Training in progress, step 40

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "JackFram/llama-68m",
+  "base_model_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "down_proj",
-    "o_proj",
-    "up_proj",
     "k_proj",
-    "v_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65441d6870d9a0279debad33f958407443b27e597864c7d0e071f8707f2cd6c
-size 18091656
+oid sha256:159277feec320a7592284f9e3696651e378c75cb98a9616d5fc9a41efc0eec40
+size 183784

added_tokens.json

@@ -1,4 +1,5 @@
 {
-  "<|im_end|>": 32000,
-  "<|im_start|>": 32001
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
 }

axolotl_config.yaml

@@ -1,5 +1,6 @@
-base_model: unsloth/OpenHermes-2.5-Mistral-7B
-batch_size: 32
+adapter: lora
+base_model: peft-internal-testing/tiny-dummy-qwen2
+batch_size: 64
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -15,36 +16,42 @@ datasets:
     system_prompt: ''
 device_map: auto
 eval_sample_packing: false
-eval_steps: 200
+eval_steps: 0.1
 flash_attention: true
 gradient_checkpointing: true
 group_by_length: true
 hub_model_id: SystemAdmin123/test-repo
 hub_strategy: checkpoint
-learning_rate: 0.0002
+learning_rate: 0.0001
 logging_steps: 10
+lora_alpha: 256
+lora_dropout: 0.1
+lora_r: 128
+lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 10000
-micro_batch_size: 2
+max_steps: 160.0
+micro_batch_size: 7
 model_type: AutoModelForCausalLM
-num_epochs: 100
+num_epochs: 10000
 optimizer: adamw_bnb_8bit
 output_dir: /root/.sn56/axolotl/tmp/test-repo
 pad_to_sequence_len: true
 resize_token_embeddings_to_32x: false
 sample_packing: true
-save_steps: 200
+save_steps: 40
 save_total_limit: 1
 sequence_len: 2048
-tokenizer_type: LlamaTokenizerFast
+tokenizer_type: Qwen2TokenizerFast
 torch_dtype: bf16
 training_args_kwargs:
+  disable_tqdm: true
   hub_private_repo: true
+  save_only_model: true
 trust_remote_code: true
-val_set_size: 0.1
+val_set_size: 0.01
 wandb_entity: ''
 wandb_mode: online
-wandb_name: unsloth/OpenHermes-2.5-Mistral-7B-argilla/databricks-dolly-15k-curated-en
+wandb_name: peft-internal-testing/tiny-dummy-qwen2-argilla/databricks-dolly-15k-curated-en
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: default

config.json

@@ -1,28 +1,29 @@
 {
-  "_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B",
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "architectures": [
-    "MistralForCausalLM"
+    "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "head_dim": 128,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 8,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
+  "intermediate_size": 32,
   "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.1",
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
   "use_cache": false,
-  "vocab_size": 32002
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

special_tokens_map.json

@@ -1,27 +1,17 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04222cd76979c181cd3f72c3bf6982fe2a09d9f4b8f23d82902efde18f1d0668
-size 3506125
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -1,64 +1,45 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
+    "151645": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "legacy": true,
   "model_max_length": 32768,
-  "pad_token": "<unk>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
   "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3eb8b3b2a8acd873a0906e2cee7771ee216bb2230a5edc2d984d58604ec971
-size 6776
+oid sha256:37476a182ec272b4a6a6254cda6d0ce55ff7d3844823bf9121f7eccf202f4723
+size 6648