End of training

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: Mistral-7B-Finetuning-Insurance
+  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. -->
+
+# Mistral-7B-Finetuning-Insurance
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 60
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b751455bac18c260c793188b2414a3cabb61d6d296185708d65553c0970461d
+size 184592616

runs/Jan07_08-30-52_096ae31a5012/events.out.tfevents.1704616274.096ae31a5012.684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c86b905e7297c5c8b7d6e29bd742d38afc6e38b6c5aeaf2d587dcb072e890f
+size 6155

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d970283b2db9e26741e20f533939320bbbc53f311abd5aa39921484c70f4190
+size 4792

wandb/debug.log

@@ -0,0 +1,131 @@
+2024-01-07 08:32:15,522 INFO    MainThread:684 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
+2024-01-07 08:32:15,523 INFO    MainThread:684 [wandb_setup.py:_flush():76] Configure stats pid to 684
+2024-01-07 08:32:15,523 INFO    MainThread:684 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Loading settings from /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/wandb/settings
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
+2024-01-07 08:32:15,525 INFO    MainThread:684 [wandb_init.py:_log_setup():524] Logging user logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/wandb/run-20240107_083215-enryt6zo/logs/debug.log
+2024-01-07 08:32:15,525 INFO    MainThread:684 [wandb_init.py:_log_setup():525] Logging internal logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/wandb/run-20240107_083215-enryt6zo/logs/debug-internal.log
+2024-01-07 08:32:15,525 INFO    MainThread:684 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7bfea43750f0>
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():564] calling init triggers
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+config: {}
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():614] starting backend
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():618] setting up manager
+2024-01-07 08:32:15,531 INFO    MainThread:684 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-01-07 08:32:15,534 INFO    MainThread:684 [wandb_init.py:init():624] backend started and connected
+2024-01-07 08:32:15,570 INFO    MainThread:684 [wandb_run.py:_label_probe_notebook():1294] probe notebook
+2024-01-07 08:32:17,418 INFO    MainThread:684 [wandb_init.py:init():716] updated telemetry
+2024-01-07 08:32:17,453 INFO    MainThread:684 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2024-01-07 08:32:17,964 INFO    MainThread:684 [wandb_run.py:_on_init():2254] communicating current version
+2024-01-07 08:32:18,119 INFO    MainThread:684 [wandb_run.py:_on_init():2263] got version response 
+2024-01-07 08:32:18,120 INFO    MainThread:684 [wandb_init.py:init():800] starting run threads in backend
+2024-01-07 08:32:18,210 INFO    MainThread:684 [wandb_run.py:_console_start():2233] atexit reg
+2024-01-07 08:32:18,211 INFO    MainThread:684 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2024-01-07 08:32:18,211 INFO    MainThread:684 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2024-01-07 08:32:18,211 INFO    MainThread:684 [wandb_run.py:_redirect():2178] Redirects installed.
+2024-01-07 08:32:18,213 INFO    MainThread:684 [wandb_init.py:init():841] run started, returning control to user process
+2024-01-07 08:32:18,219 INFO    MainThread:684 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.36.2', 'model_type': 'mistral', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', 'load_in_8bit': False, 'load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Jan07_08-30-52_096ae31a5012', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
+2024-01-07 08:44:03,889 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:44:03,890 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:44:26,570 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:44:34,326 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:44:34,327 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:44:46,475 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:46:05,058 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:46:05,058 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:46:13,038 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:46:18,516 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:46:18,516 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:50:09,111 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:50:13,508 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:50:13,513 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:51:38,094 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:51:38,098 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:51:38,098 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:51:41,383 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:52:12,662 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:52:12,662 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:52:45,454 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:53:09,095 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:53:09,096 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:55:59,367 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:56:00,251 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:56:00,252 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:56:06,562 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:56:10,699 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:56:10,700 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:57:55,151 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:57:58,981 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:57:58,981 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:00:08,883 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:00:18,822 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:00:18,822 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:01,727 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:06,231 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:06,232 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:25,862 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:25,898 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:25,898 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:35,845 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:37,716 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:37,717 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:40,487 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:40,495 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:40,501 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:45,788 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:45,793 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:45,794 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:49,111 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:49,155 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:49,155 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:09:44,376 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:09:44,379 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:09:44,380 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:16,380 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:16,383 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:16,383 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:25,980 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:26,068 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:26,076 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:52,944 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:52,950 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:52,950 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:54,782 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:54,813 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:54,813 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:12:03,682 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:12:03,692 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:12:03,692 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:12:06,232 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:12:06,325 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:12:06,326 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:12:33,934 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:12:34,001 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:12:34,004 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:00,605 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:00,639 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:00,639 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:06,384 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:06,462 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:06,462 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:24,618 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:24,664 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:24,665 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:52,451 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:52,481 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:52,481 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:14:01,980 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:14:02,039 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:14:02,040 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:14:37,393 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:14:42,402 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:14:42,403 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:16:27,093 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:16:27,127 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:16:27,127 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:19:48,148 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:19:48,193 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:19:48,193 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend

