Model save

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: opt-babylm2-clean-spacy-32k-earlystop_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-clean-spacy-32k-earlystop_seed-42_1e-3
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9103
+- Accuracy: 0.4305
+
+## 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: 20.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 5.9107        | 0.9995  | 1942  | 3.9887          | 0.3269   |
+| 3.7896        | 1.9996  | 3885  | 3.5236          | 0.3657   |
+| 3.3813        | 2.9997  | 5828  | 3.3040          | 0.3859   |
+| 3.174         | 3.9997  | 7771  | 3.1921          | 0.3962   |
+| 3.0533        | 4.9998  | 9714  | 3.1266          | 0.4026   |
+| 2.9768        | 5.9999  | 11657 | 3.0838          | 0.4071   |
+| 2.9232        | 6.9999  | 13600 | 3.0550          | 0.4101   |
+| 2.8863        | 8.0     | 15543 | 3.0363          | 0.4122   |
+| 2.8563        | 8.9995  | 17485 | 3.0208          | 0.4139   |
+| 2.8356        | 9.9996  | 19428 | 3.0117          | 0.4151   |
+| 2.816         | 10.9997 | 21371 | 3.0030          | 0.4162   |
+| 2.8069        | 11.9997 | 23314 | 2.9951          | 0.4170   |
+| 2.7941        | 12.9998 | 25257 | 2.9923          | 0.4175   |
+| 2.7889        | 13.9999 | 27200 | 2.9888          | 0.4182   |
+| 2.7802        | 14.9999 | 29143 | 2.9839          | 0.4186   |
+| 2.7802        | 16.0    | 31086 | 2.9821          | 0.4190   |
+| 2.7665        | 16.9995 | 33028 | 2.9626          | 0.4212   |
+| 2.6908        | 17.9996 | 34971 | 2.9378          | 0.4247   |
+| 2.6058        | 18.9997 | 36914 | 2.9145          | 0.4284   |
+| 2.505         | 19.9910 | 38840 | 2.9103          | 0.4305   |
+
+
+### 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-clean-spacy-32k-earlystop_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:bf29a91744f905cb94dc8bde808a0aa9ea7c22a4d1b455d517f38b72076d39e5
+size 441702288

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

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": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac66da054e67caa9dbd7e00ee8a889ebb25e3fae475be1803e5220375f49616
+size 5368