Hugging Face's logo

mlfoundations-dev
/
b2_math_random_0.3k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
ryanmarten commited on
Commit
9a0e411
·
verified ·
1 Parent(s): 3d1da37

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 +18 -18
  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 sha256:89d4c0847172a7ea1a1727bf59ef06aa1cb8826066c769a53ddc3b4d805aaf03
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457453d8185955d638851af464724c8bbea6f4c3c3bd0ac6734abc942501e4dd
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:c1f5202d6d07056b84707d3d91c56e9a033d0afa5d49b7e35bce4c9f369fb7d4
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a6fa90b330a0a2b6f5a20bc75af1871b3b96ffab0e4e75a4762450c0453b9c
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92286f318fe9e3520052256a9d0c3f554d8cc4c0312b9327ac313f7280e18e69
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111f0eaaaf91145f5674aaf17e1996a41c8b9af7e61be7479d27e22175eda013
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78eebddfd7c281f51279d5d83975c41c803b4874b4e8a3e6d667028df34d20cc
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e1aa8993b82e1656b98b84d1fa0b10a222c848cd4ddc61721ef7fdc6a449f4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,18 +1,18 @@
1
- {"current_steps": 1, "total_steps": 117, "loss": 0.876, "lr": 8.333333333333333e-07, "epoch": 0.10126582278481013, "percentage": 0.85, "elapsed_time": "0:00:15", "remaining_time": "0:29:40"}
2
- {"current_steps": 2, "total_steps": 117, "loss": 0.8658, "lr": 1.6666666666666667e-06, "epoch": 0.20253164556962025, "percentage": 1.71, "elapsed_time": "0:00:42", "remaining_time": "0:40:38"}
3
- {"current_steps": 3, "total_steps": 117, "loss": 0.818, "lr": 2.5e-06, "epoch": 0.3037974683544304, "percentage": 2.56, "elapsed_time": "0:01:16", "remaining_time": "0:48:18"}
4
- {"current_steps": 4, "total_steps": 117, "loss": 0.796, "lr": 3.3333333333333333e-06, "epoch": 0.4050632911392405, "percentage": 3.42, "elapsed_time": "0:01:30", "remaining_time": "0:42:45"}
5
- {"current_steps": 5, "total_steps": 117, "loss": 0.8071, "lr": 4.166666666666667e-06, "epoch": 0.5063291139240507, "percentage": 4.27, "elapsed_time": "0:01:54", "remaining_time": "0:42:48"}
6
- {"current_steps": 6, "total_steps": 117, "loss": 0.7126, "lr": 5e-06, "epoch": 0.6075949367088608, "percentage": 5.13, "elapsed_time": "0:02:20", "remaining_time": "0:43:11"}
7
- {"current_steps": 7, "total_steps": 117, "loss": 0.7192, "lr": 5.833333333333334e-06, "epoch": 0.7088607594936709, "percentage": 5.98, "elapsed_time": "0:02:49", "remaining_time": "0:44:29"}
8
- {"current_steps": 8, "total_steps": 117, "loss": 0.6697, "lr": 6.666666666666667e-06, "epoch": 0.810126582278481, "percentage": 6.84, "elapsed_time": "0:03:04", "remaining_time": "0:41:57"}
9
- {"current_steps": 9, "total_steps": 117, "loss": 0.6903, "lr": 7.500000000000001e-06, "epoch": 0.9113924050632911, "percentage": 7.69, "elapsed_time": "0:03:22", "remaining_time": "0:40:27"}
10
- {"current_steps": 10, "total_steps": 117, "loss": 0.637, "lr": 8.333333333333334e-06, "epoch": 1.0506329113924051, "percentage": 8.55, "elapsed_time": "0:04:22", "remaining_time": "0:46:50"}
11
- {"current_steps": 11, "total_steps": 117, "loss": 0.6389, "lr": 9.166666666666666e-06, "epoch": 1.1518987341772151, "percentage": 9.4, "elapsed_time": "0:04:43", "remaining_time": "0:45:36"}
12
- {"current_steps": 12, "total_steps": 117, "loss": 0.5806, "lr": 1e-05, "epoch": 1.2531645569620253, "percentage": 10.26, "elapsed_time": "0:04:59", "remaining_time": "0:43:38"}
13
- {"current_steps": 13, "total_steps": 117, "loss": 0.5678, "lr": 9.997762161417517e-06, "epoch": 1.3544303797468356, "percentage": 11.11, "elapsed_time": "0:05:21", "remaining_time": "0:42:53"}
14
- {"current_steps": 14, "total_steps": 117, "loss": 0.5445, "lr": 9.991050648838676e-06, "epoch": 1.4556962025316456, "percentage": 11.97, "elapsed_time": "0:05:49", "remaining_time": "0:42:51"}
15
- {"current_steps": 15, "total_steps": 117, "loss": 0.5839, "lr": 9.979871469976197e-06, "epoch": 1.5569620253164556, "percentage": 12.82, "elapsed_time": "0:06:14", "remaining_time": "0:42:27"}
16
- {"current_steps": 16, "total_steps": 117, "loss": 0.5686, "lr": 9.964234631709188e-06, "epoch": 1.6582278481012658, "percentage": 13.68, "elapsed_time": "0:06:38", "remaining_time": "0:41:55"}
17
- {"current_steps": 17, "total_steps": 117, "loss": 0.527, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:06:55", "remaining_time": "0:40:43"}
18
- {"current_steps": 18, "total_steps": 117, "loss": 0.4995, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:07:15", "remaining_time": "0:39:53"}
 
