Hugging Face's logo

mlfoundations-dev
/
stackoverflow_10000tasks_0p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
1a35d15
·
verified ·
1 Parent(s): 5ec8171

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24530fdb96562e1dd7c5102b571fd6291fb4c48771b54fbb6ee5d08e50c641eb
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce935054f372f1f7bd5ef5e6a3f084a7697ef2cb17e9b2786ee822c334489582
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:903bacbf25b6349612ec3ae55bf474a61426f35bee1a3ed307b6d136c2d1048b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:308c5ed5222b748b113d7972cfc79b5de024c3ecb78528840bd8392bde2949a7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f7180603e0f147fb42c31ef3a72e8b97c72300874ce4e8bfc9f3a2eb81c3b8c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24edabba7dce90d6e3c47a2a8fc15d761021a2eb52714dbc3474805327c068eb
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:cdb7cb79add91f454aea95a5b962ae3883e9b6fdf52c50d91c66783c05d86dcc
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17d91f449ee1d40e68f27bb479b6a9b976227b1a8eeedd6b11d93f56b3f91e2
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.6327, "lr": 5e-06, "epoch": 0.6060606060606061, "percentage": 20.2, "elapsed_time": "0:10:45", "remaining_time": "0:42:30"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.5881, "lr": 5e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "0:16:06", "remaining_time": "0:37:03"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.5583714842796326, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:18:03", "remaining_time": "0:36:07"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.6327, "lr": 5e-06, "epoch": 0.6060606060606061, "percentage": 20.2, "elapsed_time": "0:10:45", "remaining_time": "0:42:30"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.5881, "lr": 5e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "0:16:06", "remaining_time": "0:37:03"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.5583714842796326, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:18:03", "remaining_time": "0:36:07"}
5
+ {"current_steps": 40, "total_steps": 99, "loss": 0.5367, "lr": 5e-06, "epoch": 1.2121212121212122, "percentage": 40.4, "elapsed_time": "0:22:57", "remaining_time": "0:33:52"}
6
+ {"current_steps": 50, "total_steps": 99, "loss": 0.5128, "lr": 5e-06, "epoch": 1.5151515151515151, "percentage": 50.51, "elapsed_time": "0:28:16", "remaining_time": "0:27:42"}
7
+ {"current_steps": 60, "total_steps": 99, "loss": 0.4975, "lr": 5e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "0:33:34", "remaining_time": "0:21:49"}
8
+ {"current_steps": 66, "total_steps": 99, "eval_loss": 0.5151528120040894, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:37:07", "remaining_time": "0:18:33"}