Hugging Face's logo

mlfoundations-dev
/
difficulty_sorting_easy_seed_math

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
f23abb2
·
verified ·
1 Parent(s): f4fa0f6

Training in progress, epoch 0

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 -31
  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 sha256:14dcd3faec9b3e627bec90c775a2820035a9815985f0c9ea7f527ffb8044d6b9
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b767177671a88725a2c2af492fb3c09ae0388e18a6a9885e4f42d246e511c0c
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b6c4c297dfb691cec0fa1e1bbfe1ff423719f6c3a235c6f789b781cd29d1825
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81691fbe51ca46074db7cb9b8cbfe840fe01681740946f007f3b2f0712a49377
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fe6e62cece3520992478d058f61e6b18b98a77dde4ba2140819a8229154af3f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9582eec4559946641114f0403c57e9cbf81d4dce1ebbd43d42df8b5a04421037
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:d28395a5f22becae37590f334d1dc2edbfe5c69a4b58815de13f8c19d7f8eaaa
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc95e64ef9c757c92f55986df57210fbd4d62e634fa1e78a29161a8ff116b954
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,31 +1,15 @@
1
- {"current_steps": 1, "total_steps": 30, "loss": 1.1578, "lr": 3.3333333333333333e-06, "epoch": 0.09523809523809523, "percentage": 3.33, "elapsed_time": "0:00:54", "remaining_time": "0:26:33"}
2
- {"current_steps": 2, "total_steps": 30, "loss": 1.1462, "lr": 6.666666666666667e-06, "epoch": 0.19047619047619047, "percentage": 6.67, "elapsed_time": "0:01:39", "remaining_time": "0:23:15"}
3
- {"current_steps": 3, "total_steps": 30, "loss": 1.1284, "lr": 1e-05, "epoch": 0.2857142857142857, "percentage": 10.0, "elapsed_time": "0:02:28", "remaining_time": "0:22:19"}
4
- {"current_steps": 4, "total_steps": 30, "loss": 0.9639, "lr": 9.966191788709716e-06, "epoch": 0.38095238095238093, "percentage": 13.33, "elapsed_time": "0:03:14", "remaining_time": "0:21:05"}
5
- {"current_steps": 5, "total_steps": 30, "loss": 0.9276, "lr": 9.86522435289912e-06, "epoch": 0.47619047619047616, "percentage": 16.67, "elapsed_time": "0:03:51", "remaining_time": "0:19:19"}
6
- {"current_steps": 6, "total_steps": 30, "loss": 0.9728, "lr": 9.698463103929542e-06, "epoch": 0.5714285714285714, "percentage": 20.0, "elapsed_time": "0:04:33", "remaining_time": "0:18:12"}
7
- {"current_steps": 7, "total_steps": 30, "loss": 0.9381, "lr": 9.468163201617063e-06, "epoch": 0.6666666666666666, "percentage": 23.33, "elapsed_time": "0:05:00", "remaining_time": "0:16:28"}
8
- {"current_steps": 8, "total_steps": 30, "loss": 0.8628, "lr": 9.177439057064684e-06, "epoch": 0.7619047619047619, "percentage": 26.67, "elapsed_time": "0:05:41", "remaining_time": "0:15:39"}
9
- {"current_steps": 9, "total_steps": 30, "loss": 0.8703, "lr": 8.83022221559489e-06, "epoch": 0.8571428571428571, "percentage": 30.0, "elapsed_time": "0:06:16", "remaining_time": "0:14:37"}
10
- {"current_steps": 10, "total_steps": 30, "loss": 0.8566, "lr": 8.43120818934367e-06, "epoch": 0.9523809523809523, "percentage": 33.33, "elapsed_time": "0:06:52", "remaining_time": "0:13:45"}
11
- {"current_steps": 11, "total_steps": 30, "loss": 1.2228, "lr": 7.985792958513932e-06, "epoch": 1.0476190476190477, "percentage": 36.67, "elapsed_time": "0:08:13", "remaining_time": "0:14:11"}
12