wandb/run-20240107_083215-enryt6zo/files/config.yaml

@@ -0,0 +1,677 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.12
+    cli_version: 0.16.1
+    framework: huggingface
+    huggingface_version: 4.36.2
+    is_jupyter_run: true
+    is_kaggle_kernel: false
+    start_time: 1704616335.534639
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 84
+      - 98
+      2:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      - 49
+      - 51
+      - 53
+      - 55
+      - 71
+      - 84
+      - 98
+      3:
+      - 7
+      - 23
+      4: 3.10.12
+      5: 0.16.1
+      6: 4.36.2
+      8:
+      - 1
+      - 5
+      - 12
+      9:
+        1: transformers_trainer
+      13: linux-x86_64
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/loss
+      5: 1
+      6:
+      - 1
+    - 1: train/learning_rate
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/train_runtime
+      5: 1
+      6:
+      - 1
+    - 1: train/train_samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/total_flos
+      5: 1
+      6:
+      - 1
+    - 1: train/train_loss
+      5: 1
+      6:
+      - 1
+vocab_size:
+  desc: null
+  value: 32000
+max_position_embeddings:
+  desc: null
+  value: 32768
+hidden_size:
+  desc: null
+  value: 4096
+intermediate_size:
+  desc: null
+  value: 14336
+num_hidden_layers:
+  desc: null
+  value: 32
+num_attention_heads:
+  desc: null
+  value: 32
+sliding_window:
+  desc: null
+  value: 4096
+num_key_value_heads:
+  desc: null
+  value: 8
+hidden_act:
+  desc: null
+  value: silu
+initializer_range:
+  desc: null
+  value: 0.02
+rms_norm_eps:
+  desc: null
+  value: 1.0e-05
+use_cache:
+  desc: null
+  value: false
+rope_theta:
+  desc: null
+  value: 10000.0
+attention_dropout:
+  desc: null
+  value: 0.0
+return_dict:
+  desc: null
+  value: true
+output_hidden_states:
+  desc: null
+  value: false
+output_attentions:
+  desc: null
+  value: false
+torchscript:
+  desc: null
+  value: false
+torch_dtype:
+  desc: null
+  value: bfloat16
+use_bfloat16:
+  desc: null
+  value: false
+tf_legacy_loss:
+  desc: null
+  value: false
+pruned_heads:
+  desc: null
+  value: {}
+tie_word_embeddings:
+  desc: null
+  value: false
+is_encoder_decoder:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+cross_attention_hidden_size:
+  desc: null
+  value: null
+add_cross_attention:
+  desc: null
+  value: false
+tie_encoder_decoder:
+  desc: null
+  value: false
+max_length:
+  desc: null
+  value: 20
+min_length:
+  desc: null
+  value: 0
+do_sample:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+num_beams:
+  desc: null
+  value: 1
+num_beam_groups:
+  desc: null
+  value: 1
+diversity_penalty:
+  desc: null
+  value: 0.0
+temperature:
+  desc: null
+  value: 1.0
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+typical_p:
+  desc: null
+  value: 1.0
+repetition_penalty:
+  desc: null
+  value: 1.0
+length_penalty:
+  desc: null
+  value: 1.0
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+bad_words_ids:
+  desc: null
+  value: null
+num_return_sequences:
+  desc: null
+  value: 1
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+output_scores:
+  desc: null
+  value: false
+return_dict_in_generate:
+  desc: null
+  value: false
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+remove_invalid_values:
+  desc: null
+  value: false
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+suppress_tokens:
+  desc: null
+  value: null
+begin_suppress_tokens:
+  desc: null
+  value: null
+architectures:
+  desc: null
+  value:
+  - MistralForCausalLM
+finetuning_task:
+  desc: null
+  value: null
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+tokenizer_class:
+  desc: null
+  value: null
+prefix:
+  desc: null
+  value: null
+bos_token_id:
+  desc: null
+  value: 1
+pad_token_id:
+  desc: null
+  value: null
+eos_token_id:
+  desc: null
+  value: 2
+sep_token_id:
+  desc: null
+  value: null
+decoder_start_token_id:
+  desc: null
+  value: null
+task_specific_params:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+_name_or_path:
+  desc: null
+  value: mistralai/Mistral-7B-v0.1
+transformers_version:
+  desc: null
+  value: 4.36.2
+model_type:
+  desc: null
+  value: mistral
+quantization_config:
+  desc: null
+  value:
+    quant_method: QuantizationMethod.BITS_AND_BYTES
+    load_in_8bit: false
+    load_in_4bit: true
+    llm_int8_threshold: 6.0
+    llm_int8_skip_modules: null
+    llm_int8_enable_fp32_cpu_offload: false
+    llm_int8_has_fp16_weight: false
+    bnb_4bit_quant_type: nf4
+    bnb_4bit_use_double_quant: true
+    bnb_4bit_compute_dtype: bfloat16
+output_dir:
+  desc: null
+  value: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance
+overwrite_output_dir:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: false
+do_eval:
+  desc: null
+  value: false
+do_predict:
+  desc: null
+  value: false
+evaluation_strategy:
+  desc: null
+  value: 'no'
+prediction_loss_only:
+  desc: null
+  value: false
