Model save

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: microsoft/phi-2
+model-index:
+- name: phi-2-disticoder-v0.1
+  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. -->
+
+# phi-2-disticoder-v0.1
+
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the generator 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: 2.5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 100
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.84,
+    "train_loss": 0.901345341205597,
+    "train_runtime": 5180.5926,
+    "train_samples_per_second": 0.618,
+    "train_steps_per_second": 0.019
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.84,
+    "train_loss": 0.901345341205597,
+    "train_runtime": 5180.5926,
+    "train_samples_per_second": 0.618,
+    "train_steps_per_second": 0.019
+}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8433179723502304,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5e-06,
+      "loss": 0.8914,
+      "step": 1
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9438,
+      "step": 10
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4246157759823855e-05,
+      "loss": 0.9396,
+      "step": 20
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2075555538987227e-05,
+      "loss": 0.9303,
+      "step": 30
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.9161,
+      "step": 40
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.4670602220836633e-05,
+      "loss": 0.8964,
+      "step": 50
+    },
+    {
+      "epoch": 0.92,
+      "eval_runtime": 88.7397,
+      "eval_samples_per_second": 2.152,
+      "eval_steps_per_second": 0.27,
+      "step": 50
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.0329397779163372e-05,
+      "loss": 0.8927,
+      "step": 60
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.250000000000003e-06,
+      "loss": 0.8824,
+      "step": 70
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.9244444610127764e-06,
+      "loss": 0.871,
+      "step": 80
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.538422401761461e-07,
+      "loss": 0.8656,
+      "step": 90
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.0,
+      "loss": 0.8807,
+      "step": 100
+    },
+    {
+      "epoch": 1.84,
+      "eval_runtime": 88.6458,
+      "eval_samples_per_second": 2.155,
+      "eval_steps_per_second": 0.271,
+      "step": 100
+    },
+    {
+      "epoch": 1.84,
+      "step": 100,
+      "total_flos": 1.0437779703988224e+17,
+      "train_loss": 0.901345341205597,
+      "train_runtime": 5180.5926,
+      "train_samples_per_second": 0.618,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 1.0437779703988224e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}