End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: llama2
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Yellow-AI-NLP/komodo-7b-base
+datasets:
+- thonyyy/tatoeba-nusax-mt-p2
+model-index:
+- name: komodo-7b-translate-p2-skip
+  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-translate-p2-skip
+
+This model is a fine-tuned version of [Yellow-AI-NLP/komodo-7b-base](https://huggingface.co/Yellow-AI-NLP/komodo-7b-base) on the thonyyy/tatoeba-nusax-mt-p2 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: 0.0001
+- train_batch_size: 64
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: tpu
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.0.dev0
+- Pytorch 2.3.0+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": "Yellow-AI-NLP/komodo-7b-base",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:1f776e3759973e7bf46e1d9f06f8a0b5275005e64375478e9e8d8f2710ecb1f7
+size 591414752

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.210874701004407e+18,
+    "train_loss": 2.3821448783248442,
+    "train_runtime": 6004.0837,
+    "train_samples": 150796,
+    "train_samples_per_second": 75.347,
+    "train_steps_per_second": 1.177
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "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": 3.0,
+    "total_flos": 9.210874701004407e+18,
+    "train_loss": 2.3821448783248442,
+    "train_runtime": 6004.0837,
+    "train_samples": 150796,
+    "train_samples_per_second": 75.347,
+    "train_steps_per_second": 1.177
+}

trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 7068,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21222410865874364,
+      "grad_norm": 66.5,
+      "learning_rate": 7.072135785007072e-05,
+      "loss": 2.656,
+      "step": 500
+    },
+    {
+      "epoch": 0.4244482173174873,
+      "grad_norm": 37.0,
+      "learning_rate": 9.94774038398841e-05,
+      "loss": 2.976,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6366723259762309,
+      "grad_norm": 106.0,
+      "learning_rate": 9.621403253948297e-05,
+      "loss": 3.28,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8488964346349746,
+      "grad_norm": 176160768.0,
+      "learning_rate": 9.014681135272878e-05,
+      "loss": 2.048,
+      "step": 2000
+    },
+    {
+      "epoch": 1.061120543293718,
+      "grad_norm": 421527552.0,
+      "learning_rate": 8.164384443544097e-05,
+      "loss": 2.048,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2733446519524618,
+      "grad_norm": 1333788672.0,
+      "learning_rate": 7.122101498401308e-05,
+      "loss": 2.048,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4855687606112054,
+      "grad_norm": 42205184.0,
+      "learning_rate": 5.951068610477853e-05,
+      "loss": 2.048,
+      "step": 3500
+    },
+    {
+      "epoch": 1.697792869269949,
+      "grad_norm": 291504128.0,
+      "learning_rate": 4.72233347349998e-05,
+      "loss": 3.792,
+      "step": 4000
+    },
+    {
+      "epoch": 1.9100169779286928,
+      "grad_norm": 20054016.0,
+      "learning_rate": 3.510444632246376e-05,
+      "loss": 2.048,
+      "step": 4500
+    },
+    {
+      "epoch": 2.122241086587436,
+      "grad_norm": 128974848.0,
+      "learning_rate": 2.3889285505009233e-05,
+      "loss": 2.048,
+      "step": 5000
+    },
+    {
+      "epoch": 2.33446519524618,
+      "grad_norm": 200278016.0,
+      "learning_rate": 1.425828689644288e-05,
+      "loss": 2.048,
+      "step": 5500
+    },
+    {
+      "epoch": 2.5466893039049237,
+      "grad_norm": 511705088.0,
+      "learning_rate": 6.795772462847716e-06,
+      "loss": 2.048,
+      "step": 6000
+    },
+    {
+      "epoch": 2.7589134125636674,
+      "grad_norm": 574619648.0,
+      "learning_rate": 1.9545001458439126e-06,
+      "loss": 2.048,
+      "step": 6500
+    },
+    {
+      "epoch": 2.9711375212224107,
+      "grad_norm": 400556032.0,
+      "learning_rate": 2.8194601989800507e-08,
+      "loss": 2.048,
+      "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "step": 7068,
+      "total_flos": 9.210874701004407e+18,
+      "train_loss": 2.3821448783248442,
+      "train_runtime": 6004.0837,
+      "train_samples_per_second": 75.347,
+      "train_steps_per_second": 1.177
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7068,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.210874701004407e+18,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5ae4039a44a8bd31b7302d2f94f8a0c482c5c5c82d57601cb62f3f03e586e9
+size 7224