Training in progress, step 40

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

axolotl_config.yaml

@@ -0,0 +1,45 @@
+base_model: peft-internal-testing/tiny-dummy-qwen2
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- format: custom
+  path: argilla/databricks-dolly-15k-curated-en
+  type:
+    field_input: original-instruction
+    field_instruction: original-instruction
+    field_output: original-response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+group_by_length: true
+hub_model_id: SystemAdmin123/test-repo
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 2
+model_type: AutoModelForCausalLM
+num_epochs: 100
+optimizer: adamw_bnb_8bit
+output_dir: /root/.sn56/axolotl/outputs/test-repo
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: Qwen2TokenizerFast
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+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
+warmup_ratio: 0.05

config.json

@@ -1,31 +1,28 @@
 {
-  "_name_or_path": "fxmarty/small-llama-testing",
+  "_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "architectures": [
-    "LlamaForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "head_dim": 64,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 256,
+  "hidden_size": 8,
   "initializer_range": 0.02,
-  "intermediate_size": 128,
-  "max_position_embeddings": 2048,
-  "mlp_bias": false,
-  "model_type": "llama",
+  "intermediate_size": 32,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 4,
-  "pad_token_id": -1,
-  "pretraining_tp": 1,
+  "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.48.1",
   "use_cache": false,
-  "vocab_size": 32000
+  "use_sliding_window": false,
+  "vocab_size": 151646
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3981e030b93d87183bf27dee61297bc699920b1d1063e2a14a6d844ffe232f8b
-size 34214640
+oid sha256:fe161f5ecbc782395222bf2f386584a1d7eea980d6f5af667b405b40dc54ba49
+size 2433024

special_tokens_map.json

@@ -1,30 +1,20 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "eos_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
   }
 }

tokenizer_config.json

@@ -1,26 +1,24 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "151645": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,16 +26,20 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
+  "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": "</s>",
-  "legacy": true,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "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 sha256:88983683f78772e6fd62c9a97937ef6f408b0ee554cb1a96936c237405b3f78a
-size 6520
+oid sha256:d4ab1aa49f52e7f57216c42b69ed41e061894107885c3e00824c758931ff09d8
+size 6648