Model save

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: opt-babylm2-clean-20-epochs-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-20-epochs-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: 2.7611
+- Accuracy: 0.4673
+
+## 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 4.24          | 0.9998  | 2198  | 3.9528          | 0.3447   |
+| 3.5581        | 2.0     | 4397  | 3.4120          | 0.3948   |
+| 3.2191        | 2.9998  | 6595  | 3.1806          | 0.4180   |
+| 3.0495        | 4.0     | 8794  | 3.0720          | 0.4287   |
+| 2.9458        | 4.9998  | 10992 | 3.0054          | 0.4354   |
+| 2.8669        | 6.0     | 13191 | 2.9663          | 0.4399   |
+| 2.8256        | 6.9998  | 15389 | 2.9382          | 0.4430   |
+| 2.79          | 8.0     | 17588 | 2.9199          | 0.4452   |
+| 2.7624        | 8.9998  | 19786 | 2.9052          | 0.4468   |
+| 2.7361        | 10.0    | 21985 | 2.8915          | 0.4482   |
+| 2.7354        | 10.9998 | 24183 | 2.8843          | 0.4491   |
+| 2.7225        | 12.0    | 26382 | 2.8777          | 0.4500   |
+| 2.7092        | 12.9998 | 28580 | 2.8708          | 0.4505   |
+| 2.6987        | 14.0    | 30779 | 2.8688          | 0.4509   |
+| 2.6894        | 14.9998 | 32977 | 2.8542          | 0.4527   |
+| 2.6561        | 16.0    | 35176 | 2.8258          | 0.4564   |
+| 2.6055        | 16.9998 | 37374 | 2.8005          | 0.4595   |
+| 2.5464        | 18.0    | 39573 | 2.7814          | 0.4627   |
+| 2.4778        | 18.9998 | 41771 | 2.7630          | 0.4658   |
+| 2.4036        | 19.9955 | 43960 | 2.7611          | 0.4673   |
+
+
+### 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|>": 16384
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "models/opt-babylm2-clean-20-epochs-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": 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": "4.45.1",
+  "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": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b458664d85a606de326fd0bc2092788a27ceda97a39841040f609a24bcfee1d
+size 391370592

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
+    },
+    "16384": {
+      "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:d8ceee44774144ec4505ae9f3ba368f49abbd2ddc910a53e6b764eb9007a0bb7
+size 5368