Model save

README.md

@@ -1,5 +1,6 @@
 ---
 license: other
+base_model: facebook/opt-350m
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opt
 
-This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on an unknown dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
 
 ## Model description
 
@@ -32,17 +33,18 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 32
-- eval_batch_size: 64
+- train_batch_size: 4
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 1
+- mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.30.2
-- Pytorch 1.12.1
-- Datasets 2.13.2
-- Tokenizers 0.13.3
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-1.3b",
+  "_name_or_path": "facebook/opt-350m",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",
@@ -8,24 +8,24 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 2,
-  "do_layer_norm_before": true,
+  "do_layer_norm_before": false,
   "dropout": 0.1,
   "enable_bias": true,
   "eos_token_id": 2,
-  "ffn_dim": 8192,
-  "hidden_size": 2048,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
   "init_std": 0.02,
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,
   "max_position_embeddings": 2048,
   "model_type": "opt",
-  "num_attention_heads": 32,
+  "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 50265,
-  "word_embed_proj_dim": 2048
+  "word_embed_proj_dim": 512
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.30.2"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb97796f804cc7bfca00f34d7c5b1b8cafd87d0d7a41601f9a7d46c6a0fd900
+size 1324816544

tokenizer_config.json

@@ -1,40 +1,30 @@
 {
   "add_bos_token": true,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "</s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "</s>",
   "errors": "replace",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "</s>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3497f6cf8f68cda25332639a2e2495ee4edce511ddd7f1394aab52b54978dd7c
-size 3887
+oid sha256:eec0bdf0c45022371a90dd8db539f779f0f5a0d6f3519058c17932f176537f84
+size 4856