Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: Phi-3-mini-4k-instruct
+model-index:
+- name: Phi-3-mini-4k-instruct-finetuned
+  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-3-mini-4k-instruct-finetuned
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 12.3823
+
+## 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: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.36.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6aa8472d1a016e33123c15a5c2676aa431cc88fe948e5f3305dcbf9253d1803
+oid sha256:e68398d8259a2c50c62f4e7e4cb295b2f4ba222a83f4df8277ad90ff601095be
 size 4721808

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 12.382317543029785,
+    "eval_runtime": 3.6879,
+    "eval_samples": 145,
+    "eval_samples_per_second": 39.318,
+    "eval_steps_per_second": 19.795,
+    "total_flos": 1968746702340096.0,
+    "train_loss": 12.81857436607624,
+    "train_runtime": 41.5298,
+    "train_samples_per_second": 13.942,
+    "train_steps_per_second": 6.983
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 12.382317543029785,
+    "eval_runtime": 3.6879,
+    "eval_samples": 145,
+    "eval_samples_per_second": 39.318,
+    "eval_steps_per_second": 19.795
+}

tokenizer_config.json

@@ -122,7 +122,7 @@
   "legacy": false,
   "model_max_length": 2048,
   "pad_token": "<unk>",
-  "padding_side": "right",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1968746702340096.0,
+    "train_loss": 12.81857436607624,
+    "train_runtime": 41.5298,
+    "train_samples_per_second": 13.942,
+    "train_steps_per_second": 6.983
+}

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.724137931034483e-06,
+      "loss": 13.6309,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 13.5642,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.999083215558211e-06,
+      "loss": 13.3984,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.88988035667903e-06,
+      "loss": 13.3684,
+      "step": 80
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.606455184041623e-06,
+      "loss": 12.9849,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.169469396971739e-06,
+      "loss": 12.9424,
+      "step": 120
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.6107792658847597e-06,
+      "loss": 12.7222,
+      "step": 140
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.971113309695796e-06,
+      "loss": 12.615,
+      "step": 160
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.2971031861814225e-06,
+      "loss": 12.4667,
+      "step": 180
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.6378842434300746e-06,
+      "loss": 12.3938,
+      "step": 200
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.041513552231265e-06,
+      "loss": 12.3768,
+      "step": 220
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.51466544896021e-07,
+      "loss": 12.3142,
+      "step": 240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0346765559094566e-07,
+      "loss": 12.4309,
+      "step": 260
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.2886008552983064e-08,
+      "loss": 12.4571,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "step": 290,
+      "total_flos": 1968746702340096.0,
+      "train_loss": 12.81857436607624,
+      "train_runtime": 41.5298,
+      "train_samples_per_second": 13.942,
+      "train_steps_per_second": 6.983
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1968746702340096.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}