Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackoverflow_10000tasks__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
d7470cc
·
verified ·
1 Parent(s): d6042c5

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:cd807b4b06736578b313f9ece026e6bd2e805e06080d4c0a2e995237c294cf19
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6319734d8a9fb27446cd00f191802a86c72cc08ac47cddfbcdb73a9a1c394c24
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:789548a8b1cb8df86473eae3b222d532faac1b32eb42c9f31dcdcd8c025c98b0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d8b225557931078367a7e52be3a3db1b64fa81cb7df213587b1d0d55861716
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02e4c1cb450acd0786da0c757ac655b9358710212000b304be4585d7b0158b0f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347834ce6342da484af331a78aed33f56cb92027740e28b45c517597e9a3a228
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d42929eb830a6af20d3e82e587a646158db504c260290c57114c8feae4613bf
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892e85259c7209e8e2fb8a8d4d2fb7b6b78fac80a130f961d4010abd59bf528c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,9 +1,6 @@
1
- {"current_steps": 10, "total_steps": 102, "loss": 0.9197, "lr": 5e-06, "epoch": 0.29038112522686027, "percentage": 9.8, "elapsed_time": "0:26:09", "remaining_time": "4:00:39"}
2
- {"current_steps": 20, "total_steps": 102, "loss": 0.8131, "lr": 5e-06, "epoch": 0.5807622504537205, "percentage": 19.61, "elapsed_time": "0:52:07", "remaining_time": "3:33:41"}
3
- {"current_steps": 30, "total_steps": 102, "loss": 0.7844, "lr": 5e-06, "epoch": 0.8711433756805808, "percentage": 29.41, "elapsed_time": "1:18:04", "remaining_time": "3:07:23"}
4
- {"current_steps": 34, "total_steps": 102, "eval_loss": 0.7656542062759399, "epoch": 0.9872958257713249, "percentage": 33.33, "elapsed_time": "1:31:34", "remaining_time": "3:03:09"}
5
- {"current_steps": 40, "total_steps": 102, "loss": 0.7443, "lr": 5e-06, "epoch": 1.161524500907441, "percentage": 39.22, "elapsed_time": "1:47:26", "remaining_time": "2:46:31"}
6
- {"current_steps": 50, "total_steps": 102, "loss": 0.7169, "lr": 5e-06, "epoch": 1.4519056261343013, "percentage": 49.02, "elapsed_time": "2:13:24", "remaining_time": "2:18:44"}
7
- {"current_steps": 60, "total_steps": 102, "loss": 0.7088, "lr": 5e-06, "epoch": 1.7422867513611615, "percentage": 58.82, "elapsed_time": "2:39:23", "remaining_time": "1:51:34"}
8
- {"current_steps": 68, "total_steps": 102, "eval_loss": 0.7332684993743896, "epoch": 1.9745916515426498, "percentage": 66.67, "elapsed_time": "3:04:19", "remaining_time": "1:32:09"}
9
- {"current_steps": 70, "total_steps": 102, "loss": 0.6932, "lr": 5e-06, "epoch": 2.0326678765880217, "percentage": 68.63, "elapsed_time": "3:08:50", "remaining_time": "1:26:19"}
 
1
+ {"current_steps": 70, "total_steps": 102, "loss": 0.6585, "lr": 5e-06, "epoch": 2.058076225045372, "percentage": 68.63, "elapsed_time": "0:05:19", "remaining_time": "0:02:25"}
2
+ {"current_steps": 80, "total_steps": 102, "loss": 0.648, "lr": 5e-06, "epoch": 2.3484573502722323, "percentage": 78.43, "elapsed_time": "0:31:27", "remaining_time": "0:08:39"}
3
+ {"current_steps": 90, "total_steps": 102, "loss": 0.6451, "lr": 5e-06, "epoch": 2.6388384754990923, "percentage": 88.24, "elapsed_time": "0:57:44", "remaining_time": "0:07:41"}
4
+ {"current_steps": 100, "total_steps": 102, "loss": 0.638, "lr": 5e-06, "epoch": 2.9292196007259528, "percentage": 98.04, "elapsed_time": "1:24:06", "remaining_time": "0:01:40"}
5
+ {"current_steps": 102, "total_steps": 102, "eval_loss": 0.730301558971405, "epoch": 2.9872958257713247, "percentage": 100.0, "elapsed_time": "1:32:37", "remaining_time": "0:00:00"}
6
+ {"current_steps": 102, "total_steps": 102, "epoch": 2.9872958257713247, "percentage": 100.0, "elapsed_time": "1:33:32", "remaining_time": "0:00:00"}
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005e7b1939cb0890f52e6a613ab6c94df243e649d5ba7905ecef36bb986ab471
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30622b799f5303d5c401c4f163bc94ea4484984f4fc29ad16970e2617971e5e
3
+ size 7416