Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: transformers
+model_name: zephyr-7b-sft-qlora
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for zephyr-7b-sft-qlora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+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="Samtari/zephyr-7b-sft-qlora", 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: 0.12.2
+- Transformers: 4.46.3
+- Pytorch: 2.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.20.3
+
+## 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": 1.0,
+    "total_flos": 1.1953201746018304e+16,
+    "train_loss": 1.045757819624508,
+    "train_runtime": 10046.7574,
+    "train_samples": 207,
+    "train_samples_per_second": 0.014,
+    "train_steps_per_second": 0.002
+}

runs/Apr21_13-36-55_KnowledgeHub/events.out.tfevents.1745257025.KnowledgeHub.278607.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5519b51e84f703fcd1d99cc95860cd24f4276e4892e44b51c6496af97700b90a
-size 7472
+oid sha256:8e16ee85fed1be1f4473add6765dffd34036ab6fe6416dc1a12b20af022413cc
+size 8086

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.1953201746018304e+16,
+    "train_loss": 1.045757819624508,
+    "train_runtime": 10046.7574,
+    "train_samples": 207,
+    "train_samples_per_second": 0.014,
+    "train_steps_per_second": 0.002
+}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 17,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.8823225498199463,
+      "learning_rate": 0.0001,
+      "loss": 1.1403,
+      "step": 1
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.6753513813018799,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0209,
+      "step": 5
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.499729186296463,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.0693,
+      "step": 10
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.993525505065918,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.0604,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0393339395523071,
+      "eval_runtime": 9748.8038,
+      "eval_samples_per_second": 1.575,
+      "eval_steps_per_second": 0.197,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "step": 17,
+      "total_flos": 1.1953201746018304e+16,
+      "train_loss": 1.045757819624508,
+      "train_runtime": 10046.7574,
+      "train_samples_per_second": 0.014,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 17,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1953201746018304e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}