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:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test_trainer
 
-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
 

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -1,40 +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,
-  "pad_token_id": 50257,
-  "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": "4.36.2",
   "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": "4.36.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d00560d8910fbed77ffad4065dee5011c41ba401b1064e749c498ba9e20373
-size 497774208
+oid sha256:5e9e93a56efef2e4c9a01d31c9f3e1d5b7369b81843a426ecfd1889b10e4361d
+size 4400216536

runs/Jan07_22-31-12_Arashdeeps-MacBook-Air.local/events.out.tfevents.1704647365.Arashdeeps-MacBook-Air.local.710.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83773553ed780047c6a75cfe5c680ebb0bf54152c0229837fb75e40c4e5c8113
+size 13672

runs/Jan07_22-42-46_Arashdeeps-MacBook-Air.local/events.out.tfevents.1704647567.Arashdeeps-MacBook-Air.local.689.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf739e600ee3eee9651da70ab70897ab340af381ff75660b350fd90d259996d
+size 4616

runs/Jan07_22-44-28_Arashdeeps-MacBook-Air.local/events.out.tfevents.1704647672.Arashdeeps-MacBook-Air.local.689.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b28c1f86da3e2435a5624a57239ab11a16658ac6ce1d4913a509b4c5e764471
+size 4616

runs/Jan07_22-47-30_Arashdeeps-MacBook-Air.local/events.out.tfevents.1704647850.Arashdeeps-MacBook-Air.local.1093.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc1c81704dbf0c7ad9aefe31d91ed8bedc004b2ffc04c0e892f62b3371c3699
+size 4616

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "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": "<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:eb23666ef2eb9bbe8c0ab88202d233af97242b010682334380ec8b80fe97aa02
+oid sha256:c97d57d655212fd34339132e39830d529f35c465597ef7565b738cfd3ec2daaf
 size 4728