Hugging Face's logo

mlfoundations-dev
/
1k_globalbatchsize32_lr5e6_epochs3

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
c973e72
·
verified ·
1 Parent(s): ebe018a

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 +32 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2245ceeaae1d0f8549245660af05eb277b617047977390c79b4e673ea5b61828
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af14d64657ec78f498d4305e02981b721db19908912d80e521ba70b7a9fb23c1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:284cd0be05f5793d7b7c2b7a0bc722f19d5f772dabbbc097b8e81fb90203749a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681d9171d3db2850f63c220ca53c05e6f79f7be14d31c24175c1a7ab607e9ec1
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:c7bcfda3236bede3f29f7dc378ca0da07bcf75ea18285ee8d40ec0488d319304
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b301be3435b95029ac15ce495497e3165c4dcd3ecb3b67956e33d44d9f572
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4160874562b87a53479ecbaf5bf652f044d6e68ceb19c922447536696520468e
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad037de4f53ff81f5b125a892f4bdd3bf6245fc24ca395117d0e9480a5009406
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -34,3 +34,35 @@
34
  {"current_steps": 34, "total_steps": 93, "loss": 0.5749, "lr": 4.037496110044885e-06, "epoch": 1.088, "percentage": 36.56, "elapsed_time": "0:19:43", "remaining_time": "0:34:13"}
35
  {"current_steps": 35, "total_steps": 93, "loss": 0.614, "lr": 3.961797195560118e-06, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:20:10", "remaining_time": "0:33:26"}
36
  {"current_steps": 36, "total_steps": 93, "loss": 0.5273, "lr": 3.884004270673711e-06, "epoch": 1.152, "percentage": 38.71, "elapsed_time": "0:20:44", "remaining_time": "0:32:49"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  {"current_steps": 34, "total_steps": 93, "loss": 0.5749, "lr": 4.037496110044885e-06, "epoch": 1.088, "percentage": 36.56, "elapsed_time": "0:19:43", "remaining_time": "0:34:13"}
35
  {"current_steps": 35, "total_steps": 93, "loss": 0.614, "lr": 3.961797195560118e-06, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:20:10", "remaining_time": "0:33:26"}
36
  {"current_steps": 36, "total_steps": 93, "loss": 0.5273, "lr": 3.884004270673711e-06, "epoch": 1.152, "percentage": 38.71, "elapsed_time": "0:20:44", "remaining_time": "0:32:49"}
37
+ {"current_steps": 37, "total_steps": 93, "loss": 0.6375, "lr": 3.8042287730012117e-06, "epoch": 1.184, "percentage": 39.78, "elapsed_time": "0:21:25", "remaining_time": "0:32:25"}
38
+ {"current_steps": 38, "total_steps": 93, "loss": 0.6295, "lr": 3.7225849801745835e-06, "epoch": 1.216, "percentage": 40.86, "elapsed_time": "0:22:03", "remaining_time": "0:31:55"}
39
+ {"current_steps": 39, "total_steps": 93, "loss": 0.5147, "lr": 3.6391898461406045e-06, "epoch": 1.248, "percentage": 41.94, "elapsed_time": "0:22:37", "remaining_time": "0:31:19"}
40
+ {"current_steps": 40, "total_steps": 93, "loss": 0.5539, "lr": 3.55416283362546e-06, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:23:06", "remaining_time": "0:30:37"}
41
+ {"current_steps": 41, "total_steps": 93, "loss": 0.4879, "lr": 3.4676257430055438e-06, "epoch": 1.312, "percentage": 44.09, "elapsed_time": "0:23:36", "remaining_time": "0:29:56"}
42
+ {"current_steps": 42, "total_steps": 93, "loss": 0.627, "lr": 3.3797025378295826e-06, "epoch": 1.3439999999999999, "percentage": 45.16, "elapsed_time": "0:24:18", "remaining_time": "0:29:31"}
43
+ {"current_steps": 43, "total_steps": 93, "loss": 0.4996, "lr": 3.29051916724206e-06, "epoch": 1.376, "percentage": 46.24, "elapsed_time": "0:24:54", "remaining_time": "0:28:57"}
44
+ {"current_steps": 44, "total_steps": 93, "loss": 0.6106, "lr": 3.2002033855622683e-06, "epoch": 1.408, "percentage": 47.31, "elapsed_time": "0:25:24", "remaining_time": "0:28:17"}
45
+ {"current_steps": 45, "total_steps": 93, "loss": 0.644, "lr": 3.1088845692774798e-06, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:25:59", "remaining_time": "0:27:43"}
46
+ {"current_steps": 46, "total_steps": 93, "loss": 0.5099, "lr": 3.0166935317123824e-06, "epoch": 1.472, "percentage": 49.46, "elapsed_time": "0:26:28", "remaining_time": "0:27:02"}
