Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_25000tasks__75p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
EtashGuha commited on
Commit
6d43893
·
verified ·
1 Parent(s): 4b36e25

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:156eb2176dcf532fbdc4f81cd65f831b4dcdc97835588bf54c9b735a62fd0889
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1bc2f79d416a35719072403a34d075dc7177fa9459d52a711d2d63381be0f4
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:c401f835460372392623b697e67fe84ae590119b242d5c534b9c9c4f6d49ccf0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d370e067c4b5c9733214bd28d9697bb4f3d791a20ca83b6537c9034338a42e0c
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:a80c16979fc9a05acce439f393ce6f1451cb1d4d63ad1b6f686e7df283028011
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f37a38841a6eb480f6b6f36b0cd1d1ffe008b5e85881387e32cd5f4ba2b39c
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:a2200f3e12a6e9f22b53ed84309b3e4ddee67692dc6db7e9dc16958ac8c41105
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f731bfeade5823d14773035c24f6cc6a5fc1653164d953d8ae1d4a469720011
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 102, "loss": 0.8309, "lr": 5e-06, "epoch": 0.5797101449275363, "percentage": 19.61, "elapsed_time": "0:52:31", "remaining_time": "3:35:21"}
3
  {"current_steps": 30, "total_steps": 102, "loss": 0.7986, "lr": 5e-06, "epoch": 0.8695652173913043, "percentage": 29.41, "elapsed_time": "1:18:33", "remaining_time": "3:08:32"}
4
  {"current_steps": 34, "total_steps": 102, "eval_loss": 0.7891173958778381, "epoch": 0.9855072463768116, "percentage": 33.33, "elapsed_time": "1:32:17", "remaining_time": "3:04:35"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 102, "loss": 0.8309, "lr": 5e-06, "epoch": 0.5797101449275363, "percentage": 19.61, "elapsed_time": "0:52:31", "remaining_time": "3:35:21"}
3
  {"current_steps": 30, "total_steps": 102, "loss": 0.7986, "lr": 5e-06, "epoch": 0.8695652173913043, "percentage": 29.41, "elapsed_time": "1:18:33", "remaining_time": "3:08:32"}
4
  {"current_steps": 34, "total_steps": 102, "eval_loss": 0.7891173958778381, "epoch": 0.9855072463768116, "percentage": 33.33, "elapsed_time": "1:32:17", "remaining_time": "3:04:35"}
5
+ {"current_steps": 40, "total_steps": 102, "loss": 0.7623, "lr": 5e-06, "epoch": 1.1594202898550725, "percentage": 39.22, "elapsed_time": "1:47:58", "remaining_time": "2:47:21"}
6
+ {"current_steps": 50, "total_steps": 102, "loss": 0.7293, "lr": 5e-06, "epoch": 1.4492753623188406, "percentage": 49.02, "elapsed_time": "2:13:54", "remaining_time": "2:19:15"}
7
+ {"current_steps": 60, "total_steps": 102, "loss": 0.7198, "lr": 5e-06, "epoch": 1.7391304347826086, "percentage": 58.82, "elapsed_time": "2:39:49", "remaining_time": "1:51:52"}
8
+ {"current_steps": 69, "total_steps": 102, "eval_loss": 0.7413280606269836, "epoch": 2.0, "percentage": 67.65, "elapsed_time": "3:04:57", "remaining_time": "1:28:27"}
9
+ {"current_steps": 70, "total_steps": 102, "loss": 0.7071, "lr": 5e-06, "epoch": 2.028985507246377, "percentage": 68.63, "elapsed_time": "3:08:58", "remaining_time": "1:26:23"}