoch": 1.5104166666666665, "percentage": 50.35, "elapsed_time": "0:58:33", "remaining_time": "0:57:45"}
60
+ {"current_steps": 590, "total_steps": 1152, "loss": 0.2176, "learning_rate": 5e-06, "epoch": 1.5364583333333335, "percentage": 51.22, "elapsed_time": "0:59:31", "remaining_time": "0:56:42"}
61
+ {"current_steps": 600, "total_steps": 1152, "loss": 0.2198, "learning_rate": 5e-06, "epoch": 1.5625, "percentage": 52.08, "elapsed_time": "1:00:30", "remaining_time": "0:55:39"}
62
+ {"current_steps": 610, "total_steps": 1152, "loss": 0.2207, "learning_rate": 5e-06, "epoch": 1.5885416666666665, "percentage": 52.95, "elapsed_time": "1:01:28", "remaining_time": "0:54:37"}
63
+ {"current_steps": 620, "total_steps": 1152, "loss": 0.2222, "learning_rate": 5e-06, "epoch": 1.6145833333333335, "percentage": 53.82, "elapsed_time": "1:02:27", "remaining_time": "0:53:35"}
64
+ {"current_steps": 630, "total_steps": 1152, "loss": 0.225, "learning_rate": 5e-06, "epoch": 1.640625, "percentage": 54.69, "elapsed_time": "1:03:25", "remaining_time": "0:52:32"}
65
+ {"current_steps": 640, "total_steps": 1152, "loss": 0.2227, "learning_rate": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:04:23", "remaining_time": "0:51:30"}
66
+ {"current_steps": 650, "total_steps": 1152, "loss": 0.2206, "learning_rate": 5e-06, "epoch": 1.6927083333333335, "percentage": 56.42, "elapsed_time": "1:05:21", "remaining_time": "0:50:28"}
67
+ {"current_steps": 660, "total_steps": 1152, "loss": 0.2208, "learning_rate": 5e-06, "epoch": 1.71875, "percentage": 57.29, "elapsed_time": "1:06:20", "remaining_time": "0:49:27"}
68
+ {"current_steps": 670, "total_steps": 1152, "loss": 0.2194, "learning_rate": 5e-06, "epoch": 1.7447916666666665, "percentage": 58.16, "elapsed_time": "1:07:18", "remaining_time": "0:48:25"}
69
+ {"current_steps": 680, "total_steps": 1152, "loss": 0.219, "learning_rate": 5e-06, "epoch": 1.7708333333333335, "percentage": 59.03, "elapsed_time": "1:08:17", "remaining_time": "0:47:24"}
70
+ {"current_steps": 690, "total_steps": 1152, "loss": 0.2201, "learning_rate": 5e-06, "epoch": 1.796875, "percentage": 59.9, "elapsed_time": "1:09:15", "remaining_time": "0:46:22"}
71
+ {"current_steps": 700, "total_steps": 1152, "loss": 0.2173, "learning_rate": 5e-06, "epoch": 1.8229166666666665, "percentage": 60.76, "elapsed_time": "1:10:13", "remaining_time": "0:45:20"}
72
+ {"current_steps": 710, "total_steps": 1152, "loss": 0.2186, "learning_rate": 5e-06, "epoch": 1.8489583333333335, "percentage": 61.63, "elapsed_time": "1:11:11", "remaining_time": "0:44:19"}
73
+ {"current_steps": 720, "total_steps": 1152, "loss": 0.2176, "learning_rate": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "1:12:10", "remaining_time": "0:43:18"}
74
+ {"current_steps": 730, "total_steps": 1152, "loss": 0.2183, "learning_rate": 5e-06, "epoch": 1.9010416666666665, "percentage": 63.37, "elapsed_time": "1:13:08", "remaining_time": "0:42:16"}
75
+ {"current_steps": 740, "total_steps": 1152, "loss": 0.2185, "learning_rate": 5e-06, "epoch": 1.9270833333333335, "percentage": 64.24, "elapsed_time": "1:14:07", "remaining_time": "0:41:15"}
76
+ {"current_steps": 750, "total_steps": 1152, "loss": 0.2185, "learning_rate": 5e-06, "epoch": 1.953125, "percentage": 65.1, "elapsed_time": "1:15:05", "remaining_time": "0:40:14"}
77
+ {"current_steps": 760, "total_steps": 1152, "loss": 0.2198, "learning_rate": 5e-06, "epoch": 1.9791666666666665, "percentage": 65.97, "elapsed_time": "1:16:03", "remaining_time": "0:39:13"}
78
+ {"current_steps": 768, "total_steps": 1152, "eval_loss": 0.23494887351989746, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:17:27", "remaining_time": "0:38:43"}
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"}