Model save

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+model_name: lr_0.08
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for lr_0.08
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="nijji/lr_0.08", 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: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.21.0
+
+## 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}}
+}
+```

adapter_config.json

@@ -23,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "gate_proj",
+    "q_proj",
     "k_proj",
-    "up_proj",
     "down_proj",
-    "o_proj",
-    "q_proj",
+    "up_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.05836359974912e+16,
+    "train_loss": 0.0,
+    "train_runtime": 0.0102,
+    "train_samples": 106,
+    "train_samples_per_second": 21952.045,
+    "train_steps_per_second": 21952.045
+}

runs/Feb25_17-23-53_autodl-container-1b3442a671-84b9ecdf/events.out.tfevents.1740475447.autodl-container-1b3442a671-84b9ecdf.180391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf419bc550567fdfc4feb307e6afe0304e32dd7fd3113e20e11dd6949b46d6a
+size 6443

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.05836359974912e+16,
+    "train_loss": 0.0,
+    "train_runtime": 0.0102,
+    "train_samples": 106,
+    "train_samples_per_second": 21952.045,
+    "train_steps_per_second": 21952.045
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 9.698728561401367,
+      "learning_rate": 8e-05,
+      "loss": 1.225,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 6.055803298950195,
+      "learning_rate": 8e-05,
+      "loss": 0.8495,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.679312705993652,
+      "learning_rate": 8e-05,
+      "loss": 0.6574,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 4.378487586975098,
+      "learning_rate": 8e-05,
+      "loss": 0.5618,
+      "step": 40
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 7.2650227546691895,
+      "learning_rate": 8e-05,
+      "loss": 0.4845,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.8373830318450928,
+      "learning_rate": 8e-05,
+      "loss": 0.4631,
+      "step": 60
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 3.852592945098877,
+      "learning_rate": 8e-05,
+      "loss": 0.5386,
+      "step": 70
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.892258405685425,
+      "learning_rate": 8e-05,
+      "loss": 0.3107,
+      "step": 80
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.4811666011810303,
+      "learning_rate": 8e-05,
+      "loss": 0.3547,
+      "step": 90
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.9795215129852295,
+      "learning_rate": 8e-05,
+      "loss": 0.2735,
+      "step": 100
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.7794923782348633,
+      "learning_rate": 8e-05,
+      "loss": 0.2833,
+      "step": 110
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.8691558837890625,
+      "learning_rate": 8e-05,
+      "loss": 0.3257,
+      "step": 120
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 3.442941904067993,
+      "learning_rate": 8e-05,
+      "loss": 0.1854,
+      "step": 130
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 2.7556700706481934,
+      "learning_rate": 8e-05,
+      "loss": 0.3391,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.3837943077087402,
+      "learning_rate": 8e-05,
+      "loss": 0.2899,
+      "step": 150
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 3.2746551036834717,
+      "learning_rate": 8e-05,
+      "loss": 0.1971,
+      "step": 160
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.148310661315918,
+      "learning_rate": 8e-05,
+      "loss": 0.1219,
+      "step": 170
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.608214855194092,
+      "learning_rate": 8e-05,
+      "loss": 0.1486,
+      "step": 180
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 3.537290334701538,
+      "learning_rate": 8e-05,
+      "loss": 0.1678,
+      "step": 190
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.9116101264953613,
+      "learning_rate": 8e-05,
+      "loss": 0.1679,
+      "step": 200
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 3.0522828102111816,
+      "learning_rate": 8e-05,
+      "loss": 0.1545,
+      "step": 210
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 2.040424108505249,
+      "learning_rate": 8e-05,
+      "loss": 0.1119,
+      "step": 220
+    },
+    {
+      "epoch": 3.0,
+      "step": 225,
+      "total_flos": 1.05836359974912e+16,
+      "train_loss": 0.0,
+      "train_runtime": 0.0102,
+      "train_samples_per_second": 21952.045,
+      "train_steps_per_second": 21952.045
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.05836359974912e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2e63870eb0e2b094324c03b7c0d06a4759336cdc35ed724540ef84ee3c9782
+oid sha256:cd38717b7ebf695824ad76f312984b478667bd48a842bf02da79e67b67963310
 size 5688