Upload 16 files

README.md

@@ -0,0 +1,59 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: mistral_physs
+  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_physs
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the physics 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.4
+- Pytorch 2.2.1
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_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 sha256:38971402ace8dfaa4c171680108f01323ecd1d7ef217e9b4e01921d67dac59ac
+size 83945296

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9984,
+    "num_input_tokens_seen": 5111808,
+    "total_flos": 2.1873318928633037e+17,
+    "train_loss": 0.5760276004289969,
+    "train_runtime": 1768.2955,
+    "train_samples_per_second": 5.655,
+    "train_steps_per_second": 0.088
+}

llamaboard_config.yaml

@@ -0,0 +1,67 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-7B-v0.1-Chat
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: mistral
+top.visual_inputs: false
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 8
+train.compute_type: fp16
+train.create_new_adapter: false
+train.cutoff_len: 512
+train.dataset:
+- physics
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 3e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '10000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '1.0'
+train.optim: adamw_torch
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,284 @@
+[INFO|parser.py:355] 2024-08-29 20:29:00,103 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.float16
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-29 20:29:00,279 >> loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/tokenizer.model
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-29 20:29:00,280 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/tokenizer.json
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-29 20:29:00,280 >> loading file added_tokens.json from cache at None
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-29 20:29:00,280 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/special_tokens_map.json
+
+[INFO|tokenization_utils_base.py:2289] 2024-08-29 20:29:00,280 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/tokenizer_config.json
+
+[INFO|template.py:373] 2024-08-29 20:29:00,325 >> Add pad token: </s>
+
+[INFO|loader.py:52] 2024-08-29 20:29:00,326 >> Loading dataset HydraLM/physics_dataset_alpaca...
+
+[INFO|configuration_utils.py:733] 2024-08-29 20:29:03,695 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-29 20:29:03,696 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|modeling_utils.py:3644] 2024-08-29 20:29:03,719 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/model.safetensors.index.json
+
+[INFO|modeling_utils.py:1572] 2024-08-29 20:29:03,720 >> Instantiating MistralForCausalLM model under default dtype torch.float16.
+
+[INFO|configuration_utils.py:1038] 2024-08-29 20:29:03,721 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+
+[INFO|modeling_utils.py:4473] 2024-08-29 20:29:30,412 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|modeling_utils.py:4481] 2024-08-29 20:29:30,412 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at mistralai/Mistral-7B-Instruct-v0.1.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.
+
+[INFO|configuration_utils.py:993] 2024-08-29 20:29:30,511 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/generation_config.json
+
+[INFO|configuration_utils.py:1038] 2024-08-29 20:29:30,512 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2
+}
+
+
+[INFO|checkpointing.py:103] 2024-08-29 20:29:30,518 >> Gradient checkpointing enabled.
+
+[INFO|attention.py:84] 2024-08-29 20:29:30,519 >> Using torch SDPA for faster training and inference.
+