+per_device_train_batch_size:
+  desc: null
+  value: 2
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+gradient_accumulation_steps:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_delay:
+  desc: null
+  value: 0
+learning_rate:
+  desc: null
+  value: 0.0002
+weight_decay:
+  desc: null
+  value: 0.0
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+max_grad_norm:
+  desc: null
+  value: 0.3
+num_train_epochs:
+  desc: null
+  value: 3.0
+max_steps:
+  desc: null
+  value: 60
+lr_scheduler_type:
+  desc: null
+  value: cosine
+lr_scheduler_kwargs:
+  desc: null
+  value: {}
+warmup_ratio:
+  desc: null
+  value: 0.03
+warmup_steps:
+  desc: null
+  value: 0
+log_level:
+  desc: null
+  value: passive
+log_level_replica:
+  desc: null
+  value: warning
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Jan07_08-30-52_096ae31a5012
+logging_strategy:
+  desc: null
+  value: steps
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 10
+logging_nan_inf_filter:
+  desc: null
+  value: true
+save_strategy:
+  desc: null
+  value: steps
+save_steps:
+  desc: null
+  value: 10
+save_total_limit:
+  desc: null
+  value: null
+save_safetensors:
+  desc: null
+  value: true
+save_on_each_node:
+  desc: null
+  value: false
+save_only_model:
+  desc: null
+  value: false
+no_cuda:
+  desc: null
+  value: false
+use_cpu:
+  desc: null
+  value: false
+use_mps_device:
+  desc: null
+  value: false
+seed:
+  desc: null
+  value: 42
+data_seed:
+  desc: null
+  value: null
+jit_mode_eval:
+  desc: null
+  value: false
+use_ipex:
+  desc: null
+  value: false
+bf16:
+  desc: null
+  value: false
+fp16:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+half_precision_backend:
+  desc: null
+  value: auto
+bf16_full_eval:
+  desc: null
+  value: false
+fp16_full_eval:
+  desc: null
+  value: false
+tf32:
+  desc: null
+  value: false
+local_rank:
+  desc: null
+  value: 0
+ddp_backend:
+  desc: null
+  value: null
+tpu_num_cores:
+  desc: null
+  value: null
+tpu_metrics_debug:
+  desc: null
+  value: false
+debug:
+  desc: null
+  value: []
+dataloader_drop_last:
+  desc: null
+  value: false
+eval_steps:
+  desc: null
+  value: null
+dataloader_num_workers:
+  desc: null
+  value: 0
+past_index:
+  desc: null
+  value: -1
+run_name:
+  desc: null
+  value: /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance
+disable_tqdm:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+label_names:
+  desc: null
+  value: null
+load_best_model_at_end:
+  desc: null
+  value: false
+metric_for_best_model:
+  desc: null
+  value: null
+greater_is_better:
+  desc: null
+  value: null
+ignore_data_skip:
+  desc: null
+  value: false
+fsdp:
+  desc: null
+  value: []
+fsdp_min_num_params:
+  desc: null
+  value: 0
+fsdp_config:
+  desc: null
+  value:
+    min_num_params: 0
+    xla: false
+    xla_fsdp_grad_ckpt: false
+fsdp_transformer_layer_cls_to_wrap:
+  desc: null
+  value: null
+deepspeed:
+  desc: null
+  value: null
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+optim:
+  desc: null
+  value: paged_adamw_32bit
+optim_args:
+  desc: null
+  value: null
+adafactor:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: true
+length_column_name:
+  desc: null
+  value: length
+report_to:
+  desc: null
+  value:
+  - tensorboard
+  - wandb
+ddp_find_unused_parameters:
+  desc: null
+  value: null
+ddp_bucket_cap_mb:
+  desc: null
+  value: null
+ddp_broadcast_buffers:
+  desc: null
+  value: null
+dataloader_pin_memory:
+  desc: null
+  value: true
+dataloader_persistent_workers:
+  desc: null
+  value: false
+skip_memory_metrics:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+push_to_hub:
+  desc: null
+  value: true
+resume_from_checkpoint:
+  desc: null
+  value: null
+hub_model_id:
+  desc: null
+  value: null
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+hub_private_repo:
+  desc: null
+  value: false
+hub_always_push:
+  desc: null
+  value: false
+gradient_checkpointing:
+  desc: null
+  value: false
+gradient_checkpointing_kwargs:
+  desc: null
+  value: null
+include_inputs_for_metrics:
+  desc: null
+  value: false
+fp16_backend:
+  desc: null
+  value: auto
+push_to_hub_model_id:
+  desc: null
+  value: null
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+mp_parameters:
+  desc: null
+  value: ''
+auto_find_batch_size:
+  desc: null
+  value: false
+full_determinism:
+  desc: null
+  value: false
+torchdynamo:
+  desc: null
+  value: null
+ray_scope:
+  desc: null
+  value: last
+ddp_timeout:
+  desc: null
+  value: 1800
+torch_compile:
+  desc: null
+  value: false
+torch_compile_backend:
+  desc: null
+  value: null
+torch_compile_mode:
+  desc: null
+  value: null
+dispatch_batches:
+  desc: null
+  value: null
+split_batches:
+  desc: null
+  value: false
+include_tokens_per_second:
+  desc: null
+  value: false
+include_num_input_tokens_seen:
+  desc: null
+  value: false
+neftune_noise_alpha:
+  desc: null
+  value: null

