Training in progress, step 100

axolotl_config.yaml

@@ -1,5 +1,5 @@
 base_model: facebook/opt-125m
-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
@@ -33,8 +33,8 @@ output_dir: /root/.sn56/axolotl/tmp/opt-125m
 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: GPT2TokenizerFast
 torch_dtype: bf16

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03438d87162fa3ae59956221d36f82a9321e50965d77bf13e46151829d5f6e80
+oid sha256:a6afd96f0a4efb226214a2f98fc2930b95faa7d2409bdbba1791318c01e36cad
 size 250490408

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701b8fdcf7ee9a32ee2820bf97b3ab785ffbf4aa2b41bcd64bfa018085f95834
+oid sha256:91e32bef4fa18f7434f34b3ab9a59a991d12d4e7c7fd850b74f33c05529273df
 size 6840