Model save

README.md

@@ -0,0 +1,69 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- generator
+library_name: peft
+license: apache-2.0
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-qlora
+  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. -->
+
+# zephyr-7b-sft-qlora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0512
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0419        | 1.0   | 17   | 1.0336          |
+| 0.8637        | 2.0   | 34   | 1.0328          |
+| 0.8198        | 3.0   | 51   | 1.0512          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.5859605640708096e+16,
+    "train_loss": 0.9273478938084022,
+    "train_runtime": 35264.3392,
+    "train_samples": 207,
+    "train_samples_per_second": 0.012,
+    "train_steps_per_second": 0.001
+}

runs/Aug08_16-38-54_938RL43/events.out.tfevents.1723128033.938RL43.6045.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5fcd454259e2a772841de9523e136cb7ac51b564ecfb48062eba77f573df4e
-size 9286
+oid sha256:bda1f7de2168687781351cfdf4b5dae16ff1cd3117e5f8e9cada823b0fadde49
+size 9900

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.5859605640708096e+16,
+    "train_loss": 0.9273478938084022,
+    "train_runtime": 35264.3392,
+    "train_samples": 207,
+    "train_samples_per_second": 0.012,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,143 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 51,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.41075530648231506,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.0764,
+      "step": 1
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.31586405634880066,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.1671,
+      "step": 5
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.2748248875141144,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.0427,
+      "step": 10
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.26047566533088684,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0419,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0335692167282104,
+      "eval_runtime": 11418.6735,
+      "eval_samples_per_second": 1.344,
+      "eval_steps_per_second": 0.168,
+      "step": 17
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.24954748153686523,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 0.8987,
+      "step": 20
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.26379314064979553,
+      "learning_rate": 0.00012419218955996676,
+      "loss": 0.91,
+      "step": 25
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.29261425137519836,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.8637,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0328121185302734,
+      "eval_runtime": 11368.8822,
+      "eval_samples_per_second": 1.35,
+      "eval_steps_per_second": 0.169,
+      "step": 34
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.44186949729919434,
+      "learning_rate": 5.616288532109225e-05,
+      "loss": 0.9475,
+      "step": 35
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.3536168038845062,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 0.816,
+      "step": 40
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.37321916222572327,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.815,
+      "step": 45
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.34859296679496765,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 0.8198,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0511847734451294,
+      "eval_runtime": 11370.1779,
+      "eval_samples_per_second": 1.35,
+      "eval_steps_per_second": 0.169,
+      "step": 51
+    },
+    {
+      "epoch": 3.0,
+      "step": 51,
+      "total_flos": 3.5859605640708096e+16,
+      "train_loss": 0.9273478938084022,
+      "train_runtime": 35264.3392,
+      "train_samples_per_second": 0.012,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 51,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5859605640708096e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}