Hugging Face's logo

mlfoundations-dev
/
llama3_mammoth_dcft_ablation_original_50k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
reinhardh commited on
Commit
0ae05bf
·
verified ·
1 Parent(s): 41622b7

Training in progress, epoch 2

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa27ef93a848f32c0bc465e902b756ddd0226dd49cebb62db19a29a5a9ce0343
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f4ca66c3619526350a09c2e2f705d63f781f32f796e814b99fb3ca18fa1f1f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef87f92b3b08bed8c4c1a78ed691ace9129e93da929c99872e22079f0de908e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95dfd3230ef89e26530fdfa17869101552a187eae89bfe192a7ded5255381f6
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66abc056386b3f525c84e9996abc7ed72dc5ec9fdcb4de160955a79e51e6cc85
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52fba143104a9710572b04a4b30219e70cdd3fc8ebc44cc3ff127582124fa87
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:e27332422b1ec96a60f478288f341817d0bca19a6d9ada80292ea9d82bbd21ad
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e758a8ecbd9c679a247aae1b1af20f0e28742bf74b82a527f49919d77ae0152
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 7, "total_steps": 21, "eval_loss": 0.06519919633865356, "epoch": 0.896, "percentage": 33.33, "elapsed_time": "0:07:39", "remaining_time": "0:15:18"}
2
  {"current_steps": 10, "total_steps": 21, "loss": 1.0796, "lr": 5e-06, "epoch": 1.32, "percentage": 47.62, "elapsed_time": "0:12:10", "remaining_time": "0:13:23"}
3
  {"current_steps": 15, "total_steps": 21, "eval_loss": 0.06100919470191002, "epoch": 1.96, "percentage": 71.43, "elapsed_time": "0:16:59", "remaining_time": "0:06:47"}
 
 
 
 
1
  {"current_steps": 7, "total_steps": 21, "eval_loss": 0.06519919633865356, "epoch": 0.896, "percentage": 33.33, "elapsed_time": "0:07:39", "remaining_time": "0:15:18"}
2
  {"current_steps": 10, "total_steps": 21, "loss": 1.0796, "lr": 5e-06, "epoch": 1.32, "percentage": 47.62, "elapsed_time": "0:12:10", "remaining_time": "0:13:23"}
3
  {"current_steps": 15, "total_steps": 21, "eval_loss": 0.06100919470191002, "epoch": 1.96, "percentage": 71.43, "elapsed_time": "0:16:59", "remaining_time": "0:06:47"}
4
+ {"current_steps": 20, "total_steps": 21, "loss": 0.9233, "lr": 5e-06, "epoch": 2.64, "percentage": 95.24, "elapsed_time": "0:23:58", "remaining_time": "0:01:11"}
5
+ {"current_steps": 21, "total_steps": 21, "eval_loss": 0.059362392872571945, "epoch": 2.768, "percentage": 100.0, "elapsed_time": "0:27:28", "remaining_time": "0:00:00"}
6
+ {"current_steps": 21, "total_steps": 21, "epoch": 2.768, "percentage": 100.0, "elapsed_time": "0:29:48", "remaining_time": "0:00:00"}