End of training

README.md

@@ -0,0 +1,57 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: transformers
+model_name: mistral-7b-instruct-v0.3-qlora-10k-ep1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for mistral-7b-instruct-v0.3-qlora-10k-ep1
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
+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="mbCrypto/mistral-7b-instruct-v0.3-qlora-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: 2.5.0
+- 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_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cee9b52be400db6bec4749d262c980dc354d812edfec7128ad7e69ba651e6d
+size 704703384

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9971671388101983,
+    "total_flos": 1.2612738615135437e+17,
+    "train_loss": 0.5921206095001914,
+    "train_runtime": 11815.8602,
+    "train_samples": 10000,
+    "train_samples_per_second": 0.239,
+    "train_steps_per_second": 0.015
+}

runs/Jun02_16-20-29_ubuntu/events.out.tfevents.1748874496.ubuntu.3276507.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dc57c42b93447a46dc363f646beb4d8c99c01d985e5dd9820f5790a598913d
+size 13156

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9971671388101983,
+    "total_flos": 1.2612738615135437e+17,
+    "train_loss": 0.5921206095001914,
+    "train_runtime": 11815.8602,
+    "train_samples": 10000,
+    "train_samples_per_second": 0.239,
+    "train_steps_per_second": 0.015
+}

trainer_state.json

@@ -0,0 +1,287 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9971671388101983,
+  "eval_steps": 500,
+  "global_step": 176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.028328611898016998,
+      "grad_norm": 14.723566055297852,
+      "learning_rate": 0.0002,
+      "loss": 0.9121,
+      "step": 5
+    },
+    {
+      "epoch": 0.056657223796033995,
+      "grad_norm": 5.200648307800293,
+      "learning_rate": 0.0002,
+      "loss": 0.8028,
+      "step": 10
+    },
+    {
+      "epoch": 0.08498583569405099,
+      "grad_norm": 6.881194114685059,
+      "learning_rate": 0.0002,
+      "loss": 0.7291,
+      "step": 15
+    },
+    {
+      "epoch": 0.11331444759206799,
+      "grad_norm": 3.192544460296631,
+      "learning_rate": 0.0002,
+      "loss": 0.6898,
+      "step": 20
+    },
+    {
+      "epoch": 0.141643059490085,
+      "grad_norm": 2.817613363265991,
+      "learning_rate": 0.0002,
+      "loss": 0.6584,
+      "step": 25
+    },
+    {
+      "epoch": 0.16997167138810199,
+      "grad_norm": 2.6520678997039795,
+      "learning_rate": 0.0002,
+      "loss": 0.6549,
+      "step": 30
+    },
+    {
+      "epoch": 0.19830028328611898,
+      "grad_norm": 3.3515636920928955,
+      "learning_rate": 0.0002,
+      "loss": 0.6501,
+      "step": 35
+    },
+    {
+      "epoch": 0.22662889518413598,
+      "grad_norm": 2.6749367713928223,
+      "learning_rate": 0.0002,
+      "loss": 0.6405,
+      "step": 40
+    },
+    {
+      "epoch": 0.254957507082153,
+      "grad_norm": 2.8483076095581055,
+      "learning_rate": 0.0002,
+      "loss": 0.6229,
+      "step": 45
+    },
+    {
+      "epoch": 0.28328611898017,
+      "grad_norm": 2.4169209003448486,
+      "learning_rate": 0.0002,
+      "loss": 0.603,
+      "step": 50
+    },
+    {
+      "epoch": 0.311614730878187,
+      "grad_norm": 3.861983299255371,
+      "learning_rate": 0.0002,
+      "loss": 0.6231,
+      "step": 55
+    },
+    {
+      "epoch": 0.33994334277620397,
+      "grad_norm": 2.65099835395813,
+      "learning_rate": 0.0002,
+      "loss": 0.6075,
+      "step": 60
+    },
+    {
+      "epoch": 0.36827195467422097,
+      "grad_norm": 4.709205627441406,
+      "learning_rate": 0.0002,
+      "loss": 0.5982,
+      "step": 65
+    },
+    {
+      "epoch": 0.39660056657223797,
+      "grad_norm": 2.094581365585327,
+      "learning_rate": 0.0002,
+      "loss": 0.5945,
+      "step": 70
+    },
+    {
