togethercomputer-RedPajama-INCITE-Chat-3B-v1

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: togethercomputer/RedPajama-INCITE-Chat-3B-v1
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [togethercomputer/RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1) on an unknown 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- training_steps: 250
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Chat-3B-v1",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "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 sha256:37021f50978999557efd91db4a4aa71ddff6b8eb4233f30d3b31aee39e8e3c14
+size 10494984

runs/Jul03_08-29-39_883343a5d06b/events.out.tfevents.1719995382.883343a5d06b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b83eda86eb2cb53ea7f4b795b15960eeb0a592038ea52a1d04e5110f08306a
+size 5616

runs/Jul03_09-11-08_883343a5d06b/events.out.tfevents.1719997870.883343a5d06b.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1f5f48c430b0bf74f2bfe79d7e704ddfc3353758dd8d24c9a19a9ffcec930a
+size 5615

runs/Jul03_09-19-00_883343a5d06b/events.out.tfevents.1719998342.883343a5d06b.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ede82b5b1fb51a40f6dd69fb162439221d97497e5613ea38dc0713bc5ac783
+size 5614

runs/Jul03_09-24-38_883343a5d06b/events.out.tfevents.1719998686.883343a5d06b.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83900dd4116a22b1bb48a140a157d90ff65f385ce093b3838474ab5609ce23e3
+size 10985

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49920a2a3a20728a5fb2de2cb9a0d7e3cdf9db18b96f2fde527f3e568dd07ce6
+size 5112