Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks_0p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
EtashGuha commited on
Commit
555c4da
·
verified ·
1 Parent(s): e07c818

Training in progress, epoch 2

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 +5 -8
  6. training_args.bin +2 -2
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:073cd4c77bd8c8fa4859393935d0951739749e7c5f7623cee78a7fa1e9d2d4da
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbbe4f2401b0dedb2621f035def3fdc770ae2717a793eae19dcadbb8d0315d3
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7d1de55ea24f2d6324bf391e8c42b406597c1a03e5b389636261fb7649b0344
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e00961e59fcc3a5a7647f8bbdbe80713bfe3ffccf3cf9280d0b0bdf9f47c1c7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94690222a105abce79e67ebc0bfa0a3a9e37b549bec1611959d54af58ff40589
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2993b9dfe3393fb550e0c8bf4b255dc88da8f35f90407815b1ae9e7a76c21b48
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd9e5192c3d066d259760453812d4023f222ee87338d5a87b45e09216d582eb1
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f6fc322f41f2add68761960e3e3ed7fb9ca795e73faec2bf7d92b7f42a6d7c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,8 +1,5 @@
1
- {"current_steps": 10, "total_steps": 99, "loss": 0.731, "lr": 5e-06, "epoch": 0.3018867924528302, "percentage": 10.1, "elapsed_time": "0:26:23", "remaining_time": "3:54:48"}
2
- {"current_steps": 20, "total_steps": 99, "loss": 0.6309, "lr": 5e-06, "epoch": 0.6037735849056604, "percentage": 20.2, "elapsed_time": "0:52:42", "remaining_time": "3:28:11"}
3
- {"current_steps": 30, "total_steps": 99, "loss": 0.5802, "lr": 5e-06, "epoch": 0.9056603773584906, "percentage": 30.3, "elapsed_time": "1:19:01", "remaining_time": "3:01:45"}
4
- {"current_steps": 33, "total_steps": 99, "eval_loss": 0.5490819811820984, "epoch": 0.9962264150943396, "percentage": 33.33, "elapsed_time": "1:28:58", "remaining_time": "2:57:57"}
5
- {"current_steps": 40, "total_steps": 99, "loss": 0.5315, "lr": 5e-06, "epoch": 1.2075471698113207, "percentage": 40.4, "elapsed_time": "1:48:36", "remaining_time": "2:40:11"}
6
- {"current_steps": 50, "total_steps": 99, "loss": 0.5003, "lr": 5e-06, "epoch": 1.509433962264151, "percentage": 50.51, "elapsed_time": "2:14:57", "remaining_time": "2:12:15"}
7
- {"current_steps": 60, "total_steps": 99, "loss": 0.4917, "lr": 5e-06, "epoch": 1.8113207547169812, "percentage": 60.61, "elapsed_time": "2:41:20", "remaining_time": "1:44:52"}
8
- {"current_steps": 66, "total_steps": 99, "eval_loss": 0.511838436126709, "epoch": 1.9924528301886792, "percentage": 66.67, "elapsed_time": "2:59:35", "remaining_time": "1:29:47"}
 
1
+ {"current_steps": 70, "total_steps": 99, "loss": 0.4456, "lr": 5e-06, "epoch": 2.120754716981132, "percentage": 70.71, "elapsed_time": "0:10:30", "remaining_time": "0:04:21"}
2
+ {"current_steps": 80, "total_steps": 99, "loss": 0.431, "lr": 5e-06, "epoch": 2.422641509433962, "percentage": 80.81, "elapsed_time": "0:36:31", "remaining_time": "0:08:40"}
3
+ {"current_steps": 90, "total_steps": 99, "loss": 0.4262, "lr": 5e-06, "epoch": 2.7245283018867923, "percentage": 90.91, "elapsed_time": "1:02:32", "remaining_time": "0:06:15"}
4
+ {"current_steps": 99, "total_steps": 99, "eval_loss": 0.5040494799613953, "epoch": 2.9962264150943394, "percentage": 100.0, "elapsed_time": "1:29:11", "remaining_time": "0:00:00"}
5
+ {"current_steps": 99, "total_steps": 99, "epoch": 2.9962264150943394, "percentage": 100.0, "elapsed_time": "1:30:08", "remaining_time": "0:00:00"}
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c4582d80726051cb3153b82bdac926e290ed9da28ef561bcb304bd4747322d0
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254be8695672bbd0f5e936004bf3f0ba3c804c548c914dfe3b8b4a49bb276fba
3
+ size 7352