Training in progress, step 400

added_tokens.json

@@ -1,5 +1,13 @@
 {
-  "<|endoftext|>": 151643,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
 }

axolotl_config.yaml

@@ -1,4 +1,4 @@
-base_model: EleutherAI/pythia-70m-deduped
+base_model: Xenova/tiny-random-Phi3ForCausalLM
 batch_size: 32
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
@@ -36,15 +36,13 @@ sample_packing: false
 save_steps: 400
 save_total_limit: 1
 sequence_len: 2048
-special_tokens:
-  pad_token: <|endoftext|>
-tokenizer_type: GPTNeoXTokenizerFast
+tokenizer_type: LlamaTokenizerFast
 torch_dtype: bf16
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
 wandb_mode: online
-wandb_name: EleutherAI/pythia-70m-deduped-argilla/databricks-dolly-15k-curated-en
+wandb_name: Xenova/tiny-random-Phi3ForCausalLM-argilla/databricks-dolly-15k-curated-en
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: default

config.json

@@ -1,32 +1,31 @@
 {
-  "_name_or_path": "EleutherAI/pythia-70m-deduped",
+  "_name_or_path": "Xenova/tiny-random-Phi3ForCausalLM",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "Phi3ForCausalLM"
   ],
-  "attention_bias": true,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classifier_dropout": 0.1,
-  "eos_token_id": 0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 512,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 32,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
-  "partial_rotary_factor": 0.25,
+  "intermediate_size": 64,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.48.1",
   "use_cache": false,
-  "use_parallel_residual": true,
-  "vocab_size": 50278
+  "vocab_size": 32011
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87af69528d3a9f5f337cc3e1ceb9b547a6ef7f97a229fb620e469e88f32de172
-size 140808752
+oid sha256:9887d0a75dcfd98e56a4c42489abac39f5f9adfc1e32e149aaacb6e76bd402cd
+size 4140280

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -21,7 +21,7 @@
     "single_word": false
   },
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95aac127870725c031582253de8b2d45c9e3e009d893f89bec47a9b26f974aa
-size 3564484
+oid sha256:b013fe7282b7984bc14b1c64c2a70dd06b652a969810fbba6217f4ac70339f44
+size 3621089

tokenizer_config.json

@@ -1,10 +1,10 @@
 {
-  "add_bos_token": false,
+  "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
-      "content": "<|endoftext|>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,214 +12,122 @@
       "special": true
     },
     "1": {
-      "content": "<|padding|>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50254": {
-      "content": "                        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50255": {
-      "content": "                       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50256": {
-      "content": "                      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50257": {
-      "content": "                     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50258": {
-      "content": "                    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50259": {
-      "content": "                   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50260": {
-      "content": "                  ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50261": {
-      "content": "                 ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50262": {
-      "content": "                ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50263": {
-      "content": "               ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50264": {
-      "content": "              ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50265": {
-      "content": "             ",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50266": {
-      "content": "            ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "50267": {
-      "content": "           ",
+    "32000": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50268": {
-      "content": "          ",
+    "32001": {
+      "content": "<|assistant|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50269": {
-      "content": "         ",
+    "32002": {
+      "content": "<|placeholder1|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50270": {
-      "content": "        ",
+    "32003": {
+      "content": "<|placeholder2|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50271": {
-      "content": "       ",
+    "32004": {
+      "content": "<|placeholder3|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50272": {
-      "content": "      ",
+    "32005": {
+      "content": "<|placeholder4|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50273": {
-      "content": "     ",
+    "32006": {
+      "content": "<|system|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50274": {
-      "content": "    ",
+    "32007": {
+      "content": "<|end|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50275": {
-      "content": "   ",
+    "32008": {
+      "content": "<|placeholder5|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50276": {
-      "content": "  ",
+    "32009": {
+      "content": "<|placeholder6|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50277": {
-      "content": "[PAD]",
+    "32010": {
+      "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "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 %}",
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "legacy": true,
+  "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
   "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb39bdcd9027f9839c24593aa51e9c2c6db52de8ff1d60ef6eace2d38a2b7bf
+oid sha256:8ffd459aa83253f73e371e129574dd0434ee79c2c18eb103b0e4428a34062eb2
 size 6840