+[INFO|adapter.py:302] 2024-08-29 20:29:30,519 >> Upcasting trainable params to float32.
+
+[INFO|adapter.py:158] 2024-08-29 20:29:30,519 >> Fine-tuning method: LoRA
+
+[INFO|misc.py:51] 2024-08-29 20:29:30,519 >> Found linear modules: q_proj,down_proj,up_proj,k_proj,o_proj,gate_proj,v_proj
+
+[INFO|loader.py:196] 2024-08-29 20:29:46,150 >> trainable params: 20,971,520 || all params: 7,262,703,616 || trainable%: 0.2888
+
+[INFO|trainer.py:648] 2024-08-29 20:29:46,160 >> Using auto half precision backend
+
+[INFO|trainer.py:2134] 2024-08-29 20:29:46,579 >> ***** Running training *****
+
+[INFO|trainer.py:2135] 2024-08-29 20:29:46,579 >>   Num examples = 10,000
+
+[INFO|trainer.py:2136] 2024-08-29 20:29:46,579 >>   Num Epochs = 1
+
+[INFO|trainer.py:2137] 2024-08-29 20:29:46,579 >>   Instantaneous batch size per device = 8
+
+[INFO|trainer.py:2140] 2024-08-29 20:29:46,579 >>   Total train batch size (w. parallel, distributed & accumulation) = 64
+
+[INFO|trainer.py:2141] 2024-08-29 20:29:46,579 >>   Gradient Accumulation steps = 8
+
+[INFO|trainer.py:2142] 2024-08-29 20:29:46,579 >>   Total optimization steps = 156
+
+[INFO|trainer.py:2143] 2024-08-29 20:29:46,584 >>   Number of trainable parameters = 20,971,520
+
+[INFO|callbacks.py:319] 2024-08-29 20:30:43,585 >> {'loss': 0.6780, 'learning_rate': 2.9924e-05, 'epoch': 0.03, 'throughput': 2874.51}
+
+[INFO|callbacks.py:319] 2024-08-29 20:31:40,281 >> {'loss': 0.6551, 'learning_rate': 2.9697e-05, 'epoch': 0.06, 'throughput': 2882.14}
+
+[INFO|callbacks.py:319] 2024-08-29 20:32:36,903 >> {'loss': 0.6372, 'learning_rate': 2.9321e-05, 'epoch': 0.10, 'throughput': 2885.94}
+
+[INFO|callbacks.py:319] 2024-08-29 20:33:33,631 >> {'loss': 0.6201, 'learning_rate': 2.8800e-05, 'epoch': 0.13, 'throughput': 2886.5}
+
+[INFO|callbacks.py:319] 2024-08-29 20:34:30,081 >> {'loss': 0.5965, 'learning_rate': 2.8139e-05, 'epoch': 0.16, 'throughput': 2889.67}
+
+[INFO|callbacks.py:319] 2024-08-29 20:35:26,826 >> {'loss': 0.5959, 'learning_rate': 2.7345e-05, 'epoch': 0.19, 'throughput': 2889.27}
+
+[INFO|callbacks.py:319] 2024-08-29 20:36:23,284 >> {'loss': 0.6006, 'learning_rate': 2.6426e-05, 'epoch': 0.22, 'throughput': 2891.08}
+
+[INFO|callbacks.py:319] 2024-08-29 20:37:19,827 >> {'loss': 0.5940, 'learning_rate': 2.5391e-05, 'epoch': 0.26, 'throughput': 2891.9}
+
+[INFO|callbacks.py:319] 2024-08-29 20:38:16,461 >> {'loss': 0.5825, 'learning_rate': 2.4251e-05, 'epoch': 0.29, 'throughput': 2892.01}
+
+[INFO|callbacks.py:319] 2024-08-29 20:39:13,245 >> {'loss': 0.5871, 'learning_rate': 2.3017e-05, 'epoch': 0.32, 'throughput': 2891.34}
+
+[INFO|callbacks.py:319] 2024-08-29 20:40:10,089 >> {'loss': 0.5771, 'learning_rate': 2.1702e-05, 'epoch': 0.35, 'throughput': 2890.51}
+
+[INFO|callbacks.py:319] 2024-08-29 20:41:06,524 >> {'loss': 0.5544, 'learning_rate': 2.0319e-05, 'epoch': 0.38, 'throughput': 2891.57}
+
+[INFO|callbacks.py:319] 2024-08-29 20:42:03,054 >> {'loss': 0.5768, 'learning_rate': 1.8882e-05, 'epoch': 0.42, 'throughput': 2892.08}
+
+[INFO|callbacks.py:319] 2024-08-29 20:42:59,850 >> {'loss': 0.5534, 'learning_rate': 1.7406e-05, 'epoch': 0.45, 'throughput': 2891.55}
+
+[INFO|callbacks.py:319] 2024-08-29 20:43:56,581 >> {'loss': 0.5597, 'learning_rate': 1.5906e-05, 'epoch': 0.48, 'throughput': 2891.32}
+
+[INFO|callbacks.py:319] 2024-08-29 20:44:53,211 >> {'loss': 0.5710, 'learning_rate': 1.4396e-05, 'epoch': 0.51, 'throughput': 2891.43}
+
+[INFO|callbacks.py:319] 2024-08-29 20:45:49,959 >> {'loss': 0.5572, 'learning_rate': 1.2892e-05, 'epoch': 0.54, 'throughput': 2891.18}
+
+[INFO|callbacks.py:319] 2024-08-29 20:46:46,195 >> {'loss': 0.5686, 'learning_rate': 1.1410e-05, 'epoch': 0.58, 'throughput': 2892.41}
+
