Training in progress, step 100

axolotl_config.yaml

@@ -1,5 +1,5 @@
-base_model: unsloth/OpenHermes-2.5-Mistral-7B
-batch_size: 32
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+batch_size: 96
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -24,8 +24,8 @@ hub_strategy: checkpoint
 learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
-max_steps: 10000
-micro_batch_size: 2
+max_steps: 20000
+micro_batch_size: 12
 model_type: AutoModelForCausalLM
 num_epochs: 100
 optimizer: adamw_bnb_8bit
@@ -42,7 +42,7 @@ trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
 wandb_mode: online
-wandb_name: unsloth/OpenHermes-2.5-Mistral-7B-argilla/databricks-dolly-15k-curated-en
+wandb_name: TinyLlama/TinyLlama-1.1B-Chat-v1.0-argilla/databricks-dolly-15k-curated-en
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: default

config.json

@@ -1,28 +1,30 @@
 {
-  "_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
-    "MistralForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
-  "head_dim": 128,
+  "eos_token_id": 2,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pad_token_id": 0,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.1",
   "use_cache": false,
-  "vocab_size": 32002
+  "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ce8744c1e71a49bf9bff3ccecfc98f1e92613ac7fabd94737ad873ca1a94de
-size 250490408
+oid sha256:9f733e9041aab06f212569d2073af6e6c0acf30fcc84bec18f30feab19bc086f
+size 2200119864

special_tokens_map.json

@@ -7,14 +7,14 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
+    "content": "</s>",
     "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:c88bda6bdd84543eadebdf4bd2ec325ae43b71a3ff1fead6a766562c00b29bd8
+size 3619016

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -26,39 +26,20 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "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>",
-  "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 %}",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "legacy": true,
-  "model_max_length": 32768,
-  "pad_token": "<unk>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
   "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,
+  "use_default_system_prompt": false,
   "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62c95db7d808ffe6624a24b5b202f0f59342fc3d11220ea4577943c4efbf06e
-size 6776
+oid sha256:917005e54e6a74be4d5bc3c0309ff36483f7719e494b126c6cee70ee375d0421
+size 7032