aakarsh-nair/rerun-09-19-2024-experiment-distill-tree-babylm2024-95-1

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: rerun-09-19-2024-experiment-distill-tree-babylm2024-95-1
+  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. -->
+
+# rerun-09-19-2024-experiment-distill-tree-babylm2024-95-1
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0665
+
+## 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: 0.00025
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 7.0069        | 1.0   | 2065  | 7.4068          |
+| 3.7952        | 2.0   | 4130  | 4.2014          |
+| 2.9621        | 3.0   | 6195  | 3.3890          |
+| 2.6124        | 4.0   | 8260  | 2.9090          |
+| 2.2           | 5.0   | 10325 | 2.6031          |
+| 2.0533        | 6.0   | 12390 | 2.3690          |
+| 1.8556        | 7.0   | 14455 | 2.2142          |
+| 1.7613        | 8.0   | 16520 | 2.1214          |
+| 1.6772        | 9.0   | 18585 | 2.0749          |
+| 1.7112        | 10.0  | 20650 | 2.0665          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 16000
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 256,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 10,
+  "num_key_value_heads": 12,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 16000
+}

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": "4.45.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3c2e99495aeb32e709482017204dfa7ca923fe5174c690695c68630fc31727
+size 381494328

runs/Sep19_13-17-13_745c03f56d72/events.out.tfevents.1726751833.745c03f56d72.938.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22780ce9b8df2f4ac2b5c781e32aff4833b4a4abb291df6296ed6ef16be85c1f
+size 6300

runs/Sep19_13-21-46_745c03f56d72/events.out.tfevents.1726752106.745c03f56d72.938.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54731032184b6a4803cb639fc64b6291330461cac26f3eebce97282803343b4f
+size 5679

runs/Sep19_13-35-19_745c03f56d72/events.out.tfevents.1726752919.745c03f56d72.938.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ed3048d7d92bcd63bc6e35d35aa75fbb7a063406ffaf90dc49d23e9b6c8024
+size 226723

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2004056d6db786199fb3752f62dc7fd10ee079a501942351d28064203dedf14f
+size 5368