End of training

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: jan-hq/komodo-7b-chat
+datasets:
+- wikitext
+model-index:
+- name: komodo-7b-test
+  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. -->
+
+# komodo-7b-test
+
+This model is a fine-tuned version of [jan-hq/komodo-7b-chat](https://huggingface.co/jan-hq/komodo-7b-chat) on the wikitext wikitext-2-raw-v1 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: 256
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 40.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.0.dev0
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "jan-hq/komodo-7b-chat",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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:b73cfa6ffa6bcfafbad46e9e78bbec19b1478df7bb106a026461b8883b0a79ea
+size 8405600

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 40.0,
+    "total_flos": 4.167371548576973e+18,
+    "train_loss": 1.28,
+    "train_runtime": 814.2309,
+    "train_samples": 2698,
+    "train_samples_per_second": 132.542,
+    "train_steps_per_second": 0.491
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 40.0,
+    "total_flos": 4.167371548576973e+18,
+    "train_loss": 1.28,
+    "train_runtime": 814.2309,
+    "train_samples": 2698,
+    "train_samples_per_second": 132.542,
+    "train_steps_per_second": 0.491
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 40.0,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 40.0,
+      "step": 400,
+      "total_flos": 4.167371548576973e+18,
+      "train_loss": 1.28,
+      "train_runtime": 814.2309,
+      "train_samples_per_second": 132.542,
+      "train_steps_per_second": 0.491
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 4.167371548576973e+18,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2e344cdc5fce9ace2d72a63e19ce65062af4a2e635cf74add852308c9db580
+size 8824