End of training

README.md

@@ -0,0 +1,64 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral_sequence_classification_0.001
+  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. -->
+
+# mistral_sequence_classification_0.001
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2964
+- Pearson: 0.3398
+
+## 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: 0.001
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Pearson |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| No log        | 1.0   | 206  | 3.4169          | 0.3066  |
+| No log        | 2.0   | 412  | 2.2890          | 0.2229  |
+| 2.9323        | 3.0   | 618  | 1.6690          | 0.3019  |
+| 2.9323        | 4.0   | 824  | 1.4150          | 0.3351  |
+| 1.6676        | 5.0   | 1030 | 1.2964          | 0.3398  |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.45.2
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- Datasets 3.2.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd162a13e91dbd4b30a99626c7a7e197f9bd310efd2b14160af867f060ff67d
+size 218220600

runs/Feb06_12-53-57_e38d418088f5/events.out.tfevents.1738846437.e38d418088f5.83678.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b1ff1589384f27f4466b94e173be48becbeffbeefce8c7d86f4041d58470e9
+size 8109

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

trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 1.2963534593582153,
+  "best_model_checkpoint": "mistral_sequence_classification_0.001/checkpoint-1030",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1030,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.416905641555786,
+      "eval_pearson": 0.3066219069348225,
+      "eval_runtime": 15.9256,
+      "eval_samples_per_second": 58.522,
+      "eval_steps_per_second": 7.347,
+      "step": 206
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.2889981269836426,
+      "eval_pearson": 0.22286808706607436,
+      "eval_runtime": 15.8126,
+      "eval_samples_per_second": 58.94,
+      "eval_steps_per_second": 7.399,
+      "step": 412
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 113.98001098632812,
+      "learning_rate": 0.0005145631067961165,
+      "loss": 2.9323,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.6689746379852295,
+      "eval_pearson": 0.301860245775783,
+      "eval_runtime": 15.8926,
+      "eval_samples_per_second": 58.644,
+      "eval_steps_per_second": 7.362,
+      "step": 618
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4149868488311768,
+      "eval_pearson": 0.3351186514331333,
+      "eval_runtime": 15.655,
+      "eval_samples_per_second": 59.534,
+      "eval_steps_per_second": 7.474,
+      "step": 824
+    },
+    {
+      "epoch": 4.854368932038835,
+      "grad_norm": 94.90880584716797,
+      "learning_rate": 2.912621359223301e-05,
+      "loss": 1.6676,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.2963534593582153,
+      "eval_pearson": 0.339849259267878,
+      "eval_runtime": 15.959,
+      "eval_samples_per_second": 58.4,
+      "eval_steps_per_second": 7.331,
+      "step": 1030
+    },
+    {
+      "epoch": 5.0,
+      "step": 1030,
+      "total_flos": 6.321458643082445e+16,
+      "train_loss": 2.2687227786165995,
+      "train_runtime": 1145.0052,
+      "train_samples_per_second": 28.668,
+      "train_steps_per_second": 0.9
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1030,
+  "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": 6.321458643082445e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:898257814f40225a84ebd3a06c27dc4825f015b426983c5830625df0f1d94a7b
+size 5240