End of training

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mixtral-8x7B-v0.1
+model-index:
+- name: Mixtral-8x7B-v0.1_case-briefs
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Mixtral-8x7B-v0.1_case-briefs
+
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0422
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9925        | 0.34  | 50   | 1.0546          |
+| 0.9873        | 0.68  | 100  | 1.0322          |
+| 0.9577        | 1.02  | 150  | 1.0260          |
+| 0.8504        | 1.36  | 200  | 1.0648          |
+| 0.9154        | 1.7   | 250  | 1.0422          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w2",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "w1",
+    "gate",
+    "w3"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3b8ebfa695c7138c070a72026b64de09161acd92f0e708883938d927625518
+size 1938079368

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.1272878646850586,
+    "eval_runtime": 15.0096,
+    "eval_samples_per_second": 17.455,
+    "eval_steps_per_second": 4.397,
+    "train_loss": 0.9311216080269846,
+    "train_runtime": 4522.2924,
+    "train_samples_per_second": 1.042,
+    "train_steps_per_second": 0.065
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.1272878646850586,
+    "eval_runtime": 15.0096,
+    "eval_samples_per_second": 17.455,
+    "eval_steps_per_second": 4.397
+}

metrics.json

@@ -0,0 +1 @@
+{"run_name": "./output", "train_runtime": 831.3165, "train_samples_per_second": 5.668, "train_steps_per_second": 0.354, "train_loss": 1.0449795049874961, "epoch": 2.0, "eval_loss": 1.1272878646850586, "eval_runtime": 15.0096, "eval_samples_per_second": 17.455, "eval_steps_per_second": 4.397}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.9311216080269846,
+    "train_runtime": 4522.2924,
+    "train_samples_per_second": 1.042,
+    "train_steps_per_second": 0.065
+}

trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.99660441426146,
+  "eval_steps": 50,
+  "global_step": 294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 5e-05,
+      "loss": 1.1147,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5e-05,
+      "loss": 1.0413,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5e-05,
+      "loss": 1.0627,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5e-05,
+      "loss": 1.0158,
+      "step": 40
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 5e-05,
+      "loss": 0.9925,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 1.054595708847046,
+      "eval_runtime": 84.2428,
+      "eval_samples_per_second": 3.11,
+      "eval_steps_per_second": 0.783,
+      "step": 50
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5e-05,
+      "loss": 1.0051,
+      "step": 60
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5e-05,
+      "loss": 1.0116,
+      "step": 70
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5e-05,
+      "loss": 1.0378,
+      "step": 80
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5e-05,
+      "loss": 1.0309,
+      "step": 90
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5e-05,
+      "loss": 0.9873,
+      "step": 100
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.0322012901306152,
+      "eval_runtime": 84.2753,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 0.783,
+      "step": 100
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5e-05,
+      "loss": 0.9827,
+      "step": 110
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5e-05,
+      "loss": 0.9831,
+      "step": 120
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5e-05,
+      "loss": 1.009,
+      "step": 130
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5e-05,
+      "loss": 1.0236,
+      "step": 140
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 5e-05,
+      "loss": 0.9577,
+      "step": 150
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.0260435342788696,
+      "eval_runtime": 84.2852,
+      "eval_samples_per_second": 3.108,
+      "eval_steps_per_second": 0.783,
+      "step": 150
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 5e-05,
+      "loss": 0.8567,
+      "step": 160
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 5e-05,
+      "loss": 0.9293,
+      "step": 170
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 5e-05,
+      "loss": 0.8656,
+      "step": 180
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5e-05,
+      "loss": 0.7937,
+      "step": 190
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5e-05,
+      "loss": 0.8504,
+      "step": 200
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 1.0647752285003662,
+      "eval_runtime": 84.2818,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 0.783,
+      "step": 200
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5e-05,
+      "loss": 0.887,
+      "step": 210
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5e-05,
+      "loss": 0.7825,
+      "step": 220
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 5e-05,
+      "loss": 0.8271,
+      "step": 230
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5e-05,
+      "loss": 0.8465,
+      "step": 240
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 5e-05,
+      "loss": 0.9154,
+      "step": 250
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 1.0422441959381104,
+      "eval_runtime": 84.2906,
+      "eval_samples_per_second": 3.108,
+      "eval_steps_per_second": 0.783,
+      "step": 250
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 5e-05,
+      "loss": 0.7803,
+      "step": 260
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 5e-05,
+      "loss": 0.8642,
+      "step": 270
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 5e-05,
+      "loss": 0.8112,
+      "step": 280
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5e-05,
+      "loss": 0.8171,
+      "step": 290
+    },
+    {
+      "epoch": 2.0,
+      "step": 294,
+      "total_flos": 4.649929554906317e+17,
+      "train_loss": 0.9311216080269846,
+      "train_runtime": 4522.2924,
+      "train_samples_per_second": 1.042,
+      "train_steps_per_second": 0.065
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 4.649929554906317e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ebda5768d277c6c95e574fa57f945d3f2496e30fad3f2b147df1b5cf514810
+size 6712