End of training

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM-135M
+tags:
+- generated_from_trainer
+model-index:
+- name: lab7-shakespeare-generator2
+  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. -->
+
+# lab7-shakespeare-generator2
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5582
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.8418        | 0.2747 | 100  | 3.6673          |
+| 3.7432        | 0.5495 | 200  | 3.6014          |
+| 3.6580        | 0.8242 | 300  | 3.5733          |
+| 3.6421        | 1.0989 | 400  | 3.5628          |
+| 3.6488        | 1.3736 | 500  | 3.5589          |
+| 3.6311        | 1.6484 | 600  | 3.5580          |
+| 3.6232        | 1.9231 | 700  | 3.5579          |
+| 3.6232        | 2.0    | 728  | 3.5582          |
+
+
+### Framework versions
+
+- Transformers 5.12.1
+- Pytorch 2.12.1
+- Datasets 5.0.0
+- Tokenizers 0.22.2

config.json

@@ -5,15 +5,14 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "dtype": "float16",
+  "dtype": "bfloat16",
   "eos_token_id": 0,
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
+  "initializer_range": 0.02,
   "intermediate_size": 1536,
-  "is_llama_config": true,
-  "max_position_embeddings": 8192,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,
@@ -22,9 +21,8 @@
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_interleaved": false,
   "rope_parameters": {
-    "rope_theta": 100000,
+    "rope_theta": 10000.0,
     "rope_type": "default"
   },
   "tie_word_embeddings": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e11b06d6977f560ef57765748dcd17a8437b6d2acf7e9e68c2d8de353e133bd
-size 269060280
+oid sha256:e8b97f551ce6a98454cf3d74fd692a4964511814d9a7aa3687d5de1082b37405
+size 269060552

tokenizer_config.json

@@ -26,7 +26,7 @@
   ],
   "is_local": false,
   "local_files_only": false,
-  "model_max_length": 8192,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f66913e3a60bf02c0595baeef7b68061375d221d3439e9094b7fa0206326a7
+oid sha256:5029b829699a7326d00774c0c25903aef5a164c9d371b9570ba098490a6df51b
 size 5137