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
60c4ec5
·
verified ·
1 Parent(s): 6d43893

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 +6 -9
  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 sha256:5c1bc2f79d416a35719072403a34d075dc7177fa9459d52a711d2d63381be0f4
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd67dad4f4e8f2eaddba37b06297b8bc7599cf5e484b1d16753af5e93ac27ba6
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:d370e067c4b5c9733214bd28d9697bb4f3d791a20ca83b6537c9034338a42e0c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62900c4a92f4f399bf6b7f8a3741b83bfbbab0d026e99fa3e41dd59ad5f40832
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17f37a38841a6eb480f6b6f36b0cd1d1ffe008b5e85881387e32cd5f4ba2b39c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2f999cce3b49ac82d8fc555d16eba798bafc5142073197bfee4ed9b3c11252
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f731bfeade5823d14773035c24f6cc6a5fc1653164d953d8ae1d4a469720011
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76a3f0a12d17c3ecee57746c7ec12af2a46f9a43d5ccac09aded9a6594f116f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,9 +1,6 @@
1
- {"current_steps": 10, "total_steps": 102, "loss": 0.927, "lr": 5e-06, "epoch": 0.2898550724637681, "percentage": 9.8, "elapsed_time": "0:26:13", "remaining_time": "4:01:15"}
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"}
 
1
+ {"current_steps": 70, "total_steps": 102, "loss": 0.6561, "lr": 5e-06, "epoch": 2.0579710144927534, "percentage": 68.63, "elapsed_time": "0:02:46", "remaining_time": "0:01:16"}
2
+ {"current_steps": 80, "total_steps": 102, "loss": 0.6471, "lr": 5e-06, "epoch": 2.3478260869565215, "percentage": 78.43, "elapsed_time": "0:28:58", "remaining_time": "0:07:58"}
3
+ {"current_steps": 90, "total_steps": 102, "loss": 0.6426, "lr": 5e-06, "epoch": 2.63768115942029, "percentage": 88.24, "elapsed_time": "0:55:09", "remaining_time": "0:07:21"}
4
+ {"current_steps": 100, "total_steps": 102, "loss": 0.64, "lr": 5e-06, "epoch": 2.927536231884058, "percentage": 98.04, "elapsed_time": "1:21:22", "remaining_time": "0:01:37"}
5
+ {"current_steps": 102, "total_steps": 102, "eval_loss": 0.7359980344772339, "epoch": 2.9855072463768115, "percentage": 100.0, "elapsed_time": "1:29:57", "remaining_time": "0:00:00"}
6
+ {"current_steps": 102, "total_steps": 102, "epoch": 2.9855072463768115, "percentage": 100.0, "elapsed_time": "1:30:53", "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:eb87e1a4760856ca7e0c5ea63939563d422443250aa92947feb14625a480ae9e
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c005c415fb8b756e1b18d24704f4e25cb6c825b6b475f50421a06f2f3bf4736
3
+ size 7480