Model save

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: opt-babylm2-rewritten-clean-spacy_random-removal-num-adj-earlystop-bpe_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_random-removal-num-adj-earlystop-bpe_seed-42_1e-3
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6849
+- Accuracy: 0.4784
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 4.0965        | 0.9997  | 2241  | 3.8077          | 0.3617   |
+| 3.438         | 1.9997  | 4482  | 3.2954          | 0.4103   |
+| 3.124         | 2.9997  | 6723  | 3.0855          | 0.4310   |
+| 2.964         | 3.9997  | 8964  | 2.9821          | 0.4414   |
+| 2.8431        | 4.9997  | 11205 | 2.9217          | 0.4475   |
+| 2.7861        | 5.9997  | 13446 | 2.8828          | 0.4518   |
+| 2.7474        | 6.9997  | 15687 | 2.8555          | 0.4548   |
+| 2.7083        | 7.9997  | 17928 | 2.8363          | 0.4568   |
+| 2.6908        | 8.9997  | 20169 | 2.8231          | 0.4584   |
+| 2.6704        | 9.9997  | 22410 | 2.8133          | 0.4595   |
+| 2.6536        | 10.9997 | 24651 | 2.8057          | 0.4603   |
+| 2.6385        | 11.9997 | 26892 | 2.7991          | 0.4613   |
+| 2.6417        | 12.9997 | 29133 | 2.7933          | 0.4621   |
+| 2.6348        | 13.9997 | 31374 | 2.7883          | 0.4627   |
+| 2.6156        | 14.9997 | 33615 | 2.7718          | 0.4648   |
+| 2.5708        | 15.9997 | 35856 | 2.7449          | 0.4683   |
+| 2.5219        | 16.9997 | 38097 | 2.7226          | 0.4711   |
+| 2.4669        | 17.9997 | 40338 | 2.7019          | 0.4743   |
+| 2.4023        | 18.9997 | 42579 | 2.6891          | 0.4769   |
+| 2.3317        | 19.9997 | 44820 | 2.6849          | 0.4784   |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.5.1
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 16384
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "models/opt-babylm2-rewritten-clean-spacy_random-removal-num-adj-earlystop-bpe_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": 2,
+  "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": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 16384,
+  "word_embed_proj_dim": 768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056363267ec30cc34073dc8814a6a75c23264bc0017895ddf37c5447146c1b12
+size 391370592

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 +1,49 @@
+{
+  "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
+    },
+    "16384": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<s>",
+  "extra_special_tokens": {},
+  "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 sha256:173779a6903547ad6d49db9b45b3614a01d380b8dc6ea5b55108c7e672d7b480
+size 5560