Training in progress, step 100

axolotl_config.yaml

@@ -1,5 +1,5 @@
 base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
-batch_size: 64
+batch_size: 128
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -15,7 +15,7 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 50
+eval_steps: 200
 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: 32
 model_type: AutoModelForCausalLM
 num_epochs: 100
@@ -33,11 +33,13 @@ output_dir: /root/.sn56/axolotl/tmp/tiny-random-LlamaForCausalLM
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 50
-save_total_limit: 2
+save_steps: 200
+save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: LlamaTokenizerFast
 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:da6a17dd4ebabed24d872d4606102003c0e657825096a008c1ebd2fc857ec3e7
+oid sha256:25a257c5b2e34eda80e3d84f1a8cc4247ba163d63b057609915a20d5c03487fe
 size 2066752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120614a5953861571b441322c20a1add8c543820ada9a66731f41e9cf2b7b9de
+oid sha256:3cfc960a203b27f090e467325bfefda4ba62fdf00b36c1ffe04aa88d3518354f
 size 6904