wandb/run-20240107_083215-enryt6zo/files/output.log

@@ -0,0 +1,33 @@
+
+You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+-------------------------------------------------
+Pre-trained Model Answer:
+Answer the following question truthfully.
+: 고지의무가 뭐야?
+  : 어디에서 왔니?
+  : 이름은 몇번째인데요?
+  : 나는 언제 태어난거예요?
+  : 내 집주소는 어디입니까?
+  : 우리집 전화번호는 010-2345-6789 입니다.
+  : 저희 학교 위치는 여기에있습니다. (그림)
+  : 저희 학생들은 한국어,영어,수학을 배워요!
+  : 저희 선생님께서 좋아하시는것은 바로 음식과 운동입니다.
+  : 저희 학교를 찾으실때 도와드려요~
+  : 오늘 날짜는 2월 2일 입니다.
+  : 저희 학교는 매년 여러분
+-------------------------------------------------
+-------------------------------------------------
+Pre-trained Model Answer:
+Answer the following question truthfully.
+: 운전면허 미보유 보험가입 어떻게 하는지 알려줘?
+  : 10분만에 답변드립니다!
+## What is a car insurance policy for those who do not have driver's license in Korea?
+### Car Insurance Policy For Those Who Do Not Have Driver’s License In Korea
+##### [Car Insurance] How to get an auto insurance without having a driving licence (DL) or international DL in South Korea?
+In order to drive on Korean roads, you need to obtain a valid driver’s license issued by the Ministry of Land, Transport and Maritime Affairs(MLTM). If your country has signed bilateral agreements with Korea regarding mutual recognition of licenses, then it may be possible that you can use your foreign-issued driver’s license while living here temporarily as long as its expiration date hasn’t passed yet; however this does NOT apply if one wants their own personal vehicle insured under them because they will still require obtaining local certification before doing so which takes time depending upon where exactly someone lives within Seoul metropolitan area etcetera…
+The process starts off when applying through either KIA Motors Corporation headquartered near Gangnam Station OR Hyundai Motor Company located closeby too – both companies offer similar services
+-------------------------------------------------
+Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount("/content/gdrive", force_remount=True).
+/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance
+/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance
+env: LC_ALL=en_US.UTF-8

