Model save

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: babylm-unablated_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. -->
+
+# babylm-unablated_seed-42_1e-3
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0130
+- Accuracy: 0.4207
+
+## 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 6.173         | 0.9997  | 1802  | 4.2465          | 0.3068   |
+| 4.0432        | 2.0     | 3605  | 3.7284          | 0.3475   |
+| 3.6166        | 2.9997  | 5407  | 3.4711          | 0.3707   |
+| 3.3909        | 4.0     | 7210  | 3.3322          | 0.3836   |
+| 3.2635        | 4.9997  | 9012  | 3.2560          | 0.3913   |
+| 3.1946        | 6.0     | 10815 | 3.2042          | 0.3959   |
+| 3.1312        | 6.9997  | 12617 | 3.1730          | 0.3994   |
+| 3.0872        | 8.0     | 14420 | 3.1528          | 0.4014   |
+| 3.0554        | 8.9997  | 16222 | 3.1347          | 0.4037   |
+| 3.0338        | 10.0    | 18025 | 3.1247          | 0.4043   |
+| 2.9873        | 10.9997 | 19827 | 3.1119          | 0.4059   |
+| 2.9773        | 12.0    | 21630 | 3.1093          | 0.4065   |
+| 2.9714        | 12.9997 | 23432 | 3.1020          | 0.4077   |
+| 2.9667        | 14.0    | 25235 | 3.0977          | 0.4077   |
+| 2.9621        | 14.9997 | 27037 | 3.0944          | 0.4085   |
+| 2.9239        | 16.0    | 28840 | 3.0954          | 0.4082   |
+| 2.9295        | 16.9997 | 30642 | 3.0936          | 0.4085   |
+| 2.9329        | 18.0    | 32445 | 3.0771          | 0.4106   |
+| 2.8605        | 18.9997 | 34247 | 3.0338          | 0.4164   |
+| 2.7104        | 19.9945 | 36040 | 3.0130          | 0.4207   |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.20.0

added_tokens.json

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "models/babylm-unablated_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 sha256:7f6711a302ae57fef3d2f5630fd7fb802c9b060dd51071c5ee226573aa46f779
+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:e8acb14900e0287cde9bcb8f22bf36b41e47a3c0be6f5b74f028a999bc978491
+size 5304