Training in progress, step 20

axolotl_config.yaml

@@ -1,5 +1,5 @@
 base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
-batch_size: 32
+batch_size: 64
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -15,26 +15,26 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 200
+eval_steps: 40
 flash_attention: true
-gpu_memory_limit: 80GiB
+gradient_checkpointing: true
 group_by_length: true
 hub_model_id: SystemAdmin123/tiny-random-LlamaForCausalLM
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 2500
-micro_batch_size: 4
+max_steps: 5000
+micro_batch_size: 32
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
-output_dir: /root/.sn56/axolotl/outputs/tiny-random-LlamaForCausalLM
+output_dir: /root/.sn56/axolotl/tmp/tiny-random-LlamaForCausalLM
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
-sample_packing: false
-save_steps: 400
-save_total_limit: 1
+sample_packing: true
+save_steps: 20
+save_total_limit: 2
 sequence_len: 2048
 tokenizer_type: LlamaTokenizerFast
 torch_dtype: bf16

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4156994b0d2538aa2d37af1880314c638cc4d24a008e661dbcf7a289e3478dca
+oid sha256:c9b841b09c9dd8f6d4d92bae6a6575aadd48707d9b68b71831107d9f2bc76adb
 size 2066752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ab57c26802475df8b559ffa07b1995cecba20856adfc383ddb4700563cc1b9
+oid sha256:786399a4c033c92470f06cc2d0496bbd0810a0dfdf57aa0b5e9a8edf096bb52a
 size 6904