End of training

.ipynb_checkpoints/train_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.6486718999887872e+16,
+    "train_loss": 1.3161976137640756,
+    "train_runtime": 493.8113,
+    "train_samples_per_second": 1.45,
+    "train_steps_per_second": 0.362
+}

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 179,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11173184357541899,
+      "grad_norm": 2.0458016395568848,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 2.0107,
+      "step": 20
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 2.3176522254943848,
+      "learning_rate": 4.9903533134293035e-06,
+      "loss": 1.9625,
+      "step": 40
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 2.3477518558502197,
+      "learning_rate": 4.660472094042121e-06,
+      "loss": 1.7282,
+      "step": 60
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 2.8214402198791504,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 1.4047,
+      "step": 80
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "grad_norm": 1.2627031803131104,
+      "learning_rate": 2.9100607788275547e-06,
+      "loss": 1.1131,
+      "step": 100
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 1.03634512424469,
+      "learning_rate": 1.8220596619089576e-06,
+      "loss": 0.9726,
+      "step": 120
+    },
+    {
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.9175835847854614,
+      "learning_rate": 8.628481651367876e-07,
+      "loss": 0.8899,
+      "step": 140
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.9105198979377747,
+      "learning_rate": 2.1464952759020857e-07,
+      "loss": 0.8588,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "step": 179,
+      "total_flos": 1.6486718999887872e+16,
+      "train_loss": 1.3161976137640756,
+      "train_runtime": 493.8113,
+      "train_samples_per_second": 1.45,
+      "train_steps_per_second": 0.362
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 179,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6486718999887872e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

README.md

@@ -0,0 +1,59 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+datasets:
+- generator
+library_name: peft
+license: mit
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: checkpoint_dir
+  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. -->
+
+# checkpoint_dir
+
+This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the generator 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-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "gate_up_proj",
+    "qkv_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 sha256:060b0bcb07a7a61833c3c0d4d6fa80e3b4b8f0ce65d446af7d89ebdb9243056b
+size 100697728

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.6486718999887872e+16,
+    "train_loss": 1.3161976137640756,
+    "train_runtime": 493.8113,
+    "train_samples_per_second": 1.45,
+    "train_steps_per_second": 0.362
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.6486718999887872e+16,
+    "train_loss": 1.3161976137640756,
+    "train_runtime": 493.8113,
+    "train_samples_per_second": 1.45,
+    "train_steps_per_second": 0.362
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 179,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11173184357541899,
+      "grad_norm": 2.0458016395568848,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 2.0107,
+      "step": 20
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 2.3176522254943848,
+      "learning_rate": 4.9903533134293035e-06,
+      "loss": 1.9625,
+      "step": 40
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 2.3477518558502197,
+      "learning_rate": 4.660472094042121e-06,
+      "loss": 1.7282,
+      "step": 60
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 2.8214402198791504,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 1.4047,
+      "step": 80
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "grad_norm": 1.2627031803131104,
+      "learning_rate": 2.9100607788275547e-06,
+      "loss": 1.1131,
+      "step": 100
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 1.03634512424469,
+      "learning_rate": 1.8220596619089576e-06,
+      "loss": 0.9726,
+      "step": 120
+    },
+    {
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.9175835847854614,
+      "learning_rate": 8.628481651367876e-07,
+      "loss": 0.8899,
+      "step": 140
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.9105198979377747,
+      "learning_rate": 2.1464952759020857e-07,
+      "loss": 0.8588,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "step": 179,
+      "total_flos": 1.6486718999887872e+16,
+      "train_loss": 1.3161976137640756,
+      "train_runtime": 493.8113,
+      "train_samples_per_second": 1.45,
+      "train_steps_per_second": 0.362
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 179,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6486718999887872e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a57cfce748bb2eb9c2b2a3a14a0289c4c8bd2938434ffa7a8e254bf2758e133
+size 5432