Training in progress, step 20

axolotl_config.yaml

@@ -15,7 +15,7 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 50
+eval_steps: 20
 flash_attention: true
 gradient_checkpointing: true
 group_by_length: true
@@ -24,7 +24,7 @@ hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 5000
+max_steps: 10000
 micro_batch_size: 5
 model_type: AutoModelForCausalLM
 num_epochs: 100
@@ -33,11 +33,13 @@ output_dir: /root/.sn56/axolotl/tmp/Qwen2.5-3B-Instruct
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 50
-save_total_limit: 2
+save_steps: 20
+save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: Qwen2TokenizerFast
 torch_dtype: bf16
+training_args_kwargs:
+  hub_private_repo: true
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fdf89f0fd7dd6fbe9eeacac4a67aa119b62a3a4e0bb2532c080fcaaa3927fa
+oid sha256:a9a1b5fe74d30a2b57275019644a375677da441d563a6cd3de6fb409ded03f62
 size 4956450288

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f17a270ec2582d3b80ca44646e38c1190ad03af747fc0196f9aa1f5b4ad2196
+oid sha256:77f31d93e3f4bb89019d604b40346ff6e1fc555bbf740c89dc528ba7e5a1fa13
 size 1214366696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a097d8f6050774249bd291d7596e77b256195d2e9dca6b13a05d78fe71f26a2
+oid sha256:a3f334277fb93a403ef7fd7cac6f2e3db7ca0d17bb46fbd3f915c745d20e4c8e
 size 9144