End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.3
+datasets:
+- generator
+model-index:
+- name: Mistral-7B-v0.3-sft-lora_sr_ift_5ep
+  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-7B-v0.3-sft-lora_sr_ift_5ep
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2612
+
+## 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: 5.5e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4594        | 1.0   | 137  | 1.3172          |
+| 1.3294        | 2.0   | 274  | 1.2719          |
+| 1.3027        | 3.0   | 411  | 1.2624          |
+| 1.2966        | 4.0   | 548  | 1.2613          |
+| 1.2958        | 5.0   | 685  | 1.2612          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-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": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "lm_head",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_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 sha256:7ca05ca5e94e23057464d7185d22d58ac5d28504371281967cc51e289fa2e87f
+size 608759824

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4.90039991599104e+17,
+    "train_loss": 1.3367735479869982,
+    "train_runtime": 3555.8752,
+    "train_samples_per_second": 1.54,
+    "train_steps_per_second": 0.193
+}

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 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4.90039991599104e+17,
+    "train_loss": 1.3367735479869982,
+    "train_runtime": 3555.8752,
+    "train_samples_per_second": 1.54,
+    "train_steps_per_second": 0.193
+}

trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 685,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.310546875,
+      "learning_rate": 5.172536900426634e-06,
+      "loss": 1.4594,
+      "step": 137
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.3171552419662476,
+      "eval_runtime": 10.7582,
+      "eval_samples_per_second": 5.391,
+      "eval_steps_per_second": 0.744,
+      "step": 137
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.28515625,
+      "learning_rate": 3.860425138978212e-06,
+      "loss": 1.3294,
+      "step": 274
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2718597650527954,
+      "eval_runtime": 10.7485,
+      "eval_samples_per_second": 5.396,
+      "eval_steps_per_second": 0.744,
+      "step": 274
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.302734375,
+      "learning_rate": 2.0789845293039968e-06,
+      "loss": 1.3027,
+      "step": 411
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2623664140701294,
+      "eval_runtime": 10.7691,
+      "eval_samples_per_second": 5.386,
+      "eval_steps_per_second": 0.743,
+      "step": 411
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.27734375,
+      "learning_rate": 5.811532391136983e-07,
+      "loss": 1.2966,
+      "step": 548
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2613033056259155,
+      "eval_runtime": 10.7617,
+      "eval_samples_per_second": 5.39,
+      "eval_steps_per_second": 0.743,
+      "step": 548
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.25,
+      "learning_rate": 0.0,
+      "loss": 1.2958,
+      "step": 685
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.2612134218215942,
+      "eval_runtime": 10.7622,
+      "eval_samples_per_second": 5.389,
+      "eval_steps_per_second": 0.743,
+      "step": 685
+    },
+    {
+      "epoch": 5.0,
+      "step": 685,
+      "total_flos": 4.90039991599104e+17,
+      "train_loss": 1.3367735479869982,
+      "train_runtime": 3555.8752,
+      "train_samples_per_second": 1.54,
+      "train_steps_per_second": 0.193
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 685,
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.90039991599104e+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 sha256:8724a66e9b98ed4a0c2c65f8405d6a450b81ca14a7ad383c4d3e22e09eeee233
+size 5176