Hugging Face's logo

mlfoundations-dev
/
stackoverflow_25000tasks_.75p

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
b8f6ffe
•
1 Parent(s): 6e58fa2

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:d374da90f5f5c7b1e43f43c683189d9124ec76327e57e5e4f452b6e0061e3174
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c93e53c1dcea87dce60dea6ec345ac314be8b4bff95eb8811f67aaf6684af21
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:521389a4473e6d64db79bd5dda4fed1f64111b27494152c93230c709b6683f20
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cca819b6e809735c77f7da27b441516eac61471327c87a686597efde4813906
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a64f5e30e7bc068bc4ed8f7092bebba19785515e5f0b95c4309ed4fe02e6ae3
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc5bbee276072cc9701098e6a07fc57b7bff3e0ac18d1f3fd8e3a668498ff57
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:f4aff4e6396a298ae77a937be5519ebeb08d0fe57aec62461e4a467212246d75
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a515812d6e9e71850f0fca2aee8bfb694f922a3701d13e8c742efd94cea2687a
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,8 @@
7
  {"current_steps": 60, "total_steps": 102, "loss": 0.7137, "lr": 5e-06, "epoch": 1.7463768115942029, "percentage": 58.82, "elapsed_time": "0:33:36", "remaining_time": "0:23:31"}
8
  {"current_steps": 68, "total_steps": 102, "eval_loss": 0.7427083253860474, "epoch": 1.9782608695652173, "percentage": 66.67, "elapsed_time": "0:38:30", "remaining_time": "0:19:15"}
9
  {"current_steps": 70, "total_steps": 102, "loss": 0.751, "lr": 5e-06, "epoch": 2.0434782608695654, "percentage": 68.63, "elapsed_time": "0:40:37", "remaining_time": "0:18:34"}
 
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 102, "loss": 0.7137, "lr": 5e-06, "epoch": 1.7463768115942029, "percentage": 58.82, "elapsed_time": "0:33:36", "remaining_time": "0:23:31"}
8
  {"current_steps": 68, "total_steps": 102, "eval_loss": 0.7427083253860474, "epoch": 1.9782608695652173, "percentage": 66.67, "elapsed_time": "0:38:30", "remaining_time": "0:19:15"}
9
  {"current_steps": 70, "total_steps": 102, "loss": 0.751, "lr": 5e-06, "epoch": 2.0434782608695654, "percentage": 68.63, "elapsed_time": "0:40:37", "remaining_time": "0:18:34"}
10
+ {"current_steps": 80, "total_steps": 102, "loss": 0.6497, "lr": 5e-06, "epoch": 2.3333333333333335, "percentage": 78.43, "elapsed_time": "0:45:56", "remaining_time": "0:12:37"}
11
+ {"current_steps": 90, "total_steps": 102, "loss": 0.6473, "lr": 5e-06, "epoch": 2.6231884057971016, "percentage": 88.24, "elapsed_time": "0:51:14", "remaining_time": "0:06:49"}
12
+ {"current_steps": 100, "total_steps": 102, "loss": 0.6436, "lr": 5e-06, "epoch": 2.9130434782608696, "percentage": 98.04, "elapsed_time": "0:56:32", "remaining_time": "0:01:07"}
13
+ {"current_steps": 102, "total_steps": 102, "eval_loss": 0.7359128594398499, "epoch": 2.971014492753623, "percentage": 100.0, "elapsed_time": "0:59:17", "remaining_time": "0:00:00"}
14
+ {"current_steps": 102, "total_steps": 102, "epoch": 2.971014492753623, "percentage": 100.0, "elapsed_time": "1:00:32", "remaining_time": "0:00:00"}