Hugging Face's logo

mlfoundations-dev
/
stackexchange_history

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
46ee762
·
verified ·
1 Parent(s): e5d4df6

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 sha256:065a6436614a1cea8ec01d9c55c6ffeee48cffc75a6c14e1efab90527f2cc04a
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63de67ba7dc2582bebdc7cca1ed888f9f744f4c7e15664632f4c3e1c905d5753
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f2a13258021040577694778dd41cebd015c4243e2752eb1c3e7858654b01c49
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972110bb6d47822580f74757a9b35de55d9aa86027b42902c617ac12597a66bd
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:955f232158359bbe34cd6bc7c7d4d2c304dadaf909d3b99ef8907c08872d0542
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813a3bc49130f1a36aeb4cfa7cc3b4164a1a16ed826ff89771ab72ade55c2556
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62f64002bb0e13f0e5a91cd59677f409557ce1650905be06374e6ad589017b13
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01396d589736f3b9ef928be14f59f41b3e3c1c9530e0833a0a192763978cbbb
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.2678, "lr": 5e-06, "epoch": 0.425531914893617, "percentage": 14.49, "elapsed_time": "0:05:28", "remaining_time": "0:32:15"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 1.1576, "lr": 5e-06, "epoch": 0.851063829787234, "percentage": 28.99, "elapsed_time": "0:10:48", "remaining_time": "0:26:27"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 1.126758337020874, "epoch": 0.9787234042553191, "percentage": 33.33, "elapsed_time": "0:12:56", "remaining_time": "0:25:52"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 69, "loss": 1.2678, "lr": 5e-06, "epoch": 0.425531914893617, "percentage": 14.49, "elapsed_time": "0:05:28", "remaining_time": "0:32:15"}
2
  {"current_steps": 20, "total_steps": 69, "loss": 1.1576, "lr": 5e-06, "epoch": 0.851063829787234, "percentage": 28.99, "elapsed_time": "0:10:48", "remaining_time": "0:26:27"}
3
  {"current_steps": 23, "total_steps": 69, "eval_loss": 1.126758337020874, "epoch": 0.9787234042553191, "percentage": 33.33, "elapsed_time": "0:12:56", "remaining_time": "0:25:52"}
4
+ {"current_steps": 30, "total_steps": 69, "loss": 1.159, "lr": 5e-06, "epoch": 1.2765957446808511, "percentage": 43.48, "elapsed_time": "0:17:39", "remaining_time": "0:22:56"}
5
+ {"current_steps": 40, "total_steps": 69, "loss": 1.0659, "lr": 5e-06, "epoch": 1.702127659574468, "percentage": 57.97, "elapsed_time": "0:22:59", "remaining_time": "0:16:40"}
6
+ {"current_steps": 47, "total_steps": 69, "eval_loss": 1.0796161890029907, "epoch": 2.0, "percentage": 68.12, "elapsed_time": "0:26:56", "remaining_time": "0:12:36"}