Update README.md
8ed931a
verified
-
last-checkpoint
Training in progress, step 600, checkpoint
-
safety-checkpoint-120
Best model at step 120 with eval_loss=0.7461 | WandB Run: https://wandb.ai/tuandung/Qwen2.5-Coder-1.5B-Instruct-LoRA-Training/runs/k00n15pk
-
safety-checkpoint-180
Best model at step 180 with eval_loss=0.6672 | WandB Run: https://wandb.ai/tuandung/Qwen2.5-Coder-1.5B-Instruct-LoRA-Training/runs/k00n15pk
-
safety-checkpoint-240
Best model at step 240 with eval_loss=0.5921 | WandB Run: https://wandb.ai/tuandung/Qwen2.5-Coder-1.5B-Instruct-LoRA-Training/runs/k00n15pk
-
safety-checkpoint-300
Training in progress, step 300
-
safety-checkpoint-360
Training in progress, step 360
-
safety-checkpoint-420
Training in progress, step 420
-
safety-checkpoint-480
Training in progress, step 480
-
safety-checkpoint-540
Training in progress, step 540
-
safety-checkpoint-60
Best model at step 60 with eval_loss=1.1265 | WandB Run: https://wandb.ai/tuandung/Qwen2.5-Coder-1.5B-Instruct-LoRA-Training/runs/k00n15pk
-
safety-checkpoint-600
Training in progress, step 600
-
validation_metrics
Training in progress, step 600
-
1.57 kB
Best model at step 0 with eval_loss=1.5860
-
46.5 kB
Update README.md
-
877 Bytes
Best model at step 0 with eval_loss=1.5860
-
73.9 MB
Training in progress, step 600
-
632 Bytes
Best model at step 0 with eval_loss=1.5860
-
1.67 MB
Best model at step 0 with eval_loss=1.5860
-
613 Bytes
Best model at step 0 with eval_loss=1.5860
-
11.4 MB
Best model at step 0 with eval_loss=1.5860
-
7.54 kB
Best model at step 0 with eval_loss=1.5860
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState"
How to fix it?
5.56 kB
Best model at step 0 with eval_loss=1.6147 | WandB Run: https://wandb.ai/tuandung/Qwen2.5-Coder-1.5B-Instruct-LoRA-Training/runs/k00n15pk
-
2.78 MB
Best model at step 0 with eval_loss=1.5860
