Training in progress, step 200

axolotl_config.yaml

@@ -1,5 +1,5 @@
 base_model: unsloth/SmolLM-360M
-batch_size: 32
+batch_size: 92
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -17,23 +17,23 @@ 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
 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
+output_dir: /root/.sn56/axolotl/tmp/SmolLM-360M
 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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc7459b8070f26a9a864b85343d1738e3d2dcd6020a04f5fb8b9aca1951ffd2
+oid sha256:6ca635966f2128b90695cdcf1b450ff9388c9812f95f690192973e5b7eefd3c9
 size 723674912

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1d092fd3f29167bdacdba8b2489c3b0abb5e1e28bd152259e356428fc4a59e
+oid sha256:3156bde561d7a483929e0f1d8c097a973dfeb26f4690b823508131f70e6df615
 size 6840