wandb/run-20240107_083215-enryt6zo/files/requirements.txt

@@ -0,0 +1,497 @@
+absl-py==1.4.0
+accelerate==0.25.0
+aiohttp==3.9.1
+aiosignal==1.3.1
+alabaster==0.7.13
+albumentations==1.3.1
+altair==4.2.2
+anyio==3.7.1
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==23.1.0
+array-record==0.5.0
+arviz==0.15.1
+astropy==5.3.4
+astunparse==1.6.3
+async-timeout==4.0.3
+atpublic==4.0
+attrs==23.1.0
+audioread==3.0.1
+autograd==1.6.2
+babel==2.14.0
+backcall==0.2.0
+beautifulsoup4==4.11.2
+bidict==0.22.1
+bigframes==0.17.0
+bitsandbytes==0.41.3.post2
+bleach==6.1.0
+blinker==1.4
+blis==0.7.11
+blosc2==2.0.0
+bokeh==3.3.2
+bqplot==0.12.42
+branca==0.7.0
+build==1.0.3
+cachecontrol==0.13.1
+cachetools==5.3.2
+catalogue==2.0.10
+certifi==2023.11.17
+cffi==1.16.0
+chardet==5.2.0
+charset-normalizer==3.3.2
+chex==0.1.7
+click-plugins==1.1.1
+click==8.1.7
+cligj==0.7.2
+cloudpickle==2.2.1
+cmake==3.27.9
+cmdstanpy==1.2.0
+colorcet==3.0.1
+colorlover==0.3.0
+colour==0.1.5
+community==1.0.0b1
+confection==0.1.4
+cons==0.4.6
+contextlib2==21.6.0
+contourpy==1.2.0
+cryptography==41.0.7
+cufflinks==0.17.3
+cupy-cuda12x==12.2.0
+cvxopt==1.3.2
+cvxpy==1.3.2
+cycler==0.12.1
+cymem==2.0.8
+cython==3.0.7
+dask==2023.8.1
+datascience==0.17.6
+datasets==2.16.1
+db-dtypes==1.2.0
+dbus-python==1.2.18
+debugpy==1.6.6
+decorator==4.4.2
+defusedxml==0.7.1
+dill==0.3.7
+diskcache==5.6.3
+distributed==2023.8.1
+distro==1.7.0
+dlib==19.24.2
+dm-tree==0.1.8
+docker-pycreds==0.4.0
+docstring-parser==0.15
+docutils==0.18.1
+dopamine-rl==4.0.6
+duckdb==0.9.2
+earthengine-api==0.1.384
+easydict==1.11
+ecos==2.0.12
+editdistance==0.6.2
+eerepr==0.0.4
+einops==0.7.0
+en-core-web-sm==3.6.0
+entrypoints==0.4
+et-xmlfile==1.1.0
+etils==1.6.0
+etuples==0.3.9
+exceptiongroup==1.2.0
+fastai==2.7.13
+fastcore==1.5.29
+fastdownload==0.0.7
+fastjsonschema==2.19.0
+fastprogress==1.0.3
+fastrlock==0.8.2
+filelock==3.13.1
+fiona==1.9.5
+firebase-admin==5.3.0
+flask==2.2.5
+flatbuffers==23.5.26
+flax==0.7.5
+folium==0.14.0
+fonttools==4.47.0
+frozendict==2.3.10
+frozenlist==1.4.1
+fsspec==2023.6.0
+future==0.18.3
+gast==0.5.4
+gcsfs==2023.6.0
+gdal==3.4.3
+gdown==4.6.6
+geemap==0.29.6
+gensim==4.3.2
+geocoder==1.38.1
+geographiclib==2.0
+geopandas==0.13.2
+geopy==2.3.0
+gin-config==0.5.0
+gitdb==4.0.11
+gitpython==3.1.40
+glob2==0.7
+google-ai-generativelanguage==0.4.0
+google-api-core==2.11.1
+google-api-python-client==2.84.0
+google-auth-httplib2==0.1.1
+google-auth-oauthlib==1.2.0
+google-auth==2.17.3
+google-cloud-aiplatform==1.38.1
+google-cloud-bigquery-connection==1.12.1
+google-cloud-bigquery-storage==2.24.0
+google-cloud-bigquery==3.12.0
+google-cloud-core==2.3.3
+google-cloud-datastore==2.15.2
+google-cloud-firestore==2.11.1
+google-cloud-functions==1.13.3
+google-cloud-iam==2.13.0
+google-cloud-language==2.9.1
+google-cloud-resource-manager==1.11.0
+google-cloud-storage==2.8.0
+google-cloud-translate==3.11.3
+google-colab==1.0.0
+google-crc32c==1.5.0
+google-generativeai==0.3.2
+google-pasta==0.2.0
+google-resumable-media==2.7.0
+google==2.0.3
+googleapis-common-protos==1.62.0
+googledrivedownloader==0.4
+graphviz==0.20.1
+greenlet==3.0.2
+grpc-google-iam-v1==0.13.0
+grpcio-status==1.48.2
+grpcio==1.60.0
+gspread-dataframe==3.3.1
+gspread==3.4.2
+gym-notices==0.0.8
+gym==0.25.2
+h5netcdf==1.3.0
+h5py==3.9.0
+holidays==0.39
+holoviews==1.17.1
+html5lib==1.1
+httpimport==1.3.1
+httplib2==0.22.0
+huggingface-hub==0.20.1
+humanize==4.7.0
+hyperopt==0.2.7
+ibis-framework==6.2.0
+idna==3.6
+imageio-ffmpeg==0.4.9
+imageio==2.31.6
+imagesize==1.4.1
+imbalanced-learn==0.10.1
+imgaug==0.4.0
+importlib-metadata==7.0.0
+importlib-resources==6.1.1
+imutils==0.5.4
+inflect==7.0.0
+iniconfig==2.0.0
+install==1.3.5
+intel-openmp==2023.2.3
+ipyevents==2.0.2
+ipyfilechooser==0.6.0
+ipykernel==5.5.6
+ipyleaflet==0.18.1
+ipython-genutils==0.2.0
+ipython-sql==0.5.0
+ipython==7.34.0
+ipytree==0.2.2
+ipywidgets==7.7.1
+itsdangerous==2.1.2
+jax==0.4.23
+jaxlib==0.4.23+cuda12.cudnn89
+jeepney==0.7.1
+jieba==0.42.1
+jinja2==3.1.2
+joblib==1.3.2
+jsonpickle==3.0.2
+jsonschema-specifications==2023.11.2
+jsonschema==4.19.2
+jupyter-client==6.1.12
+jupyter-console==6.1.0
+jupyter-core==5.5.1
+jupyter-server==1.24.0
+jupyterlab-pygments==0.3.0
+jupyterlab-widgets==3.0.9
+kaggle==1.5.16
+kagglehub==0.1.4
+keras==2.15.0
+keyring==23.5.0
+kiwisolver==1.4.5
+langcodes==3.3.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+lazy-loader==0.3
+libclang==16.0.6
+librosa==0.10.1
+lida==0.0.10
+lightgbm==4.1.0
+linkify-it-py==2.0.2
+llmx==0.0.15a0
+llvmlite==0.41.1
+locket==1.0.0
+logical-unification==0.4.6
+lxml==4.9.4
+malloy==2023.1067
+markdown-it-py==3.0.0
+markdown==3.5.1
+markupsafe==2.1.3
+matplotlib-inline==0.1.6
+matplotlib-venn==0.11.9
+matplotlib==3.7.1
+mdit-py-plugins==0.4.0
+mdurl==0.1.2
+minikanren==1.0.3
