Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: peft
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: llama3-8b-kasa-summarization-11-v1
+  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. -->
+
+# llama3-8b-kasa-summarization-11-v1
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4800
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 256
+- total_eval_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.9163        | 0.9955 | 111  | 2.4800          |
+
+
+### Framework versions
+
+- PEFT 0.13.1.dev0
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405737692455a8e6f1049088975904b70b0da7275b4250444e1cfd7f6fb81cf8
+oid sha256:97ab0f66cc1b155a4002a2495d0fb09bef3fd588113ed315db508dee9418798f
 size 4216432272

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9955156950672646,
+    "total_flos": 6.55433093364056e+17,
+    "train_loss": 2.0809848867021166,
+    "train_runtime": 573.6215,
+    "train_samples": 129221,
+    "train_samples_per_second": 49.595,
+    "train_steps_per_second": 0.194
+}

runs/Nov19_01-21-13_fair-door-smiles-fin-02/events.out.tfevents.1731980559.fair-door-smiles-fin-02.53076.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047400a831fe5dd686477f0dcfa8b0aa760a428807108b8a5bb8abe600cd45d2
-size 9951
+oid sha256:fe41d69dbff4f2c52cb7646fd97279edd1c9a38bd53761cf699d2941fa11970b
+size 10979

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9955156950672646,
+    "total_flos": 6.55433093364056e+17,
+    "train_loss": 2.0809848867021166,
+    "train_runtime": 573.6215,
+    "train_samples": 129221,
+    "train_samples_per_second": 49.595,
+    "train_steps_per_second": 0.194
+}

trainer_state.json

@@ -0,0 +1,211 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9955156950672646,
+  "eval_steps": 500,
+  "global_step": 111,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008968609865470852,
+      "grad_norm": 2.8099851608276367,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.746,
+      "step": 1
+    },
+    {
+      "epoch": 0.04484304932735426,
+      "grad_norm": 2.2227981090545654,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 2.7561,
+      "step": 5
+    },
+    {
+      "epoch": 0.08968609865470852,
+      "grad_norm": 0.7163326740264893,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 2.6626,
+      "step": 10
+    },
+    {
+      "epoch": 0.13452914798206278,
+      "grad_norm": 0.7108013033866882,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 2.5067,
+      "step": 15
+    },
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 0.7055566310882568,
+      "learning_rate": 0.00019679487013963564,
+      "loss": 2.3196,
+      "step": 20
+    },
+    {
+      "epoch": 0.2242152466367713,
+      "grad_norm": 0.5784558057785034,
+      "learning_rate": 0.00019161084574320696,
+      "loss": 2.1977,
+      "step": 25
+    },
+    {
+      "epoch": 0.26905829596412556,
+      "grad_norm": 0.4505833089351654,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 2.117,
+      "step": 30
+    },
+    {
+      "epoch": 0.31390134529147984,
+      "grad_norm": 0.3613595962524414,
+      "learning_rate": 0.0001745264449675755,
+      "loss": 2.0559,
+      "step": 35
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.2955701947212219,
+      "learning_rate": 0.00016305526670845226,
+      "loss": 2.0269,
+      "step": 40
+    },
+    {
+      "epoch": 0.40358744394618834,
+      "grad_norm": 0.2612513601779938,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9972,
+      "step": 45
+    },
+    {
+      "epoch": 0.4484304932735426,
+      "grad_norm": 0.257419228553772,
+      "learning_rate": 0.00013568862215918717,
+      "loss": 1.9858,
+      "step": 50
+    },
+    {
+      "epoch": 0.49327354260089684,
+      "grad_norm": 0.244528129696846,
+      "learning_rate": 0.00012048066680651908,
+      "loss": 1.9762,
+      "step": 55
+    },
+    {
+      "epoch": 0.5381165919282511,
+      "grad_norm": 0.25337350368499756,
+      "learning_rate": 0.00010475819158237425,
+      "loss": 1.9581,
+      "step": 60
+    },
+    {
+      "epoch": 0.5829596412556054,
+      "grad_norm": 0.2533525824546814,
+      "learning_rate": 8.891618000989891e-05,
+      "loss": 1.9428,
+      "step": 65
+    },
+    {
+      "epoch": 0.6278026905829597,
+      "grad_norm": 0.23752403259277344,
+      "learning_rate": 7.335261863099651e-05,
+      "loss": 1.9451,
+      "step": 70
+    },
+    {
+      "epoch": 0.672645739910314,
+      "grad_norm": 0.24802494049072266,
+      "learning_rate": 5.845849869981137e-05,
+      "loss": 1.9307,
+      "step": 75
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.26005855202674866,
+      "learning_rate": 4.4607993613388976e-05,
+      "loss": 1.9209,
+      "step": 80
+    },
+    {
+      "epoch": 0.7623318385650224,
+      "grad_norm": 0.2599089741706848,
+      "learning_rate": 3.21490588442868e-05,
+      "loss": 1.9176,
+      "step": 85
+    },
+    {
+      "epoch": 0.8071748878923767,
+      "grad_norm": 0.2820660173892975,
+      "learning_rate": 2.139469052572127e-05,
+      "loss": 1.924,
+      "step": 90
+    },
+    {
+      "epoch": 0.852017937219731,
+      "grad_norm": 0.233997642993927,
+      "learning_rate": 1.2615062293021507e-05,
+      "loss": 1.9249,
+      "step": 95
+    },
+    {
+      "epoch": 0.8968609865470852,
+      "grad_norm": 0.3044739067554474,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.9218,
+      "step": 100
+    },
+    {
+      "epoch": 0.9417040358744395,
+      "grad_norm": 0.2602479159832001,
+      "learning_rate": 1.8071302737293295e-06,
+      "loss": 1.9181,
+      "step": 105
+    },
+    {
+      "epoch": 0.9865470852017937,
+      "grad_norm": 0.26399335265159607,
+      "learning_rate": 5.0345761681491746e-08,
+      "loss": 1.9163,
+      "step": 110
+    },
+    {
+      "epoch": 0.9955156950672646,
+      "eval_loss": 2.4799907207489014,
+      "eval_runtime": 0.8112,
+      "eval_samples_per_second": 25.886,
+      "eval_steps_per_second": 1.233,
+      "step": 111
+    },
+    {
+      "epoch": 0.9955156950672646,
+      "step": 111,
+      "total_flos": 6.55433093364056e+17,
+      "train_loss": 2.0809848867021166,
+      "train_runtime": 573.6215,
+      "train_samples_per_second": 49.595,
+      "train_steps_per_second": 0.194
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 111,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 6.55433093364056e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}