Training in progress, step 20

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: petals-team/falcon-rw-1b
+model-index:
+- name: GenAI-task2-ModelC-DS
+  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. -->
+
+# GenAI-task2-ModelC-DS
+
+This model is a fine-tuned version of [petals-team/falcon-rw-1b](https://huggingface.co/petals-team/falcon-rw-1b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5320
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.7725        | 0.0196 | 20   | 1.5112          |
+| 2.3202        | 0.0393 | 40   | 1.4942          |
+| 2.2062        | 0.0589 | 60   | 1.4996          |
+| 1.7606        | 0.0785 | 80   | 1.4954          |
+| 1.9712        | 0.0982 | 100  | 1.5320          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense_4h_to_h",
+    "dense"
+  ],
+  "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:e31634348c42b6d5f5917201d8ba5b6b3e4957b51d4c2f6121b21d2172b4fd12
+size 100703344

runs/Apr28_10-55-50_eb13383a0286/events.out.tfevents.1714301776.eb13383a0286.1729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556c1e8b16a326dd7e1a4be4f292b184b68603500a72bbfa39e9daf97609fd3a
+size 8120

runs/Apr28_10-55-50_eb13383a0286/events.out.tfevents.1714302607.eb13383a0286.1729.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe39ee41d0ce31e8f129a195e13c3051702790c4fbce96d33bbd50e54523ca10
+size 5880

runs/Apr28_11-17-33_eb13383a0286/events.out.tfevents.1714303064.eb13383a0286.1729.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96728ac290d603b748e93df03e98838b0d96a7648c4d6538e322127143e88ba
+size 8120

runs/Apr28_11-54-29_eb13383a0286/events.out.tfevents.1714305286.eb13383a0286.1729.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84a055cd77331e2520f3f8f3f7a0266c25aac666c1b5d1272d9b560ffc899cd
+size 8593

runs/Apr28_12-09-52_eb13383a0286/events.out.tfevents.1714306228.eb13383a0286.1729.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d75662f9eab3d96f3dbc19ee5727eaf32c992cc94414ddbeda77a13dd7da435
+size 6353

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097770d996027ae4ea98f01a5186d367ca85f31ad1b33366fce5fd977d567fd7
+size 5048