- {"current_steps": 12, "total_steps": 30, "loss": 0.8184, "lr": 7.500000000000001e-06, "epoch": 1.1428571428571428, "percentage": 40.0, "elapsed_time": "0:08:47", "remaining_time": "0:13:11"}
13
- {"current_steps": 13, "total_steps": 30, "loss": 0.7946, "lr": 6.980398830195785e-06, "epoch": 1.2380952380952381, "percentage": 43.33, "elapsed_time": "0:09:28", "remaining_time": "0:12:23"}
14
- {"current_steps": 14, "total_steps": 30, "loss": 0.854, "lr": 6.434016163555452e-06, "epoch": 1.3333333333333333, "percentage": 46.67, "elapsed_time": "0:09:59", "remaining_time": "0:11:24"}
15
- {"current_steps": 15, "total_steps": 30, "loss": 0.7038, "lr": 5.8682408883346535e-06, "epoch": 1.4285714285714286, "percentage": 50.0, "elapsed_time": "0:10:32", "remaining_time": "0:10:32"}
16
- {"current_steps": 16, "total_steps": 30, "loss": 0.8028, "lr": 5.290724144552379e-06, "epoch": 1.5238095238095237, "percentage": 53.33, "elapsed_time": "0:11:01", "remaining_time": "0:09:39"}
17
- {"current_steps": 17, "total_steps": 30, "loss": 0.8274, "lr": 4.7092758554476215e-06, "epoch": 1.619047619047619, "percentage": 56.67, "elapsed_time": "0:11:53", "remaining_time": "0:09:05"}
18
- {"current_steps": 18, "total_steps": 30, "loss": 0.9132, "lr": 4.131759111665349e-06, "epoch": 1.7142857142857144, "percentage": 60.0, "elapsed_time": "0:12:42", "remaining_time": "0:08:28"}
19
- {"current_steps": 19, "total_steps": 30, "loss": 0.7172, "lr": 3.5659838364445505e-06, "epoch": 1.8095238095238095, "percentage": 63.33, "elapsed_time": "0:13:33", "remaining_time": "0:07:50"}
20
- {"current_steps": 20, "total_steps": 30, "loss": 0.856, "lr": 3.019601169804216e-06, "epoch": 1.9047619047619047, "percentage": 66.67, "elapsed_time": "0:14:18", "remaining_time": "0:07:09"}
21
- {"current_steps": 21, "total_steps": 30, "loss": 1.0469, "lr": 2.5000000000000015e-06, "epoch": 2.0, "percentage": 70.0, "elapsed_time": "0:14:59", "remaining_time": "0:06:25"}
22
- {"current_steps": 22, "total_steps": 30, "loss": 0.7511, "lr": 2.0142070414860704e-06, "epoch": 2.0952380952380953, "percentage": 73.33, "elapsed_time": "0:16:35", "remaining_time": "0:06:01"}
23
- {"current_steps": 23, "total_steps": 30, "loss": 0.6867, "lr": 1.5687918106563326e-06, "epoch": 2.1904761904761907, "percentage": 76.67, "elapsed_time": "0:17:04", "remaining_time": "0:05:11"}
24
- {"current_steps": 24, "total_steps": 30, "loss": 0.7337, "lr": 1.1697777844051105e-06, "epoch": 2.2857142857142856, "percentage": 80.0, "elapsed_time": "0:17:37", "remaining_time": "0:04:24"}
25
- {"current_steps": 25, "total_steps": 30, "loss": 0.8412, "lr": 8.225609429353187e-07, "epoch": 2.380952380952381, "percentage": 83.33, "elapsed_time": "0:18:25", "remaining_time": "0:03:41"}
26
- {"current_steps": 26, "total_steps": 30, "loss": 0.7219, "lr": 5.318367983829393e-07, "epoch": 2.4761904761904763, "percentage": 86.67, "elapsed_time": "0:19:00", "remaining_time": "0:02:55"}
27
- {"current_steps": 27, "total_steps": 30, "loss": 0.7787, "lr": 3.015368960704584e-07, "epoch": 2.571428571428571, "percentage": 90.0, "elapsed_time": "0:19:49", "remaining_time": "0:02:12"}
28
- {"current_steps": 28, "total_steps": 30, "loss": 0.8023, "lr": 1.3477564710088097e-07, "epoch": 2.6666666666666665, "percentage": 93.33, "elapsed_time": "0:20:25", "remaining_time": "0:01:27"}
29
- {"current_steps": 29, "total_steps": 30, "loss": 0.7005, "lr": 3.3808211290284886e-08, "epoch": 2.761904761904762, "percentage": 96.67, "elapsed_time": "0:21:00", "remaining_time": "0:00:43"}
30
