Training in progress, step 200

axolotl_config.yaml

@@ -1,5 +1,5 @@
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
-batch_size: 96
+base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
+batch_size: 256
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
 datasets:
@@ -25,7 +25,7 @@ learning_rate: 0.0002
 logging_steps: 10
 lr_scheduler: cosine
 max_steps: 20000
-micro_batch_size: 12
+micro_batch_size: 32
 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: TinyLlama/TinyLlama-1.1B-Chat-v1.0-argilla/databricks-dolly-15k-curated-en
+wandb_name: trl-internal-testing/tiny-random-LlamaForCausalLM-argilla/databricks-dolly-15k-curated-en
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: default

config.json

@@ -1,25 +1,26 @@
 {
-  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "_name_or_path": "trl-internal-testing/tiny-random-LlamaForCausalLM",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
+  "bos_token_id": 0,
   "eos_token_id": 2,
-  "head_dim": 64,
+  "head_dim": 4,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 16,
   "initializer_range": 0.02,
-  "intermediate_size": 5632,
+  "intermediate_size": 64,
   "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 22,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
   "num_key_value_heads": 4,
+  "pad_token_id": -1,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f733e9041aab06f212569d2073af6e6c0acf30fcc84bec18f30feab19bc086f
-size 2200119864
+oid sha256:23835aa3baa0dcf892abf69863f1f0c1ea20a2c3908d99240a722cf7177381d0
+size 2066752

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88bda6bdd84543eadebdf4bd2ec325ae43b71a3ff1fead6a766562c00b29bd8
-size 3619016
+oid sha256:d606f46a8aa6f29f0a0abdec7c3ffddefc9f9bfe26919532d209a0a850e25029
+size 3619013

tokenizer_config.json

@@ -29,17 +29,15 @@
     }
   },
   "bos_token": "<s>",
-  "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 %}",
+  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_special_tokens": {},
-  "legacy": false,
+  "legacy": true,
   "model_max_length": 2048,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
+  "pad_token": "<unk>",
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
+  "use_default_system_prompt": true,
   "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917005e54e6a74be4d5bc3c0309ff36483f7719e494b126c6cee70ee375d0421
-size 7032
+oid sha256:c9e9fca0c23d9cd44121007d8469411a44af500190e6fe6533d8ba7e8ebaeafa
+size 6840