+missingno==0.5.2
+mistune==0.8.4
+mizani==0.9.3
+mkl==2023.2.0
+ml-dtypes==0.2.0
+mlxtend==0.22.0
+more-itertools==10.1.0
+moviepy==1.0.3
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+multipledispatch==1.0.0
+multiprocess==0.70.15
+multitasking==0.0.11
+murmurhash==1.0.10
+music21==9.1.0
+natsort==8.4.0
+nbclassic==1.0.0
+nbclient==0.9.0
+nbconvert==6.5.4
+nbformat==5.9.2
+nest-asyncio==1.5.8
+networkx==3.2.1
+nibabel==4.0.2
+nltk==3.8.1
+notebook-shim==0.2.3
+notebook==6.5.5
+numba==0.58.1
+numexpr==2.8.8
+numpy==1.23.5
+oauth2client==4.1.3
+oauthlib==3.2.2
+opencv-contrib-python==4.8.0.76
+opencv-python-headless==4.8.1.78
+opencv-python==4.8.0.76
+openpyxl==3.1.2
+opt-einsum==3.3.0
+optax==0.1.7
+orbax-checkpoint==0.4.4
+osqp==0.6.2.post8
+packaging==23.2
+pandas-datareader==0.10.0
+pandas-gbq==0.19.2
+pandas-stubs==1.5.3.230304
+pandas==1.5.3
+pandocfilters==1.5.0
+panel==1.3.6
+param==2.0.1
+parso==0.8.3
+parsy==2.1
+partd==1.4.1
+pathlib==1.0.1
+pathy==0.10.3
+patsy==0.5.4
+peewee==3.17.0
+peft==0.7.2.dev0
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==9.4.0
+pip-tools==6.13.0
+pip==23.1.2
+platformdirs==4.1.0
+plotly==5.15.0
+plotnine==0.12.4
+pluggy==1.3.0
+polars==0.17.3
+pooch==1.8.0
+portpicker==1.5.2
+prefetch-generator==1.0.3
+preshed==3.0.9
+prettytable==3.9.0
+proglog==0.1.10
+progressbar2==4.2.0
+prometheus-client==0.19.0
+promise==2.3
+prompt-toolkit==3.0.43
+prophet==1.1.5
+proto-plus==1.23.0
+protobuf==3.20.3
+psutil==5.9.5
+psycopg2==2.9.9
+ptyprocess==0.7.0
+py-cpuinfo==9.0.0
+py4j==0.10.9.7
+pyarrow-hotfix==0.6
+pyarrow==10.0.1
+pyasn1-modules==0.3.0
+pyasn1==0.5.1
+pycocotools==2.0.7
+pycparser==2.21
+pyct==0.5.0
+pydantic==1.10.13
+pydata-google-auth==1.8.2
+pydot-ng==2.0.0
+pydot==1.4.2
+pydotplus==2.0.2
+pydrive2==1.6.3
+pydrive==1.3.1
+pyerfa==2.0.1.1
+pygame==2.5.2
+pygments==2.16.1
+pygobject==3.42.1
+pyjwt==2.3.0
+pymc==5.7.2
+pymystem3==0.2.0
+pyopengl==3.1.7
+pyopenssl==23.3.0
+pyparsing==3.1.1
+pyperclip==1.8.2
+pyproj==3.6.1
+pyproject-hooks==1.0.0
+pyshp==2.3.1
+pysocks==1.7.1
+pytensor==2.14.2
+pytest==7.4.3
+python-apt==0.0.0
+python-box==7.1.1
+python-dateutil==2.8.2
+python-louvain==0.16
+python-slugify==8.0.1
+python-utils==3.8.1
+pytz==2023.3.post1
+pyviz-comms==3.0.0
+pywavelets==1.5.0
+pyyaml==6.0.1
+pyzmq==23.2.1
+qdldl==0.1.7.post0
+qudida==0.0.4
+ratelim==0.1.6
+referencing==0.32.0
+regex==2023.6.3
+requests-oauthlib==1.3.1
+requests==2.31.0
+requirements-parser==0.5.0
+rich==13.7.0
+rpds-py==0.15.2
+rpy2==3.4.2
+rsa==4.9
+safetensors==0.4.1
+scikit-image==0.19.3
+scikit-learn==1.2.2
+scipy==1.11.4
+scooby==0.9.2
+scs==3.2.4.post1
+seaborn==0.12.2
+secretstorage==3.3.1
+send2trash==1.8.2
+sentry-sdk==1.39.1
+setproctitle==1.3.3
+setuptools==67.7.2
+shapely==2.0.2
+shtab==1.6.5
+six==1.16.0
+sklearn-pandas==2.2.0
+smart-open==6.4.0
+smmap==5.0.1
+sniffio==1.3.0
+snowballstemmer==2.2.0
+sortedcontainers==2.4.0
+soundfile==0.12.1
+soupsieve==2.5
+soxr==0.3.7
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+spacy==3.6.1
+sphinx==5.0.2
+sphinxcontrib-applehelp==1.0.7
+sphinxcontrib-devhelp==1.0.5
+sphinxcontrib-htmlhelp==2.0.4
+sphinxcontrib-jsmath==1.0.1
+sphinxcontrib-qthelp==1.0.6
+sphinxcontrib-serializinghtml==1.1.9
+sqlalchemy==2.0.23
+sqlglot==17.16.2
+sqlparse==0.4.4
+srsly==2.4.8
+stanio==0.3.0
+statsmodels==0.14.1
+sympy==1.12
+tables==3.8.0
+tabulate==0.9.0
+tbb==2021.11.0
+tblib==3.0.0
+tenacity==8.2.3
+tensorboard-data-server==0.7.2
+tensorboard==2.15.1
+tensorflow-datasets==4.9.4
+tensorflow-estimator==2.15.0
+tensorflow-gcs-config==2.15.0
+tensorflow-hub==0.15.0
+tensorflow-io-gcs-filesystem==0.35.0
+tensorflow-metadata==1.14.0
+tensorflow-probability==0.22.0
+tensorflow==2.15.0
+tensorstore==0.1.45
+termcolor==2.4.0
+terminado==0.18.0
+text-unidecode==1.3
+textblob==0.17.1
+tf-slim==1.1.0
+thinc==8.1.12
+threadpoolctl==3.2.0
+tifffile==2023.12.9
+tinycss2==1.2.1
+tokenizers==0.15.0
+toml==0.10.2
+tomli==2.0.1
+toolz==0.12.0
+torch==2.1.0+cu121
+torchaudio==2.1.0+cu121
+torchdata==0.7.0
+torchsummary==1.5.1
+torchtext==0.16.0
+torchvision==0.16.0+cu121
+tornado==6.3.2
+tqdm==4.66.1
+traitlets==5.7.1
+traittypes==0.2.1
+transformers==4.36.2
+triton==2.1.0
+trl==0.7.7
+tweepy==4.14.0
+typer==0.9.0
+types-pytz==2023.3.1.1
+types-setuptools==69.0.0.0
+typing-extensions==4.5.0
+tyro==0.6.3
+tzlocal==5.2
+uc-micro-py==1.0.2
+uritemplate==4.1.1
+urllib3==2.0.7
+vega-datasets==0.9.0
+wadllib==1.3.6
+wandb==0.16.1
+wasabi==1.1.2
+wcwidth==0.2.12
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.7.0
+werkzeug==3.0.1
+wheel==0.42.0
+widgetsnbextension==3.6.6
+wordcloud==1.9.3
+wrapt==1.14.1
+xarray-einstats==0.6.0
+xarray==2023.7.0
+xgboost==2.0.3
+xlrd==2.0.1
+xxhash==3.4.1
+xyzservices==2023.10.1
+yarl==1.9.4
+yellowbrick==1.5
+yfinance==0.2.33
+zict==3.0.0
+zipp==3.17.0

