Hugging Face's logo

secmlr
/
QWQ-JAVA_DS-JAVA_final_model_sft

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
yuzhounie commited on
Commit
8c9d98e
·
verified ·
1 Parent(s): 6a9c4c0

Training in progress, step 14

Browse files
Files changed (6) 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 +15 -15
  6. training_args.bin +1 -1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be9ae767c87f81a5106f04654418dd41bf17ea66cac710ab885a5a9d7b751090
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b109edb65db33ea41d84de2e6da4eadf0a60e181c6784b8cc788958841ce58ae
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72ad95619be84c2900f428fd3feb0ae8645471d9fbc043ccff890c7441e643be
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7110eae4f21fd28da975252d2e5a987220e9c480ac7e48868717e7e56f3b6b
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:e62625c191ffbe475344b22ff47105c55ba9083d70e611dade352f6e53f4c63f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216bac96ffb270d9f00fac634f79b36d337d7e96fdd3bb936e3a31994468f2f8
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50e822168dac3fd6b426508b8712624498f17e544e3b5de41766bce0dc76a9e8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d65cd8d169dc0ffdb9a0d698df37e775c102c4296a8124b1e098c85456b3788
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,15 +1,15 @@
1
- {"current_steps": 1, "total_steps": 14, "loss": 1.3139, "lr": 0.0, "epoch": 0.12631578947368421, "percentage": 7.14, "elapsed_time": "0:00:27", "remaining_time": "0:05:56"}
2
- {"current_steps": 2, "total_steps": 14, "loss": 1.3348, "lr": 5e-06, "epoch": 0.25263157894736843, "percentage": 14.29, "elapsed_time": "0:00:45", "remaining_time": "0:04:34"}
3
- {"current_steps": 3, "total_steps": 14, "loss": 1.237, "lr": 1e-05, "epoch": 0.37894736842105264, "percentage": 21.43, "elapsed_time": "0:01:08", "remaining_time": "0:04:09"}
4
- {"current_steps": 4, "total_steps": 14, "loss": 1.1375, "lr": 9.829629131445342e-06, "epoch": 0.5052631578947369, "percentage": 28.57, "elapsed_time": "0:01:24", "remaining_time": "0:03:31"}
5
- {"current_steps": 5, "total_steps": 14, "loss": 1.1392, "lr": 9.330127018922195e-06, "epoch": 0.631578947368421, "percentage": 35.71, "elapsed_time": "0:01:43", "remaining_time": "0:03:06"}
6
- {"current_steps": 6, "total_steps": 14, "loss": 1.0664, "lr": 8.535533905932739e-06, "epoch": 0.7578947368421053, "percentage": 42.86, "elapsed_time": "0:02:05", "remaining_time": "0:02:47"}
7
- {"current_steps": 7, "total_steps": 14, "loss": 1.1586, "lr": 7.500000000000001e-06, "epoch": 0.8842105263157894, "percentage": 50.0, "elapsed_time": "0:02:25", "remaining_time": "0:02:25"}
8
- {"current_steps": 8, "total_steps": 14, "loss": 2.0988, "lr": 6.294095225512604e-06, "epoch": 1.1263157894736842, "percentage": 57.14, "elapsed_time": "0:03:03", "remaining_time": "0:02:17"}
9
- {"current_steps": 9, "total_steps": 14, "loss": 1.078, "lr": 5e-06, "epoch": 1.2526315789473683, "percentage": 64.29, "elapsed_time": "0:03:24", "remaining_time": "0:01:53"}
10
- {"current_steps": 10, "total_steps": 14, "loss": 0.9588, "lr": 3.705904774487396e-06, "epoch": 1.3789473684210527, "percentage": 71.43, "elapsed_time": "0:03:41", "remaining_time": "0:01:28"}
11
- {"current_steps": 11, "total_steps": 14, "loss": 0.9933, "lr": 2.5000000000000015e-06, "epoch": 1.5052631578947369, "percentage": 78.57, "elapsed_time": "0:04:00", "remaining_time": "0:01:05"}
12
- {"current_steps": 12, "total_steps": 14, "loss": 1.0245, "lr": 1.4644660940672628e-06, "epoch": 1.631578947368421, "percentage": 85.71, "elapsed_time": "0:04:17", "remaining_time": "0:00:42"}
