End of training

README.md

@@ -1,7 +1,7 @@
 ---
-library_name: peft
-license: apache-2.0
-base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+library_name: transformers
+license: other
+base_model: facebook/opt-125m
 tags:
 - trl
 - sft
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # checkpoint
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
 
 ## Model description
 
@@ -36,16 +36,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 3
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 16
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- training_steps: 1
-- mixed_precision_training: Native AMP
+- lr_scheduler_type: linear
+- num_epochs: 10
 
 ### Training results
 
@@ -53,8 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.14.0
 - Transformers 4.46.1
 - Pytorch 2.1.1+cu121
 - Datasets 2.18.0
-- Tokenizers 0.20.3
+- Tokenizers 0.20.3

config.json

@@ -1,34 +1,31 @@
 {
-  "_name_or_path": "appvoid/llama-3-1b",
+  "_name_or_path": "facebook/opt-125m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
   "architectures": [
-    "LlamaForCausalLM"
+    "OPTForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
-  "num_key_value_heads": 8,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "rope_type": "linear",
-    "type": "linear"
-  },
-  "rope_theta": 500000.0,
-  "tie_word_embeddings": true,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "float32",
   "transformers_version": "4.46.1",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
   "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979cbcf0f3f07e8e91ed93e66bd9e92025f81be1817957980142c2149d23cd7a
-size 4943274328
+oid sha256:83cc672c5e12b5aa4b14c9ae23cea9c0fa1c8664810d29930c45fa5465dc385d
+size 500979600

special_tokens_map.json

@@ -1,23 +1,23 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": "</s>",
   "unk_token": {
-    "content": "<unk>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6386c019c9a2ec0aeaafc7f5ee4c17155e7e27151843d4f9b2d0141aa3e57d5d
-size 3619114
+oid sha256:1376cab04a2341905d16a36c455fd483733e230a95c3fdabd804bb785fab9644
+size 3559091

tokenizer_config.json

@@ -1,26 +1,25 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "50265": {
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,15 +27,12 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "</s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
+  "errors": "replace",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616d6b5b45858e867f19e3ca64ff777cbebe13688f7968329a5c72cd7a7e9cdb
-size 5496
+oid sha256:51494b36584bc4c48d58f187d2f620663db90c6b845fd1fa6416b676df3b8e86
+size 5560