47
+ {"current_steps": 47, "total_steps": 93, "loss": 0.5716, "lr": 2.9237623356402423e-06, "epoch": 1.504, "percentage": 50.54, "elapsed_time": "0:27:02", "remaining_time": "0:26:27"}
48
+ {"current_steps": 48, "total_steps": 93, "loss": 0.5895, "lr": 2.8302241041042564e-06, "epoch": 1.536, "percentage": 51.61, "elapsed_time": "0:27:35", "remaining_time": "0:25:52"}
49
+ {"current_steps": 49, "total_steps": 93, "loss": 0.6191, "lr": 2.7362128297200784e-06, "epoch": 1.568, "percentage": 52.69, "elapsed_time": "0:28:10", "remaining_time": "0:25:17"}
50
+ {"current_steps": 50, "total_steps": 93, "loss": 0.5595, "lr": 2.6418631827326857e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:28:44", "remaining_time": "0:24:42"}
51
+ {"current_steps": 51, "total_steps": 93, "loss": 0.5506, "lr": 2.547310318102548e-06, "epoch": 1.6320000000000001, "percentage": 54.84, "elapsed_time": "0:29:12", "remaining_time": "0:24:03"}
52
+ {"current_steps": 52, "total_steps": 93, "loss": 0.6013, "lr": 2.4526896818974534e-06, "epoch": 1.6640000000000001, "percentage": 55.91, "elapsed_time": "0:29:40", "remaining_time": "0:23:24"}
53
+ {"current_steps": 53, "total_steps": 93, "loss": 0.5804, "lr": 2.358136817267315e-06, "epoch": 1.696, "percentage": 56.99, "elapsed_time": "0:30:07", "remaining_time": "0:22:44"}
54
+ {"current_steps": 54, "total_steps": 93, "loss": 0.5112, "lr": 2.263787170279922e-06, "epoch": 1.728, "percentage": 58.06, "elapsed_time": "0:30:45", "remaining_time": "0:22:13"}
55
+ {"current_steps": 55, "total_steps": 93, "loss": 0.5302, "lr": 2.169775895895745e-06, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:31:17", "remaining_time": "0:21:37"}
56
+ {"current_steps": 56, "total_steps": 93, "loss": 0.5912, "lr": 2.0762376643597586e-06, "epoch": 1.792, "percentage": 60.22, "elapsed_time": "0:31:45", "remaining_time": "0:20:59"}
57
+ {"current_steps": 57, "total_steps": 93, "loss": 0.524, "lr": 1.9833064682876175e-06, "epoch": 1.8239999999999998, "percentage": 61.29, "elapsed_time": "0:32:17", "remaining_time": "0:20:23"}
58
+ {"current_steps": 58, "total_steps": 93, "loss": 0.567, "lr": 1.8911154307225204e-06, "epoch": 1.8559999999999999, "percentage": 62.37, "elapsed_time": "0:32:47", "remaining_time": "0:19:47"}
59
+ {"current_steps": 59, "total_steps": 93, "loss": 0.4889, "lr": 1.7997966144377328e-06, "epoch": 1.888, "percentage": 63.44, "elapsed_time": "0:33:08", "remaining_time": "0:19:05"}
60
+ {"current_steps": 60, "total_steps": 93, "loss": 0.5566, "lr": 1.7094808327579401e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:33:42", "remaining_time": "0:18:32"}
61
+ {"current_steps": 61, "total_steps": 93, "loss": 0.6002, "lr": 1.6202974621704176e-06, "epoch": 1.952, "percentage": 65.59, "elapsed_time": "0:34:16", "remaining_time": "0:17:58"}
62
+ {"current_steps": 62, "total_steps": 93, "loss": 0.5745, "lr": 1.5323742569944573e-06, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:34:51", "remaining_time": "0:17:25"}
63
+ {"current_steps": 63, "total_steps": 93, "loss": 0.8374, "lr": 1.44583716637454e-06, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "0:36:34", "remaining_time": "0:17:25"}
64
+ {"current_steps": 64, "total_steps": 93, "loss": 0.5162, "lr": 1.3608101538593965e-06, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "0:37:01", "remaining_time": "0:16:46"}
65
+ {"current_steps": 65, "total_steps": 93, "loss": 0.5509, "lr": 1.277415019825417e-06, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:37:25", "remaining_time": "0:16:07"}
66
+ {"current_steps": 66, "total_steps": 93, "loss": 0.505, "lr": 1.195771226998789e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "0:37:49", "remaining_time": "0:15:28"}
67
+ {"current_steps": 67, "total_steps": 93, "loss": 0.5505, "lr": 1.1159957293262888e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "0:38:27", "remaining_time": "0:14:55"}
68
+ {"current_steps": 68, "total_steps": 93, "loss": 0.4181, "lr": 1.0382028044398823e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "0:38:59", "remaining_time": "0:14:20"}