Hugging Face's logo

mlfoundations-dev
/
no_pipeline_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
neginr commited on
Commit
9002bc8
·
verified ·
1 Parent(s): befd8b8

Training in progress, epoch 3

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:728c765a7967765e05698bf380d20b71f6f3ed45ba85fd88c6233e7f3a6b7af4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eac6bfb604f6172853f0207a3b5962b95e1f26276091ace82293083ae54346c
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:d63c35d8c02acad523d3fc86346a2322bb0c8a04835d1a7c76d3a82b6bd9259e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d653c697314c16f6969a10433252def909160dbcd5fbe63b42aa5d675f695e7
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:583cbb404f36f0c12d20731c486c495faf7427f4b3143616285e0bf10757a7a6
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5931281c9bdc2ca6c9ec5d4d748a27ab94f74be464f16971d05e0330a9c1e21b
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:e8dd3a7c3ef37508db157e7269c2a3f952b074858ca2477a1c4df64f11bf0f47
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c270bcdc52d332fe69a8ce911dbe808043c7e05dd0dc9e21ed7dbfbacb5fb5
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -39,3 +39,13 @@
39
  {"current_steps": 39, "total_steps": 70, "loss": 0.3361, "lr": 9.750693082619274e-06, "epoch": 3.75, "percentage": 55.71, "elapsed_time": "0:13:41", "remaining_time": "0:10:53"}
40
  {"current_steps": 40, "total_steps": 70, "loss": 0.32, "lr": 9.252699064135759e-06, "epoch": 3.84375, "percentage": 57.14, "elapsed_time": "0:13:54", "remaining_time": "0:10:25"}
41
  {"current_steps": 41, "total_steps": 70, "loss": 0.3349, "lr": 8.756562953525151e-06, "epoch": 3.9375, "percentage": 58.57, "elapsed_time": "0:14:06", "remaining_time": "0:09:58"}
 
 
 
 
 
 
 
 
 
 
 
39
  {"current_steps": 39, "total_steps": 70, "loss": 0.3361, "lr": 9.750693082619274e-06, "epoch": 3.75, "percentage": 55.71, "elapsed_time": "0:13:41", "remaining_time": "0:10:53"}
40
  {"current_steps": 40, "total_steps": 70, "loss": 0.32, "lr": 9.252699064135759e-06, "epoch": 3.84375, "percentage": 57.14, "elapsed_time": "0:13:54", "remaining_time": "0:10:25"}
41
  {"current_steps": 41, "total_steps": 70, "loss": 0.3349, "lr": 8.756562953525151e-06, "epoch": 3.9375, "percentage": 58.57, "elapsed_time": "0:14:06", "remaining_time": "0:09:58"}
42
+ {"current_steps": 42, "total_steps": 70, "loss": 0.3181, "lr": 8.263518223330698e-06, "epoch": 4.0625, "percentage": 60.0, "elapsed_time": "0:16:04", "remaining_time": "0:10:43"}
43
+ {"current_steps": 43, "total_steps": 70, "loss": 0.2878, "lr": 7.774790660436857e-06, "epoch": 4.15625, "percentage": 61.43, "elapsed_time": "0:16:15", "remaining_time": "0:10:12"}
44
+ {"current_steps": 44, "total_steps": 70, "loss": 0.2664, "lr": 7.291595318569951e-06, "epoch": 4.25, "percentage": 62.86, "elapsed_time": "0:16:30", "remaining_time": "0:09:45"}
45
+ {"current_steps": 45, "total_steps": 70, "loss": 0.2519, "lr": 6.815133497483157e-06, "epoch": 4.34375, "percentage": 64.29, "elapsed_time": "0:16:45", "remaining_time": "0:09:18"}
46
+ {"current_steps": 46, "total_steps": 70, "loss": 0.2389, "lr": 6.34658975633605e-06, "epoch": 4.4375, "percentage": 65.71, "elapsed_time": "0:16:59", "remaining_time": "0:08:51"}
47
+ {"current_steps": 47, "total_steps": 70, "loss": 0.2535, "lr": 5.887128968693887e-06, "epoch": 4.53125, "percentage": 67.14, "elapsed_time": "0:17:11", "remaining_time": "0:08:24"}
48
+ {"current_steps": 48, "total_steps": 70, "loss": 0.2445, "lr": 5.43789342646837e-06, "epoch": 4.625, "percentage": 68.57, "elapsed_time": "0:17:20", "remaining_time": "0:07:57"}
49
+ {"current_steps": 49, "total_steps": 70, "loss": 0.2338, "lr": 5.000000000000003e-06, "epoch": 4.71875, "percentage": 70.0, "elapsed_time": "0:17:33", "remaining_time": "0:07:31"}
50
+ {"current_steps": 50, "total_steps": 70, "loss": 0.2713, "lr": 4.5745373613424075e-06, "epoch": 4.8125, "percentage": 71.43, "elapsed_time": "0:17:47", "remaining_time": "0:07:07"}
51
+ {"current_steps": 51, "total_steps": 70, "loss": 0.2671, "lr": 4.162563277652104e-06, "epoch": 4.90625, "percentage": 72.86, "elapsed_time": "0:18:00", "remaining_time": "0:06:42"}