Hugging Face's logo

mlfoundations-dev
/
stackoverflow_10000tasks_1p

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
7a2cd70
·
verified ·
1 Parent(s): 2586286

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 sha256:5e94c21066b90650f6aa2fd0ab847d7a4725d52131cdfe873408156e068e7aab
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe578fc498ab1479a12bfa06c1e3330b63a2b7e3740e705549096d9f270ff713
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:c4fff64ef0d55d27f810fb04a3402f3d248944e711b1dac20a2ac3968c9355c5
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c31779e14fbaf60191f3bea3d66eeaf7738f32a866f729e4ecf127530cc87b
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:a0134ad651afa18a047fcaa75d893026e6d2e8fad4c141621e8b0688ef211b47
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbae3ad23625a94fc39d9bed5c798b28e11811b70293ed5bf683cb7c6586dcc
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d8233262063dd1ecad28435f01eb6c1152aeda36fe0e8c1842c693175894ab1
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f1091181b4fcb5a368ad2d48df8b3152280d008c92376b25ed44982c50851f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 105, "loss": 0.8834, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:10:50", "remaining_time": "0:46:05"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8528, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:12", "remaining_time": "0:40:30"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8279964327812195, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:15", "remaining_time": "0:38:31"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 105, "loss": 0.8834, "lr": 5e-06, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:10:50", "remaining_time": "0:46:05"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 0.8528, "lr": 5e-06, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "0:16:12", "remaining_time": "0:40:30"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 0.8279964327812195, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:15", "remaining_time": "0:38:31"}
5
+ {"current_steps": 40, "total_steps": 105, "loss": 0.8161, "lr": 5e-06, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "0:23:06", "remaining_time": "0:37:32"}
6
+ {"current_steps": 50, "total_steps": 105, "loss": 0.7784, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:28:26", "remaining_time": "0:31:16"}
7
+ {"current_steps": 60, "total_steps": 105, "loss": 0.7735, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:47", "remaining_time": "0:25:20"}
8
+ {"current_steps": 70, "total_steps": 105, "loss": 0.7691, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:08", "remaining_time": "0:19:34"}
9
+ {"current_steps": 70, "total_steps": 105, "eval_loss": 0.7998312711715698, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:32", "remaining_time": "0:19:46"}