wandb/run-20240107_083215-enryt6zo/files/wandb-metadata.json

@@ -0,0 +1,52 @@
+{
+    "os": "Linux-6.1.58+-x86_64-with-glibc2.35",
+    "python": "3.10.12",
+    "heartbeatAt": "2024-01-07T08:32:18.151267",
+    "startedAt": "2024-01-07T08:32:15.488264",
+    "docker": null,
+    "cuda": null,
+    "args": [],
+    "state": "running",
+    "program": "Mistral-7B-Finetuning-Insurance.ipynb",
+    "codePathLocal": null,
+    "colab": "https://colab.research.google.com/notebook#fileId=1yggNDPxtSX3bri4ON4ppYc-G-Q2zFtkQ",
+    "host": "096ae31a5012",
+    "username": "root",
+    "executable": "/usr/bin/python3",
+    "cpu_count": 1,
+    "cpu_count_logical": 2,
+    "cpu_freq": {
+        "current": 2199.998,
+        "min": 0.0,
+        "max": 0.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2199.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2199.998,
+            "min": 0.0,
+            "max": 0.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 78.1898422241211,
+            "used": 40.23767852783203
+        }
+    },
+    "gpu": "Tesla T4",
+    "gpu_count": 1,
+    "gpu_devices": [
+        {
+            "name": "Tesla T4",
+            "memory_total": 16106127360
+        }
+    ],
+    "memory": {
+        "total": 12.674781799316406
+    }
+}

wandb/run-20240107_083215-enryt6zo/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss": 1.2937, "train/learning_rate": 0.0, "train/epoch": 0.44, "train/global_step": 60, "_timestamp": 1704617031.0774682, "_runtime": 695.5428292751312, "_step": 6, "train/train_runtime": 756.7394, "train/train_samples_per_second": 0.317, "train/train_steps_per_second": 0.079, "train/total_flos": 1588809031680000.0, "train/train_loss": 1.4518062591552734}