+      "epoch": 0.42492917847025496,
+      "grad_norm": 3.4592018127441406,
+      "learning_rate": 0.0002,
+      "loss": 0.5706,
+      "step": 75
+    },
+    {
+      "epoch": 0.45325779036827196,
+      "grad_norm": 5.805232524871826,
+      "learning_rate": 0.0002,
+      "loss": 0.5794,
+      "step": 80
+    },
+    {
+      "epoch": 0.48158640226628896,
+      "grad_norm": 1.982815146446228,
+      "learning_rate": 0.0002,
+      "loss": 0.5505,
+      "step": 85
+    },
+    {
+      "epoch": 0.509915014164306,
+      "grad_norm": 9.649585723876953,
+      "learning_rate": 0.0002,
+      "loss": 0.5712,
+      "step": 90
+    },
+    {
+      "epoch": 0.5382436260623229,
+      "grad_norm": 2.012679100036621,
+      "learning_rate": 0.0002,
+      "loss": 0.5762,
+      "step": 95
+    },
+    {
+      "epoch": 0.56657223796034,
+      "grad_norm": 2.317387342453003,
+      "learning_rate": 0.0002,
+      "loss": 0.5652,
+      "step": 100
+    },
+    {
+      "epoch": 0.5949008498583569,
+      "grad_norm": 2.179086685180664,
+      "learning_rate": 0.0002,
+      "loss": 0.5469,
+      "step": 105
+    },
+    {
+      "epoch": 0.623229461756374,
+      "grad_norm": 2.0399320125579834,
+      "learning_rate": 0.0002,
+      "loss": 0.5443,
+      "step": 110
+    },
+    {
+      "epoch": 0.6515580736543909,
+      "grad_norm": 2.095395565032959,
+      "learning_rate": 0.0002,
+      "loss": 0.5498,
+      "step": 115
+    },
+    {
+      "epoch": 0.6798866855524079,
+      "grad_norm": 3.5913994312286377,
+      "learning_rate": 0.0002,
+      "loss": 0.5338,
+      "step": 120
+    },
+    {
+      "epoch": 0.7082152974504249,
+      "grad_norm": 3.3710949420928955,
+      "learning_rate": 0.0002,
+      "loss": 0.5518,
+      "step": 125
+    },
+    {
+      "epoch": 0.7365439093484419,
+      "grad_norm": 2.205059051513672,
+      "learning_rate": 0.0002,
+      "loss": 0.5366,
+      "step": 130
+    },
+    {
+      "epoch": 0.7648725212464589,
+      "grad_norm": 2.1114184856414795,
+      "learning_rate": 0.0002,
+      "loss": 0.5266,
+      "step": 135
+    },
+    {
+      "epoch": 0.7932011331444759,
+      "grad_norm": 2.238480567932129,
+      "learning_rate": 0.0002,
+      "loss": 0.506,
+      "step": 140
+    },
+    {
+      "epoch": 0.8215297450424929,
+      "grad_norm": 2.1656649112701416,
+      "learning_rate": 0.0002,
+      "loss": 0.5317,
+      "step": 145
+    },
+    {
+      "epoch": 0.8498583569405099,
+      "grad_norm": 2.247891664505005,
+      "learning_rate": 0.0002,
+      "loss": 0.5276,
+      "step": 150
+    },
+    {
+      "epoch": 0.8781869688385269,
+      "grad_norm": 2.897693634033203,
+      "learning_rate": 0.0002,
+      "loss": 0.5128,
+      "step": 155
+    },
+    {
+      "epoch": 0.9065155807365439,
+      "grad_norm": 1.935969352722168,
+      "learning_rate": 0.0002,
+      "loss": 0.5264,
+      "step": 160
+    },
+    {
+      "epoch": 0.9348441926345609,
+      "grad_norm": 1.9943110942840576,
+      "learning_rate": 0.0002,
+      "loss": 0.5211,
+      "step": 165
+    },
+    {
+      "epoch": 0.9631728045325779,
+      "grad_norm": 2.2417781352996826,
+      "learning_rate": 0.0002,
+      "loss": 0.5097,
+      "step": 170
+    },
+    {
+      "epoch": 0.9915014164305949,
+      "grad_norm": 2.086829662322998,
+      "learning_rate": 0.0002,
+      "loss": 0.5136,
+      "step": 175
+    },
+    {
+      "epoch": 0.9971671388101983,
+      "step": 176,
+      "total_flos": 1.2612738615135437e+17,
+      "train_loss": 0.5921206095001914,
+      "train_runtime": 11815.8602,
+      "train_samples_per_second": 0.239,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 176,
+  "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": 1.2612738615135437e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7382f6a580b39e4f2a6568111ca2522bc9e882a7227773b5bfe377c4c60fdd0a
+size 5624