Hugging Face's logo

mlfoundations-dev
/
stackexchange_codereview

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
61928c0
·
verified ·
1 Parent(s): 62a3bb0

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 +7 -7
  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 sha256:7c93e846d132f31f384b2db8f880faa83a97e20bbd4cc28bb84b2c6a06083bdc
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578c8e2c4da3b850a713f99afc961a815161da5c7379d1e865d60b525b338636
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:889d9a3739dce85625358e9818b7641858a9d12ac11777d345f8395663e9de71
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f3b48e637a25e099d837a9da3349ba881ba4e5808f71b2ad8f7f0a08114c00
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:454516d75aad64f29eebf63d167a78eeefa0856550865dd479ec86a39b2b33f0
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8906b0b1e681eeb5e1c7455cf8bf60cb456cf1c5f71ca9102c58241ab464c6cd
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:c285da2660c6fc6df4d7e51c629dd3b11e94c2357c107648a64678d63135ea49
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489b85346139e0560d8042c251848b48b835240d95582a3817eff9579bac83df
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,7 +1,7 @@
1
- {"current_steps": 10, "total_steps": 198, "loss": 0.9642, "lr": 5e-06, "epoch": 0.15037593984962405, "percentage": 5.05, "elapsed_time": "0:09:45", "remaining_time": "3:03:29"}
2
- {"current_steps": 20, "total_steps": 198, "loss": 0.8383, "lr": 5e-06, "epoch": 0.3007518796992481, "percentage": 10.1, "elapsed_time": "0:19:26", "remaining_time": "2:53:04"}
3
- {"current_steps": 30, "total_steps": 198, "loss": 0.7809, "lr": 5e-06, "epoch": 0.45112781954887216, "percentage": 15.15, "elapsed_time": "0:29:07", "remaining_time": "2:43:04"}
4
- {"current_steps": 40, "total_steps": 198, "loss": 0.7593, "lr": 5e-06, "epoch": 0.6015037593984962, "percentage": 20.2, "elapsed_time": "0:38:47", "remaining_time": "2:33:12"}
5
- {"current_steps": 50, "total_steps": 198, "loss": 0.7443, "lr": 5e-06, "epoch": 0.7518796992481203, "percentage": 25.25, "elapsed_time": "0:48:28", "remaining_time": "2:23:27"}
6
- {"current_steps": 60, "total_steps": 198, "loss": 0.7378, "lr": 5e-06, "epoch": 0.9022556390977443, "percentage": 30.3, "elapsed_time": "0:58:07", "remaining_time": "2:13:40"}
7
- {"current_steps": 66, "total_steps": 198, "eval_loss": 0.7359598278999329, "epoch": 0.9924812030075187, "percentage": 33.33, "elapsed_time": "1:05:33", "remaining_time": "2:11:06"}
 
1
+ {"current_steps": 10, "total_steps": 198, "loss": 0.9599, "lr": 5e-06, "epoch": 0.15037593984962405, "percentage": 5.05, "elapsed_time": "0:09:47", "remaining_time": "3:04:06"}
2
+ {"current_steps": 20, "total_steps": 198, "loss": 0.8336, "lr": 5e-06, "epoch": 0.3007518796992481, "percentage": 10.1, "elapsed_time": "0:19:30", "remaining_time": "2:53:35"}
3
+ {"current_steps": 30, "total_steps": 198, "loss": 0.7791, "lr": 5e-06, "epoch": 0.45112781954887216, "percentage": 15.15, "elapsed_time": "0:29:11", "remaining_time": "2:43:31"}
4
+ {"current_steps": 40, "total_steps": 198, "loss": 0.7583, "lr": 5e-06, "epoch": 0.6015037593984962, "percentage": 20.2, "elapsed_time": "0:38:55", "remaining_time": "2:33:43"}
5
+ {"current_steps": 50, "total_steps": 198, "loss": 0.7441, "lr": 5e-06, "epoch": 0.7518796992481203, "percentage": 25.25, "elapsed_time": "0:48:38", "remaining_time": "2:23:59"}
6
+ {"current_steps": 60, "total_steps": 198, "loss": 0.7377, "lr": 5e-06, "epoch": 0.9022556390977443, "percentage": 30.3, "elapsed_time": "0:58:20", "remaining_time": "2:14:11"}
7
+ {"current_steps": 66, "total_steps": 198, "eval_loss": 0.7360510230064392, "epoch": 0.9924812030075187, "percentage": 33.33, "elapsed_time": "1:05:49", "remaining_time": "2:11:39"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f60adb5d8befb8e301d1a05d2c1d333b489d4ea3733f8e4d3a836a8c9150190b
3
  size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7ec61435194d0e92739704c0ff2008815a4e6fd89fa99d6c7cf5561bb44d58
3
  size 7160