1
+ {"current_steps": 1, "total_steps": 117, "loss": 0.876, "lr": 8.333333333333333e-07, "epoch": 0.10126582278481013, "percentage": 0.85, "elapsed_time": "0:00:15", "remaining_time": "0:29:39"}
2
+ {"current_steps": 2, "total_steps": 117, "loss": 0.8658, "lr": 1.6666666666666667e-06, "epoch": 0.20253164556962025, "percentage": 1.71, "elapsed_time": "0:00:42", "remaining_time": "0:40:29"}
3
+ {"current_steps": 3, "total_steps": 117, "loss": 0.8177, "lr": 2.5e-06, "epoch": 0.3037974683544304, "percentage": 2.56, "elapsed_time": "0:01:15", "remaining_time": "0:48:07"}
4
+ {"current_steps": 4, "total_steps": 117, "loss": 0.7961, "lr": 3.3333333333333333e-06, "epoch": 0.4050632911392405, "percentage": 3.42, "elapsed_time": "0:01:30", "remaining_time": "0:42:35"}
5
+ {"current_steps": 5, "total_steps": 117, "loss": 0.8073, "lr": 4.166666666666667e-06, "epoch": 0.5063291139240507, "percentage": 4.27, "elapsed_time": "0:01:54", "remaining_time": "0:42:39"}
6
+ {"current_steps": 6, "total_steps": 117, "loss": 0.7123, "lr": 5e-06, "epoch": 0.6075949367088608, "percentage": 5.13, "elapsed_time": "0:02:19", "remaining_time": "0:43:00"}
7
+ {"current_steps": 7, "total_steps": 117, "loss": 0.719, "lr": 5.833333333333334e-06, "epoch": 0.7088607594936709, "percentage": 5.98, "elapsed_time": "0:02:49", "remaining_time": "0:44:17"}
8
+ {"current_steps": 8, "total_steps": 117, "loss": 0.6693, "lr": 6.666666666666667e-06, "epoch": 0.810126582278481, "percentage": 6.84, "elapsed_time": "0:03:03", "remaining_time": "0:41:46"}
9
+ {"current_steps": 9, "total_steps": 117, "loss": 0.6902, "lr": 7.500000000000001e-06, "epoch": 0.9113924050632911, "percentage": 7.69, "elapsed_time": "0:03:21", "remaining_time": "0:40:16"}
10
+ {"current_steps": 10, "total_steps": 117, "loss": 0.6371, "lr": 8.333333333333334e-06, "epoch": 1.0506329113924051, "percentage": 8.55, "elapsed_time": "0:04:23", "remaining_time": "0:46:59"}
11
+ {"current_steps": 11, "total_steps": 117, "loss": 0.6389, "lr": 9.166666666666666e-06, "epoch": 1.1518987341772151, "percentage": 9.4, "elapsed_time": "0:04:44", "remaining_time": "0:45:43"}
12
+ {"current_steps": 12, "total_steps": 117, "loss": 0.5804, "lr": 1e-05, "epoch": 1.2531645569620253, "percentage": 10.26, "elapsed_time": "0:04:59", "remaining_time": "0:43:44"}
13
+ {"current_steps": 13, "total_steps": 117, "loss": 0.5677, "lr": 9.997762161417517e-06, "epoch": 1.3544303797468356, "percentage": 11.11, "elapsed_time": "0:05:22", "remaining_time": "0:42:57"}
14
+ {"current_steps": 14, "total_steps": 117, "loss": 0.5447, "lr": 9.991050648838676e-06, "epoch": 1.4556962025316456, "percentage": 11.97, "elapsed_time": "0:05:49", "remaining_time": "0:42:54"}
15
+ {"current_steps": 15, "total_steps": 117, "loss": 0.5839, "lr": 9.979871469976197e-06, "epoch": 1.5569620253164556, "percentage": 12.82, "elapsed_time": "0:06:14", "remaining_time": "0:42:29"}
16
+ {"current_steps": 16, "total_steps": 117, "loss": 0.5685, "lr": 9.964234631709188e-06, "epoch": 1.6582278481012658, "percentage": 13.68, "elapsed_time": "0:06:38", "remaining_time": "0:41:56"}
17
+ {"current_steps": 17, "total_steps": 117, "loss": 0.5271, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:06:55", "remaining_time": "0:40:44"}
18
+ {"current_steps": 18, "total_steps": 117, "loss": 0.4994, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:07:15", "remaining_time": "0:39:53"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2859ec1baf102e41a82d274d7077f7bb9a00fa5f72e60d5292058aa6516e9dc0
3
  size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99514c761c33ab792952a8955a52d49ed47e7703d4fec04afa091365a32dd59f
3
  size 7288