Hugging Face's logo

mlfoundations-dev
/
qwen2-5_multiple_samples_random_seed_code

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
gsmyrnis commited on
Commit
19fdac6
·
verified ·
1 Parent(s): 8e33c49

Training in progress, epoch 1

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 +25 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379be0824ae6fc7d3b7dfe925a75b925ec1c6924c9f27c0458756111e3efb696
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5a779cd20d597da8e84fb740cb12a350dcceed2c00dc1918a29808e160092f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a3b4777afa6a91dfce94565a0b6fe6bd8a21b5978e7c04b54ba99c67c0c583b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674b2f23bd9d3a7a7d5ac2882c481162a4261bf139079f71d92fa55ab086c832
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f401950db7c4547a9c5517770e2d035ffbc77a4c7ee20281caa226d329aa1b47
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13866f345a69d03f87780cd59e8c76605023802426bd84f0ef8900f6e9224c2f
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de22aa2725fc79844734d701d4ded20a4cd4530f8909f0e6fb5ca0e65ce222ce
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485130a5322c72c4600d8320b76e9855f535135bfb613d290bd0c2b251f4ef6e
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -36,3 +36,28 @@
36
  {"current_steps": 36, "total_steps": 78, "loss": 0.7473, "lr": 6.545084971874738e-06, "epoch": 1.3670886075949367, "percentage": 46.15, "elapsed_time": "0:09:17", "remaining_time": "0:10:50"}
37
  {"current_steps": 37, "total_steps": 78, "loss": 0.8813, "lr": 6.330184227833376e-06, "epoch": 1.4050632911392404, "percentage": 47.44, "elapsed_time": "0:09:34", "remaining_time": "0:10:36"}
38
  {"current_steps": 38, "total_steps": 78, "loss": 0.831, "lr": 6.112604669781572e-06, "epoch": 1.4430379746835442, "percentage": 48.72, "elapsed_time": "0:09:51", "remaining_time": "0:10:22"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  {"current_steps": 36, "total_steps": 78, "loss": 0.7473, "lr": 6.545084971874738e-06, "epoch": 1.3670886075949367, "percentage": 46.15, "elapsed_time": "0:09:17", "remaining_time": "0:10:50"}
37
  {"current_steps": 37, "total_steps": 78, "loss": 0.8813, "lr": 6.330184227833376e-06, "epoch": 1.4050632911392404, "percentage": 47.44, "elapsed_time": "0:09:34", "remaining_time": "0:10:36"}
38
  {"current_steps": 38, "total_steps": 78, "loss": 0.831, "lr": 6.112604669781572e-06, "epoch": 1.4430379746835442, "percentage": 48.72, "elapsed_time": "0:09:51", "remaining_time": "0:10:22"}
39
+ {"current_steps": 39, "total_steps": 78, "loss": 0.8186, "lr": 5.892784473993184e-06, "epoch": 1.481012658227848, "percentage": 50.0, "elapsed_time": "0:10:05", "remaining_time": "0:10:05"}
40
+ {"current_steps": 40, "total_steps": 78, "loss": 0.844, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:10:19", "remaining_time": "0:09:48"}
41
+ {"current_steps": 41, "total_steps": 78, "loss": 0.8697, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:10:35", "remaining_time": "0:09:33"}
42
+ {"current_steps": 42, "total_steps": 78, "loss": 0.8231, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:10:48", "remaining_time": "0:09:16"}
43
+ {"current_steps": 43, "total_steps": 78, "loss": 0.8021, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:11:02", "remaining_time": "0:08:59"}
44
+ {"current_steps": 44, "total_steps": 78, "loss": 0.8431, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:11:16", "remaining_time": "0:08:42"}
45
+ {"current_steps": 45, "total_steps": 78, "loss": 0.7526, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:11:32", "remaining_time": "0:08:27"}
46
+ {"current_steps": 46, "total_steps": 78, "loss": 0.848, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:11:47", "remaining_time": "0:08:12"}
47
+ {"current_steps": 47, "total_steps": 78, "loss": 0.8349, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:12:02", "remaining_time": "0:07:56"}
48
+ {"current_steps": 48, "total_steps": 78, "loss": 0.776, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:12:18", "remaining_time": "0:07:41"}
49
+ {"current_steps": 49, "total_steps": 78, "loss": 0.846, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:12:35", "remaining_time": "0:07:27"}
50
+ {"current_steps": 50, "total_steps": 78, "loss": 0.764, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:12:49", "remaining_time": "0:07:10"}
51
+ {"current_steps": 51, "total_steps": 78, "loss": 0.7651, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:13:00", "remaining_time": "0:06:53"}
52
+ {"current_steps": 52, "total_steps": 78, "loss": 0.8124, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:13:12", "remaining_time": "0:06:36"}
53
+ {"current_steps": 53, "total_steps": 78, "loss": 1.2474, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:14:38", "remaining_time": "0:06:54"}
54
+ {"current_steps": 54, "total_steps": 78, "loss": 0.7472, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:14:51", "remaining_time": "0:06:36"}
55
+ {"current_steps": 55, "total_steps": 78, "loss": 0.7427, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:15:03", "remaining_time": "0:06:17"}
56
+ {"current_steps": 56, "total_steps": 78, "loss": 0.7223, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:15:17", "remaining_time": "0:06:00"}
57
+ {"current_steps": 57, "total_steps": 78, "loss": 0.7785, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:15:30", "remaining_time": "0:05:42"}
58
+ {"current_steps": 58, "total_steps": 78, "loss": 0.8173, "lr": 1.8825509907063328e-06, "epoch": 2.2025316455696204, "percentage": 74.36, "elapsed_time": "0:15:44", "remaining_time": "0:05:25"}
59
+ {"current_steps": 59, "total_steps": 78, "loss": 0.6874, "lr": 1.7103063703014372e-06, "epoch": 2.240506329113924, "percentage": 75.64, "elapsed_time": "0:15:57", "remaining_time": "0:05:08"}
60
+ {"current_steps": 60, "total_steps": 78, "loss": 0.7127, "lr": 1.544686755065677e-06, "epoch": 2.278481012658228, "percentage": 76.92, "elapsed_time": "0:16:13", "remaining_time": "0:04:52"}
61
+ {"current_steps": 61, "total_steps": 78, "loss": 0.8729, "lr": 1.3860256808630429e-06, "epoch": 2.3164556962025316, "percentage": 78.21, "elapsed_time": "0:16:24", "remaining_time": "0:04:34"}
62
+ {"current_steps": 62, "total_steps": 78, "loss": 0.6866, "lr": 1.234642669981946e-06, "epoch": 2.3544303797468356, "percentage": 79.49, "elapsed_time": "0:16:41", "remaining_time": "0:04:18"}
63
+ {"current_steps": 63, "total_steps": 78, "loss": 0.8314, "lr": 1.0908425876598512e-06, "epoch": 2.392405063291139, "percentage": 80.77, "elapsed_time": "0:16:58", "remaining_time": "0:04:02"}