End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: gpt2
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
 - trl
 - sft
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mayo
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
+- train_batch_size: 2
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

config.json

@@ -1,39 +1,28 @@
 {
-  "_name_or_path": "gpt2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
-    "GPT2LMHeadModel"
+    "LlamaForCausalLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.39.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daba1f0e79e633cb39f4038180551d9410234037003640d4f3486a422577d8ec
-size 497774208
+oid sha256:2179f5dfe40702302e450d03cc60a4394e3805f0b690556c357c40a19799a02f
+size 4400216536

runs/May28_01-51-02_da98241e7d99/events.out.tfevents.1716861079.da98241e7d99.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16664721934d764075364f544ea3b92fdb3c1cdfc35cf60a151f6fef5a34cc69
+size 4989

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,20 +1,42 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "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>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f0c5d4b27eda891df5efc134226b67ac3b0ed8ad0322ec04152b98840b435c
+oid sha256:6beb574b5bf628f500e95c189c29c13a15d1254092404aa86dcfcf9a8e01e983
 size 4920