End of training

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mnist_test.csv filter=lfs diff=lfs merge=lfs -text
+mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+base_model: facebook/opt-350m
+library_name: peft
+license: other
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: sample_data
+  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. -->
+
+# sample_data
+
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.6426
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.9032        | 0.4444 | 1    | 5.1705          |
+| 4.8617        | 0.8889 | 2    | 4.8856          |
+| 4.6261        | 1.3333 | 3    | 4.7009          |
+| 4.4803        | 1.7778 | 4    | 4.6426          |
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.0
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-350m",
+  "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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_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:ea13a75c80f71ea17f2498ce0cb3b3c9646e7bedbe8e348e0bc3847dc74629e4
+size 9457432

anscombe.json

@@ -0,0 +1,49 @@
+[
+  {"Series":"I", "X":10.0, "Y":8.04},
+  {"Series":"I", "X":8.0, "Y":6.95},
+  {"Series":"I", "X":13.0, "Y":7.58},
+  {"Series":"I", "X":9.0, "Y":8.81},
+  {"Series":"I", "X":11.0, "Y":8.33},
+  {"Series":"I", "X":14.0, "Y":9.96},
+  {"Series":"I", "X":6.0, "Y":7.24},
+  {"Series":"I", "X":4.0, "Y":4.26},
+  {"Series":"I", "X":12.0, "Y":10.84},
+  {"Series":"I", "X":7.0, "Y":4.81},
+  {"Series":"I", "X":5.0, "Y":5.68},
+
+  {"Series":"II", "X":10.0, "Y":9.14},
+  {"Series":"II", "X":8.0, "Y":8.14},
+  {"Series":"II", "X":13.0, "Y":8.74},
+  {"Series":"II", "X":9.0, "Y":8.77},
+  {"Series":"II", "X":11.0, "Y":9.26},
+  {"Series":"II", "X":14.0, "Y":8.10},
+  {"Series":"II", "X":6.0, "Y":6.13},
+  {"Series":"II", "X":4.0, "Y":3.10},
+  {"Series":"II", "X":12.0, "Y":9.13},
+  {"Series":"II", "X":7.0, "Y":7.26},
+  {"Series":"II", "X":5.0, "Y":4.74},
+
+  {"Series":"III", "X":10.0, "Y":7.46},
+  {"Series":"III", "X":8.0, "Y":6.77},
+  {"Series":"III", "X":13.0, "Y":12.74},
+  {"Series":"III", "X":9.0, "Y":7.11},
+  {"Series":"III", "X":11.0, "Y":7.81},
+  {"Series":"III", "X":14.0, "Y":8.84},
+  {"Series":"III", "X":6.0, "Y":6.08},
+  {"Series":"III", "X":4.0, "Y":5.39},
+  {"Series":"III", "X":12.0, "Y":8.15},
+  {"Series":"III", "X":7.0, "Y":6.42},
+  {"Series":"III", "X":5.0, "Y":5.73},
+
+  {"Series":"IV", "X":8.0, "Y":6.58},
+  {"Series":"IV", "X":8.0, "Y":5.76},
+  {"Series":"IV", "X":8.0, "Y":7.71},
+  {"Series":"IV", "X":8.0, "Y":8.84},
+  {"Series":"IV", "X":8.0, "Y":8.47},
+  {"Series":"IV", "X":8.0, "Y":7.04},
+  {"Series":"IV", "X":8.0, "Y":5.25},
+  {"Series":"IV", "X":19.0, "Y":12.50},
+  {"Series":"IV", "X":8.0, "Y":5.56},
+  {"Series":"IV", "X":8.0, "Y":7.91},
+  {"Series":"IV", "X":8.0, "Y":6.89}
+]

mnist_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c292478d94ec3a01461bdfa82eb0885d262eb09e615679b2d69dedb6ad09e7
+size 18289443

mnist_train_small.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef64781aa03180f4f5ce504314f058f5d0227277df86060473d973cf43b033e
+size 36523880

runs/Sep26_06-59-12_dea55a8a373f/events.out.tfevents.1727334054.dea55a8a373f.227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00fa0d602c715347e9ad5803106a49f9b65561bef06172c9c10482661003748
+size 5563

runs/Sep26_06-59-12_dea55a8a373f/events.out.tfevents.1727335277.dea55a8a373f.227.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2076c78d9d1dd446a581ff997b190d110f11bc2756464e25acbc46456f3474a3
+size 7596

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe702fdcb635ec38f9bb08c33f6b890d8af8e0b6ff864a469a824d5b3948d558
+size 5496