Model save

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+model_name: double_train_1-1_down
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for double_train_1-1_down
+
+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/double_train_1-1_down", 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: 2.5.1
+- Datasets: 3.1.0
+- 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}}
+}
+```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc085bfeef3ade5b0f0f160f458b49a4cf6433fdb799f260bce8aeae8954303
+oid sha256:ed7784759803741aa1655eff3936e90268b33ac796d763adef64d4c1a5f1fba5
 size 2341522936

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.7639393329152e+16,
+    "train_loss": 0.24209010950724283,
+    "train_runtime": 903.6834,
+    "train_samples": 106,
+    "train_samples_per_second": 0.415,
+    "train_steps_per_second": 0.415
+}

runs/Feb21_17-21-17_autodl-container-1b3442a671-84b9ecdf/events.out.tfevents.1740129689.autodl-container-1b3442a671-84b9ecdf.63014.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d7ea5a604b248bc32eb74cea3d876d8cd95f83e951ccf572286c517654d6b2
-size 12373
+oid sha256:a20e666ea8d80f8a27705e49cf3c496ee719c36e9ef9beb40d5180bc4ee313ff
+size 14204

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.7639393329152e+16,
+    "train_loss": 0.24209010950724283,
+    "train_runtime": 903.6834,
+    "train_samples": 106,
+    "train_samples_per_second": 0.415,
+    "train_steps_per_second": 0.415
+}

trainer_state.json

@@ -0,0 +1,301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 6.505666255950928,
+      "learning_rate": 1e-05,
+      "loss": 0.9381,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 11.050951957702637,
+      "learning_rate": 1e-05,
+      "loss": 0.8876,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.7279372215271,
+      "learning_rate": 1e-05,
+      "loss": 0.7756,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 6.32816743850708,
+      "learning_rate": 1e-05,
+      "loss": 0.6711,
+      "step": 40
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 4.042453765869141,
+      "learning_rate": 1e-05,
+      "loss": 0.5652,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.4663736820220947,
+      "learning_rate": 1e-05,
+      "loss": 0.4867,
+      "step": 60
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 3.2002265453338623,
+      "learning_rate": 1e-05,
+      "loss": 0.362,
+      "step": 70
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 3.3230040073394775,
+      "learning_rate": 1e-05,
+      "loss": 0.3476,
+      "step": 80
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.9953352212905884,
+      "learning_rate": 1e-05,
+      "loss": 0.2338,
+      "step": 90
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.7286195755004883,
+      "learning_rate": 1e-05,
+      "loss": 0.1643,
+      "step": 100
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.5366934537887573,
+      "learning_rate": 1e-05,
+      "loss": 0.2192,
+      "step": 110
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.9483023881912231,
+      "learning_rate": 1e-05,
+      "loss": 0.1741,
+      "step": 120
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 2.4931719303131104,
+      "learning_rate": 1e-05,
+      "loss": 0.1204,
+      "step": 130
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 2.0894625186920166,
+      "learning_rate": 1e-05,
+      "loss": 0.1849,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.3106706142425537,
+      "learning_rate": 1e-05,
+      "loss": 0.1583,
+      "step": 150
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 2.315725803375244,
+      "learning_rate": 1e-05,
+      "loss": 0.1814,
+      "step": 160
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.4159507751464844,
+      "learning_rate": 1e-05,
+      "loss": 0.1314,
+      "step": 170
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.2906599044799805,
+      "learning_rate": 1e-05,
+      "loss": 0.1364,
+      "step": 180
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.7275636196136475,
+      "learning_rate": 1e-05,
+      "loss": 0.1572,
+      "step": 190
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.793707013130188,
+      "learning_rate": 1e-05,
+      "loss": 0.1272,
+      "step": 200
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.650312900543213,
+      "learning_rate": 1e-05,
+      "loss": 0.1225,
+      "step": 210
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.925577163696289,
+      "learning_rate": 1e-05,
+      "loss": 0.1022,
+      "step": 220
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 1.8806871175765991,
+      "learning_rate": 1e-05,
+      "loss": 0.1671,
+      "step": 230
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.2901535034179688,
+      "learning_rate": 1e-05,
+      "loss": 0.1346,
+      "step": 240
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 2.187326431274414,
+      "learning_rate": 1e-05,
+      "loss": 0.1497,
+      "step": 250
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 1.8143903017044067,
+      "learning_rate": 1e-05,
+      "loss": 0.1025,
+      "step": 260
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.7334603071212769,
+      "learning_rate": 1e-05,
+      "loss": 0.1105,
+      "step": 270
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 1.70522141456604,
+      "learning_rate": 1e-05,
+      "loss": 0.1242,
+      "step": 280
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 1.2355444431304932,
+      "learning_rate": 1e-05,
+      "loss": 0.0826,
+      "step": 290
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.6104403734207153,
+      "learning_rate": 1e-05,
+      "loss": 0.1302,
+      "step": 300
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 1.4280835390090942,
+      "learning_rate": 1e-05,
+      "loss": 0.0951,
+      "step": 310
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 1.7377476692199707,
+      "learning_rate": 1e-05,
+      "loss": 0.0922,
+      "step": 320
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.8996360301971436,
+      "learning_rate": 1e-05,
+      "loss": 0.152,
+      "step": 330
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 1.5604692697525024,
+      "learning_rate": 1e-05,
+      "loss": 0.1184,
+      "step": 340
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 1.5387630462646484,
+      "learning_rate": 1e-05,
+      "loss": 0.1138,
+      "step": 350
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.6977715492248535,
+      "learning_rate": 1e-05,
+      "loss": 0.0892,
+      "step": 360
+    },
+    {
+      "epoch": 4.933333333333334,
+      "grad_norm": 1.4408897161483765,
+      "learning_rate": 1e-05,
+      "loss": 0.1192,
+      "step": 370
+    },
+    {
+      "epoch": 5.0,
+      "step": 375,
+      "total_flos": 1.7639393329152e+16,
+      "train_loss": 0.24209010950724283,
+      "train_runtime": 903.6834,
+      "train_samples_per_second": 0.415,
+      "train_steps_per_second": 0.415
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.7639393329152e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}