Training in progress, step 200

axolotl_config.yaml

@@ -17,23 +17,23 @@ device_map: auto
 eval_sample_packing: false
 eval_steps: 200
 flash_attention: true
-gpu_memory_limit: 80GiB
+gradient_checkpointing: true
 group_by_length: true
 hub_model_id: SystemAdmin123/mistral-7b-instruct-v0.2
 hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 2500
+max_steps: 10000
 micro_batch_size: 2
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
-output_dir: /root/.sn56/axolotl/outputs/mistral-7b-instruct-v0.2
+output_dir: /root/.sn56/axolotl/tmp/mistral-7b-instruct-v0.2
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
-sample_packing: false
-save_steps: 400
+sample_packing: true
+save_steps: 200
 save_total_limit: 1
 sequence_len: 2048
 tokenizer_type: LlamaTokenizerFast

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a53927ae2256cbe56c90bac7da700e354fc7f21de628d3eed0a7b4b2e27915c
+oid sha256:bcd5b3fe28539d7c27e9c1c72289ef993f1955987b0acb6a12cc40eca8ba1e3a
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016c04f40d99fc3227fb09a2989f83c2c0b7ca6c9ae1852b219eaec29324b1a7
+oid sha256:406d436e48e98f1c89ab6ba1e12b026d54e9080c4538d743c32e9130af202cda
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a0242b504cd39971acad38f3f79f3699759d99b6e4c43785f15cf3e56cd666
+oid sha256:22b75146ff6313b5530681487be10972d2689efa7f86e01835f0e8e234259e58
 size 4540516344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0166b1a0dbc748fd83bbe842fbeb36ef63c27fa9749423e46ed3ac591ce2951e
-size 7672
+oid sha256:adab2cd4b892729a3f8cb9343d382b49be7d93397bee49b30af6cf5be7d19904
+size 7736