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-3.5-mini-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:a4830c7dfae77af1baf72bf90cd6854788975df823f1b1ec49037d3331f4b713
+oid sha256:450c9abcb2cd1e6e4af1e4a59c9778c0e70b3b369df43240c125a97e65d6cfee
 size 4972163696

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922d604842e24363921eaa52716294005a05f1ccdec8b6716513c45ad8592ea7
+oid sha256:2f959b5005cd08bf04586e9bad600aa7cc023cdd6f2dd81a4a7d263bfa2bfc38
 size 2669366920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4320434255846d7d3d8916bcc913b473a3b0890bc89a39d373bf3ce9e989285
+oid sha256:a90b92ab52eced9e524eb7132f1e76d851e587a77af62e153750168c8dcdf0cf
 size 7096