wandb/run-20240107_083215-enryt6zo/logs/debug.log

@@ -0,0 +1,131 @@
+2024-01-07 08:32:15,522 INFO    MainThread:684 [wandb_setup.py:_flush():76] Current SDK version is 0.16.1
+2024-01-07 08:32:15,523 INFO    MainThread:684 [wandb_setup.py:_flush():76] Configure stats pid to 684
+2024-01-07 08:32:15,523 INFO    MainThread:684 [wandb_setup.py:_flush():76] Loading settings from /root/.config/wandb/settings
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Loading settings from /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/wandb/settings
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program': '<python with no main file>'}
+2024-01-07 08:32:15,524 INFO    MainThread:684 [wandb_setup.py:_flush():76] Applying login settings: {'api_key': '***REDACTED***'}
+2024-01-07 08:32:15,525 INFO    MainThread:684 [wandb_init.py:_log_setup():524] Logging user logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/wandb/run-20240107_083215-enryt6zo/logs/debug.log
+2024-01-07 08:32:15,525 INFO    MainThread:684 [wandb_init.py:_log_setup():525] Logging internal logs to /content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/wandb/run-20240107_083215-enryt6zo/logs/debug-internal.log
+2024-01-07 08:32:15,525 INFO    MainThread:684 [wandb_init.py:_jupyter_setup():470] configuring jupyter hooks <wandb.sdk.wandb_init._WandbInit object at 0x7bfea43750f0>
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():564] calling init triggers
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+config: {}
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():614] starting backend
+2024-01-07 08:32:15,526 INFO    MainThread:684 [wandb_init.py:init():618] setting up manager
+2024-01-07 08:32:15,531 INFO    MainThread:684 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-01-07 08:32:15,534 INFO    MainThread:684 [wandb_init.py:init():624] backend started and connected
+2024-01-07 08:32:15,570 INFO    MainThread:684 [wandb_run.py:_label_probe_notebook():1294] probe notebook
+2024-01-07 08:32:17,418 INFO    MainThread:684 [wandb_init.py:init():716] updated telemetry
+2024-01-07 08:32:17,453 INFO    MainThread:684 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2024-01-07 08:32:17,964 INFO    MainThread:684 [wandb_run.py:_on_init():2254] communicating current version
+2024-01-07 08:32:18,119 INFO    MainThread:684 [wandb_run.py:_on_init():2263] got version response 
+2024-01-07 08:32:18,120 INFO    MainThread:684 [wandb_init.py:init():800] starting run threads in backend
+2024-01-07 08:32:18,210 INFO    MainThread:684 [wandb_run.py:_console_start():2233] atexit reg
+2024-01-07 08:32:18,211 INFO    MainThread:684 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2024-01-07 08:32:18,211 INFO    MainThread:684 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2024-01-07 08:32:18,211 INFO    MainThread:684 [wandb_run.py:_redirect():2178] Redirects installed.
+2024-01-07 08:32:18,213 INFO    MainThread:684 [wandb_init.py:init():841] run started, returning control to user process
+2024-01-07 08:32:18,219 INFO    MainThread:684 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'mistralai/Mistral-7B-v0.1', 'transformers_version': '4.36.2', 'model_type': 'mistral', 'quantization_config': {'quant_method': 'QuantizationMethod.BITS_AND_BYTES', 'load_in_8bit': False, 'load_in_4bit': True, 'llm_int8_threshold': 6.0, 'llm_int8_skip_modules': None, 'llm_int8_enable_fp32_cpu_offload': False, 'llm_int8_has_fp16_weight': False, 'bnb_4bit_quant_type': 'nf4', 'bnb_4bit_use_double_quant': True, 'bnb_4bit_compute_dtype': 'bfloat16'}, 'output_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 0.3, 'num_train_epochs': 3.0, 'max_steps': 60, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.03, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance/runs/Jan07_08-30-52_096ae31a5012', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 10, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': False, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/content/gdrive/MyDrive/LLM/Mistral-7B-Finetuning-Insurance', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
+2024-01-07 08:44:03,889 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:44:03,890 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:44:26,570 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:44:34,326 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:44:34,327 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:44:46,475 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:46:05,058 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:46:05,058 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:46:13,038 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:46:18,516 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:46:18,516 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:50:09,111 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:50:13,508 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:50:13,513 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:51:38,094 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:51:38,098 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:51:38,098 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:51:41,383 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:52:12,662 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:52:12,662 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:52:45,454 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:53:09,095 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:53:09,096 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:55:59,367 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:56:00,251 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:56:00,252 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:56:06,562 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:56:10,699 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:56:10,700 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 08:57:55,151 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 08:57:58,981 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 08:57:58,981 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:00:08,883 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:00:18,822 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:00:18,822 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:01,727 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:06,231 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:06,232 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:25,862 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:25,898 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:25,898 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:35,845 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:37,716 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:37,717 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:40,487 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:40,495 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:40,501 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:45,788 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:45,793 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:45,794 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:08:49,111 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:08:49,155 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:08:49,155 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:09:44,376 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:09:44,379 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:09:44,380 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:16,380 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:16,383 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:16,383 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:25,980 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:26,068 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:26,076 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:52,944 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:52,950 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:52,950 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:10:54,782 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:10:54,813 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:10:54,813 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:12:03,682 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:12:03,692 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:12:03,692 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:12:06,232 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:12:06,325 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:12:06,326 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:12:33,934 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:12:34,001 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:12:34,004 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:00,605 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:00,639 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:00,639 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:06,384 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:06,462 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:06,462 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:24,618 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:24,664 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:24,665 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:13:52,451 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:13:52,481 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:13:52,481 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:14:01,980 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:14:02,039 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:14:02,040 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:14:37,393 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:14:42,402 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:14:42,403 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:16:27,093 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:16:27,127 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:16:27,127 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend
+2024-01-07 09:19:48,148 INFO    MainThread:684 [wandb_init.py:_resume_backend():440] resuming backend
+2024-01-07 09:19:48,193 INFO    MainThread:684 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-07 09:19:48,193 INFO    MainThread:684 [wandb_init.py:_pause_backend():435] pausing backend