Training in progress, step 20

axolotl_config.yaml

@@ -1,5 +1,5 @@
 base_model: EleutherAI/pythia-160m
-batch_size: 32
+batch_size: 120
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -13,29 +13,35 @@ datasets:
     no_input_format: '{instruction}'
     system_format: '{system}'
     system_prompt: ''
+device_map: auto
+eval_sample_packing: false
 eval_steps: 20
 flash_attention: true
-gpu_memory_limit: 80GiB
+gradient_checkpointing: true
 group_by_length: true
 hub_model_id: SystemAdmin123/pythia-160m
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 2500
-micro_batch_size: 2
+max_steps: 10000
+micro_batch_size: 30
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
-output_dir: /root/.sn56/axolotl/outputs/pythia-160m
+output_dir: /root/.sn56/axolotl/tmp/pythia-160m
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
-save_steps: 40
+sample_packing: true
+save_steps: 20
 save_total_limit: 1
 sequence_len: 2048
 special_tokens:
   pad_token: <|endoftext|>
 tokenizer_type: GPTNeoXTokenizerFast
+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:f371b30bd02968723f473636f0a6fddaff98d7a5e4b3c9920b77b1ab432fdc21
+oid sha256:650e16f158fb094c89487e9d941f2e4920b88f8a613605d49400644f0803fd3d
 size 324583112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be66df826678fce466503b7939e4e5def82ad515802f7829759857649b46c13
-size 6712
+oid sha256:6814dea57c4e9c5e3cc740573e43698239e823a9436395fe2f363fffc34e7212
+size 6840