Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: Meta-Llama/Meta-Llama-3.1-8B
+library_name: transformers
+model_name: llama-3-1-8b-math-orca-spectrum-10k-ep1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for llama-3-1-8b-math-orca-spectrum-10k-ep1
+
+This model is a fine-tuned version of [Meta-Llama/Meta-Llama-3.1-8B](https://huggingface.co/Meta-Llama/Meta-Llama-3.1-8B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="philschmid/llama-3-1-8b-math-orca-spectrum-10k-ep1", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.1
+- Transformers: 4.46.3
+- Pytorch: 2.4.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9882352941176471,
+    "total_flos": 8684660632584192.0,
+    "train_loss": 0.4845818508239019,
+    "train_runtime": 2191.8228,
+    "train_samples": 10000,
+    "train_samples_per_second": 2.468,
+    "train_steps_per_second": 0.019
+}

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9882352941176471,
+    "total_flos": 8684660632584192.0,
+    "train_loss": 0.4845818508239019,
+    "train_runtime": 2191.8228,
+    "train_samples": 10000,
+    "train_samples_per_second": 2.468,
+    "train_steps_per_second": 0.019
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9882352941176471,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 3.502065765112122,
+      "learning_rate": 5e-05,
+      "loss": 1.2955,
+      "step": 5
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.0166353187103343,
+      "learning_rate": 4.77807122597034e-05,
+      "loss": 0.5761,
+      "step": 10
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 2.0609265403495867,
+      "learning_rate": 4.151686808475204e-05,
+      "loss": 0.4265,
+      "step": 15
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.42584227426186005,
+      "learning_rate": 3.232056928191376e-05,
+      "loss": 0.3626,
+      "step": 20
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.31196594170810965,
+      "learning_rate": 2.182455450632803e-05,
+      "loss": 0.337,
+      "step": 25
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.2951365308766864,
+      "learning_rate": 1.1892317911069212e-05,
+      "loss": 0.3255,
+      "step": 30
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.2794268174086481,
+      "learning_rate": 4.2872587689039484e-06,
+      "loss": 0.3152,
+      "step": 35
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.27293344082468357,
+      "learning_rate": 3.5960224130728857e-07,
+      "loss": 0.3135,
+      "step": 40
+    },
+    {
+      "epoch": 0.9882352941176471,
+      "step": 42,
+      "total_flos": 8684660632584192.0,
+      "train_loss": 0.4845818508239019,
+      "train_runtime": 2191.8228,
+      "train_samples_per_second": 2.468,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8684660632584192.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}