- {"current_steps": 30, "total_steps": 30, "loss": 0.7909, "lr": 0.0, "epoch": 2.857142857142857, "percentage": 100.0, "elapsed_time": "0:21:50", "remaining_time": "0:00:00"}
31
- {"current_steps": 30, "total_steps": 30, "epoch": 2.857142857142857, "percentage": 100.0, "elapsed_time": "0:23:30", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 30, "loss": 1.1578, "lr": 3.3333333333333333e-06, "epoch": 0.09523809523809523, "percentage": 3.33, "elapsed_time": "0:00:55", "remaining_time": "0:26:58"}
2
+ {"current_steps": 2, "total_steps": 30, "loss": 1.1462, "lr": 6.666666666666667e-06, "epoch": 0.19047619047619047, "percentage": 6.67, "elapsed_time": "0:01:41", "remaining_time": "0:23:39"}
3
+ {"current_steps": 3, "total_steps": 30, "loss": 1.1288, "lr": 1e-05, "epoch": 0.2857142857142857, "percentage": 10.0, "elapsed_time": "0:02:30", "remaining_time": "0:22:38"}
4
+ {"current_steps": 4, "total_steps": 30, "loss": 0.9638, "lr": 9.966191788709716e-06, "epoch": 0.38095238095238093, "percentage": 13.33, "elapsed_time": "0:03:17", "remaining_time": "0:21:23"}
5
+ {"current_steps": 5, "total_steps": 30, "loss": 0.9276, "lr": 9.86522435289912e-06, "epoch": 0.47619047619047616, "percentage": 16.67, "elapsed_time": "0:03:54", "remaining_time": "0:19:34"}
6
+ {"current_steps": 6, "total_steps": 30, "loss": 0.9728, "lr": 9.698463103929542e-06, "epoch": 0.5714285714285714, "percentage": 20.0, "elapsed_time": "0:04:36", "remaining_time": "0:18:27"}
7
+ {"current_steps": 7, "total_steps": 30, "loss": 0.938, "lr": 9.468163201617063e-06, "epoch": 0.6666666666666666, "percentage": 23.33, "elapsed_time": "0:05:04", "remaining_time": "0:16:41"}
8
+ {"current_steps": 8, "total_steps": 30, "loss": 0.8628, "lr": 9.177439057064684e-06, "epoch": 0.7619047619047619, "percentage": 26.67, "elapsed_time": "0:05:45", "remaining_time": "0:15:50"}
9
+ {"current_steps": 9, "total_steps": 30, "loss": 0.8703, "lr": 8.83022221559489e-06, "epoch": 0.8571428571428571, "percentage": 30.0, "elapsed_time": "0:06:20", "remaining_time": "0:14:47"}
10
+ {"current_steps": 10, "total_steps": 30, "loss": 0.8566, "lr": 8.43120818934367e-06, "epoch": 0.9523809523809523, "percentage": 33.33, "elapsed_time": "0:06:56", "remaining_time": "0:13:53"}
11
+ {"current_steps": 11, "total_steps": 30, "loss": 1.2228, "lr": 7.985792958513932e-06, "epoch": 1.0476190476190477, "percentage": 36.67, "elapsed_time": "0:08:17", "remaining_time": "0:14:19"}
12
+ {"current_steps": 12, "total_steps": 30, "loss": 0.8186, "lr": 7.500000000000001e-06, "epoch": 1.1428571428571428, "percentage": 40.0, "elapsed_time": "0:08:51", "remaining_time": "0:13:17"}
13
+ {"current_steps": 13, "total_steps": 30, "loss": 0.7946, "lr": 6.980398830195785e-06, "epoch": 1.2380952380952381, "percentage": 43.33, "elapsed_time": "0:09:33", "remaining_time": "0:12:29"}
14
+ {"current_steps": 14, "total_steps": 30, "loss": 0.8539, "lr": 6.434016163555452e-06, "epoch": 1.3333333333333333, "percentage": 46.67, "elapsed_time": "0:10:04", "remaining_time": "0:11:30"}
15
+ {"current_steps": 15, "total_steps": 30, "loss": 0.7039, "lr": 5.8682408883346535e-06, "epoch": 1.4285714285714286, "percentage": 50.0, "elapsed_time": "0:10:37", "remaining_time": "0:10:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d065e3bf570204616a753d2c9803e8074ba42b6d6ba1a1643abf3e76505e7c55
3
  size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9f608b5daf16e2cf78913d73d7fe0d87c2de194dd3597ee4f6f13d9eda7972
3
  size 7416