Training in progress, step 200

axolotl_config.yaml

@@ -1,5 +1,5 @@
 base_model: unsloth/SmolLM-360M-Instruct
-batch_size: 32
+batch_size: 92
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -17,27 +17,29 @@ device_map: auto
 eval_sample_packing: false
 eval_steps: 200
 flash_attention: true
-gpu_memory_limit: 80GiB
+gradient_checkpointing: true
 group_by_length: true
 hub_model_id: SystemAdmin123/SmolLM-360M-Instruct
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 2500
-micro_batch_size: 4
+max_steps: 10000
+micro_batch_size: 23
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
-output_dir: /root/.sn56/axolotl/outputs/SmolLM-360M-Instruct
+output_dir: /root/.sn56/axolotl/tmp/SmolLM-360M-Instruct
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
-sample_packing: false
-save_steps: 400
+sample_packing: true
+save_steps: 200
 save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: GPT2TokenizerFast
 torch_dtype: bf16
+training_args_kwargs:
+  hub_private_repo: true
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4dc1cc1cc9b54bfe6d9ce46c6c48d5e71549cfb18e37c573da51b96a6b7c6fc
+oid sha256:089ab77c575af96a66c3eebde29eb20b4802b1ca35d7fcd6a82088b5dfc73176
 size 723674912

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c005ee5b7b542fe5c31ab145aa5cb83513af587ae4027e5fb31ac777061c2a2
+oid sha256:3dcec2cd7965a72fb6ad084d768d0c5ed5e5db711cd1f0987f9e8de610b55004
 size 6840