Training in progress, step 20

axolotl_config.yaml

@@ -15,7 +15,7 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 50
+eval_steps: 20
 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: 4
 model_type: AutoModelForCausalLM
 num_epochs: 100
@@ -33,11 +33,13 @@ output_dir: /root/.sn56/axolotl/tmp/Phi-3-mini-4k-instruct
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 50
-save_total_limit: 2
+save_steps: 20
+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-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b17fb7f911aac944c07f7d1e60d4aff773114a73adcd1c432996250386e07e
+oid sha256:6f3d812570002e67e4c524bc9167715869351666b679db2c2113d31ed4a9130f
 size 4972163696

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ffa09e7423c38be4314cbbc1311ec46c75e31ecc5a2d4f0df329edce91a7de
+oid sha256:71f5715344e5f551de03351627f6738c6b66ba1ac393a2f90e551e5e4e2de1cf
 size 2669366920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899fb22d8728c672dc9aaedc431359fdbdbfbd5b7a9873d1f61a5375b7b7faef
+oid sha256:b6fc8e85610e9c1d7355072f44fd8ceaef90645fb06533af173045356dc826ea
 size 7032