jennhu/olmo-7b-lora_bigtom_train_bigtom_train

README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: allenai/OLMo-7B-0724-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: bigtom_train
+  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. -->
+
+# bigtom_train
+
+This model is a fine-tuned version of [allenai/OLMo-7B-0724-hf](https://huggingface.co/allenai/OLMo-7B-0724-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8782
+
+## 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: 0.002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8221        | 6.8   | 20   | 1.9057          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.49.0
+- Pytorch 2.6.0
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "allenai/OLMo-7B-0724-hf",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "lm_head",
+    "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:e470d8a281a23fdb34e8a5981c76297f3e8af0a663712c7cc0f135ca0dbfc3c6
+size 1477800176

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.8,
+  "eval_steps": 20,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.026561671867966652,
+      "learning_rate": 0.001894736842105263,
+      "loss": 2.4537,
+      "step": 2
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.1137104481458664,
+      "learning_rate": 0.0016842105263157893,
+      "loss": 2.4379,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.24436840415000916,
+      "learning_rate": 0.0014736842105263158,
+      "loss": 2.3347,
+      "step": 6
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.30128273367881775,
+      "learning_rate": 0.0012631578947368421,
+      "loss": 2.1954,
+      "step": 8
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.4249122440814972,
+      "learning_rate": 0.0010526315789473684,
+      "loss": 2.0775,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4739112854003906,
+      "learning_rate": 0.0008421052631578947,
+      "loss": 1.9817,
+      "step": 12
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.44454509019851685,
+      "learning_rate": 0.0006315789473684211,
+      "loss": 1.9018,
+      "step": 14
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.3762497007846832,
+      "learning_rate": 0.00042105263157894734,
+      "loss": 1.8925,
+      "step": 16
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.34596943855285645,
+      "learning_rate": 0.00021052631578947367,
+      "loss": 1.8335,
+      "step": 18
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.3068355619907379,
+      "learning_rate": 0.0,
+      "loss": 1.8221,
+      "step": 20
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 1.905713677406311,
+      "eval_runtime": 1.8411,
+      "eval_samples_per_second": 43.452,
+      "eval_steps_per_second": 5.432,
+      "step": 20
+    },
+    {
+      "epoch": 6.8,
+      "step": 20,
+      "total_flos": 2.448849371136e+16,
+      "train_loss": 2.093080127239227,
+      "train_runtime": 118.9098,
+      "train_samples_per_second": 53.822,
+      "train_steps_per_second": 0.168
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 1.905713677406311,
+      "eval_runtime": 1.8743,
+      "eval_samples_per_second": 42.682,
+      "eval_steps_per_second": 5.335,
+      "step": 20
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 1.8781611919403076,
+      "eval_runtime": 1.8586,
+      "eval_samples_per_second": 43.043,
+      "eval_steps_per_second": 5.38,
+      "step": 20
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.448849371136e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffccbf7f1484aecbe404187e58241be7f5bcf3ba962a4f6d8336125962c4501
+size 5432