Model save

README.md

@@ -0,0 +1,90 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: opt-babylm2-rewritten-clean-spacy-32k-earlystop-40epochs_seed-42_1e-3
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# opt-babylm2-rewritten-clean-spacy-32k-earlystop-40epochs_seed-42_1e-3
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9601
+- Accuracy: 0.4245
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 32
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 32000
+- num_epochs: 40.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 5.9216        | 0.9996  | 1931  | 4.0134          | 0.3253   |
+| 3.7977        | 1.9997  | 3863  | 3.5448          | 0.3639   |
+| 3.3887        | 2.9999  | 5795  | 3.3242          | 0.3841   |
+| 3.1805        | 4.0     | 7727  | 3.2082          | 0.3949   |
+| 3.0632        | 4.9996  | 9658  | 3.1432          | 0.4012   |
+| 2.9865        | 5.9997  | 11590 | 3.1010          | 0.4056   |
+| 2.9347        | 6.9999  | 13522 | 3.0715          | 0.4087   |
+| 2.8953        | 8.0     | 15454 | 3.0539          | 0.4108   |
+| 2.8689        | 8.9996  | 17385 | 3.0392          | 0.4122   |
+| 2.8456        | 9.9997  | 19317 | 3.0310          | 0.4134   |
+| 2.8298        | 10.9999 | 21249 | 3.0251          | 0.4144   |
+| 2.817         | 12.0    | 23181 | 3.0175          | 0.4152   |
+| 2.8069        | 12.9996 | 25112 | 3.0119          | 0.4158   |
+| 2.7996        | 13.9997 | 27044 | 3.0060          | 0.4163   |
+| 2.7615        | 14.9999 | 28976 | 3.0038          | 0.4171   |
+| 2.7575        | 16.0    | 30908 | 3.0022          | 0.4169   |
+| 2.7573        | 16.9996 | 32839 | 2.9962          | 0.4179   |
+| 2.7451        | 17.9997 | 34771 | 2.9867          | 0.4189   |
+| 2.7275        | 18.9999 | 36703 | 2.9804          | 0.4201   |
+| 2.7099        | 20.0    | 38635 | 2.9760          | 0.4208   |
+| 2.693         | 20.9996 | 40566 | 2.9683          | 0.4216   |
+| 2.6785        | 21.9997 | 42498 | 2.9666          | 0.4221   |
+| 2.6628        | 22.9999 | 44430 | 2.9646          | 0.4227   |
+| 2.6501        | 24.0    | 46362 | 2.9626          | 0.4228   |
+| 2.6343        | 24.9996 | 48293 | 2.9600          | 0.4233   |
+| 2.6198        | 25.9997 | 50225 | 2.9638          | 0.4236   |
+| 2.604         | 26.9999 | 52157 | 2.9604          | 0.4240   |
+| 2.5876        | 28.0    | 54089 | 2.9601          | 0.4245   |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 32768
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "models/opt-babylm2-rewritten-clean-spacy-32k-earlystop-40epochs_seed-42_1e-3",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 1,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 256,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "prefix": "<s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 32768,
+  "word_embed_proj_dim": 768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c46300e1507891ff4bcba77642a126e2e0677feebee0e37eb327ba558116c0
+size 441702288

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": "<pad>",
+    "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 +1,48 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32768": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<s>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036c4696325cf5cf83debeaa7899cf73ea0bdeae8e84c36fe9c6e8d7605ae537
+size 5368