13
- {"current_steps": 13, "total_steps": 14, "loss": 1.0274, "lr": 6.698729810778065e-07, "epoch": 1.7578947368421054, "percentage": 92.86, "elapsed_time": "0:04:37", "remaining_time": "0:00:21"}
14
- {"current_steps": 14, "total_steps": 14, "loss": 0.9399, "lr": 1.7037086855465902e-07, "epoch": 1.8842105263157896, "percentage": 100.0, "elapsed_time": "0:04:59", "remaining_time": "0:00:00"}
15
- {"current_steps": 14, "total_steps": 14, "epoch": 1.8842105263157896, "percentage": 100.0, "elapsed_time": "0:06:04", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 14, "loss": 1.3139, "lr": 0.0, "epoch": 0.12631578947368421, "percentage": 7.14, "elapsed_time": "0:00:27", "remaining_time": "0:05:51"}
2
+ {"current_steps": 2, "total_steps": 14, "loss": 1.3348, "lr": 5e-06, "epoch": 0.25263157894736843, "percentage": 14.29, "elapsed_time": "0:00:45", "remaining_time": "0:04:32"}
3
+ {"current_steps": 3, "total_steps": 14, "loss": 1.2368, "lr": 1e-05, "epoch": 0.37894736842105264, "percentage": 21.43, "elapsed_time": "0:01:07", "remaining_time": "0:04:07"}
4
+ {"current_steps": 4, "total_steps": 14, "loss": 1.1371, "lr": 9.829629131445342e-06, "epoch": 0.5052631578947369, "percentage": 28.57, "elapsed_time": "0:01:24", "remaining_time": "0:03:30"}
5
+ {"current_steps": 5, "total_steps": 14, "loss": 1.1389, "lr": 9.330127018922195e-06, "epoch": 0.631578947368421, "percentage": 35.71, "elapsed_time": "0:01:43", "remaining_time": "0:03:05"}
6
+ {"current_steps": 6, "total_steps": 14, "loss": 1.066, "lr": 8.535533905932739e-06, "epoch": 0.7578947368421053, "percentage": 42.86, "elapsed_time": "0:02:05", "remaining_time": "0:02:46"}
7
+ {"current_steps": 7, "total_steps": 14, "loss": 1.1584, "lr": 7.500000000000001e-06, "epoch": 0.8842105263157894, "percentage": 50.0, "elapsed_time": "0:02:25", "remaining_time": "0:02:25"}
8
+ {"current_steps": 8, "total_steps": 14, "loss": 2.098, "lr": 6.294095225512604e-06, "epoch": 1.1263157894736842, "percentage": 57.14, "elapsed_time": "0:03:03", "remaining_time": "0:02:17"}
9
+ {"current_steps": 9, "total_steps": 14, "loss": 1.0779, "lr": 5e-06, "epoch": 1.2526315789473683, "percentage": 64.29, "elapsed_time": "0:03:24", "remaining_time": "0:01:53"}
10
+ {"current_steps": 10, "total_steps": 14, "loss": 0.9586, "lr": 3.705904774487396e-06, "epoch": 1.3789473684210527, "percentage": 71.43, "elapsed_time": "0:03:41", "remaining_time": "0:01:28"}
11
+ {"current_steps": 11, "total_steps": 14, "loss": 0.9933, "lr": 2.5000000000000015e-06, "epoch": 1.5052631578947369, "percentage": 78.57, "elapsed_time": "0:03:59", "remaining_time": "0:01:05"}
12
+ {"current_steps": 12, "total_steps": 14, "loss": 1.0243, "lr": 1.4644660940672628e-06, "epoch": 1.631578947368421, "percentage": 85.71, "elapsed_time": "0:04:17", "remaining_time": "0:00:42"}
13
+ {"current_steps": 13, "total_steps": 14, "loss": 1.0271, "lr": 6.698729810778065e-07, "epoch": 1.7578947368421054, "percentage": 92.86, "elapsed_time": "0:04:37", "remaining_time": "0:00:21"}
14
+ {"current_steps": 14, "total_steps": 14, "loss": 0.94, "lr": 1.7037086855465902e-07, "epoch": 1.8842105263157896, "percentage": 100.0, "elapsed_time": "0:04:58", "remaining_time": "0:00:00"}
15
+ {"current_steps": 14, "total_steps": 14, "epoch": 1.8842105263157896, "percentage": 100.0, "elapsed_time": "0:06:06", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aaf25b60977e5cf3223721b185b4d7ca5a080b9b9fc18b89ba40acc426d1101
3
  size 7800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bded2ee1a3e4a6652222eb0c7478a16ce64b03d52a10847551afbccd9a96bf4b
3
  size 7800