End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 35
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.13.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:449b5e107283a12b3a96cbd3633cda4411b1f14cda1f293063694d0f37de3053
+size 1871769944

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.01,
+    "total_flos": 908815265390592.0,
+    "train_loss": 28.59544857570103,
+    "train_runtime": 251.2453,
+    "train_samples_per_second": 0.557,
+    "train_steps_per_second": 0.139
+}

runs/Jan30_16-27-29_4722e29c37b2/events.out.tfevents.1706632049.4722e29c37b2.3889.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd2d0e8091154f662e3f6dc69df6138357e892a5d60513ede474dc1f389c43a
+size 10320

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.01,
+    "total_flos": 908815265390592.0,
+    "train_loss": 28.59544857570103,
+    "train_runtime": 251.2453,
+    "train_samples_per_second": 0.557,
+    "train_steps_per_second": 0.139
+}

trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.007607041947402739,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 27.7055,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 29.3076,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.6913,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.0342,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.0921,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.4638,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.3358,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 29.0762,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.4791,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 29.1039,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.1263,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.1885,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 29.316,
+      "step": 13
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.5523,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.4897,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.97,
+      "step": 16
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.7696,
+      "step": 17
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.4166,
+      "step": 18
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.3972,
+      "step": 19
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 29.4283,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 29.0497,
+      "step": 21
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 28.2659,
+      "step": 22
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 27.0353,
+      "step": 23
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 28.461,
+      "step": 24
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 28.1895,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 28.1563,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 29.384,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 28.0906,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 29.2357,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001,
+      "loss": 29.1711,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 28.4014,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 28.7946,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001878787878787879,
+      "loss": 28.5782,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 28.8898,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 29.1936,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "step": 35,
+      "total_flos": 908815265390592.0,
+      "train_loss": 28.59544857570103,
+      "train_runtime": 251.2453,
+      "train_samples_per_second": 0.557,
+      "train_steps_per_second": 0.139
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 35,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 908815265390592.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb109b7736e0002d082622abaa240edc5ac708e4f60563848e36d4a5c720067b
+size 4536