+[INFO|callbacks.py:319] 2024-08-29 20:47:42,985 >> {'loss': 0.5525, 'learning_rate': 9.9644e-06, 'epoch': 0.61, 'throughput': 2892.02}
+
+[INFO|callbacks.py:319] 2024-08-29 20:48:39,767 >> {'loss': 0.5594, 'learning_rate': 8.5696e-06, 'epoch': 0.64, 'throughput': 2891.69}
+
+[INFO|trainer.py:3503] 2024-08-29 20:48:39,768 >> Saving model checkpoint to saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/checkpoint-100
+
+[INFO|configuration_utils.py:733] 2024-08-29 20:48:40,107 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-29 20:48:40,107 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|tokenization_utils_base.py:2702] 2024-08-29 20:48:40,206 >> tokenizer config file saved in saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/checkpoint-100/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2711] 2024-08-29 20:48:40,207 >> Special tokens file saved in saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/checkpoint-100/special_tokens_map.json
+
+[INFO|callbacks.py:319] 2024-08-29 20:49:36,953 >> {'loss': 0.5709, 'learning_rate': 7.2399e-06, 'epoch': 0.67, 'throughput': 2890.41}
+
+[INFO|callbacks.py:319] 2024-08-29 20:50:33,412 >> {'loss': 0.5555, 'learning_rate': 5.9889e-06, 'epoch': 0.70, 'throughput': 2890.93}
+
+[INFO|callbacks.py:319] 2024-08-29 20:51:29,876 >> {'loss': 0.5597, 'learning_rate': 4.8291e-06, 'epoch': 0.74, 'throughput': 2891.4}
+
+[INFO|callbacks.py:319] 2024-08-29 20:52:26,764 >> {'loss': 0.5432, 'learning_rate': 3.7723e-06, 'epoch': 0.77, 'throughput': 2890.92}
+
+[INFO|callbacks.py:319] 2024-08-29 20:53:23,270 >> {'loss': 0.5363, 'learning_rate': 2.8293e-06, 'epoch': 0.80, 'throughput': 2891.26}
+
+[INFO|callbacks.py:319] 2024-08-29 20:54:19,827 >> {'loss': 0.5582, 'learning_rate': 2.0096e-06, 'epoch': 0.83, 'throughput': 2891.48}
+
+[INFO|callbacks.py:319] 2024-08-29 20:55:16,550 >> {'loss': 0.5539, 'learning_rate': 1.3215e-06, 'epoch': 0.86, 'throughput': 2891.37}
+
+[INFO|callbacks.py:319] 2024-08-29 20:56:13,084 >> {'loss': 0.5529, 'learning_rate': 7.7195e-07, 'epoch': 0.90, 'throughput': 2891.6}
+
+[INFO|callbacks.py:319] 2024-08-29 20:57:09,602 >> {'loss': 0.5584, 'learning_rate': 3.6654e-07, 'epoch': 0.93, 'throughput': 2891.86}
+
+[INFO|callbacks.py:319] 2024-08-29 20:58:06,181 >> {'loss': 0.5503, 'learning_rate': 1.0937e-07, 'epoch': 0.96, 'throughput': 2891.99}
+
+[INFO|callbacks.py:319] 2024-08-29 20:59:02,816 >> {'loss': 0.5549, 'learning_rate': 3.0416e-09, 'epoch': 0.99, 'throughput': 2892.02}
+
+[INFO|trainer.py:3503] 2024-08-29 20:59:14,245 >> Saving model checkpoint to saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/checkpoint-156
+
+[INFO|configuration_utils.py:733] 2024-08-29 20:59:14,599 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-29 20:59:14,600 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|tokenization_utils_base.py:2702] 2024-08-29 20:59:14,671 >> tokenizer config file saved in saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/checkpoint-156/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2711] 2024-08-29 20:59:14,671 >> Special tokens file saved in saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/checkpoint-156/special_tokens_map.json
+
+[INFO|trainer.py:2394] 2024-08-29 20:59:14,879 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|trainer.py:3503] 2024-08-29 20:59:14,882 >> Saving model checkpoint to saves/Mistral-7B-v0.1-Chat/lora/mistral_physs
+
+[INFO|configuration_utils.py:733] 2024-08-29 20:59:15,109 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/2dcff66eac0c01dc50e4c41eea959968232187fe/config.json
+
+[INFO|configuration_utils.py:800] 2024-08-29 20:59:15,110 >> Model config MistralConfig {
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}
+
+
+[INFO|tokenization_utils_base.py:2702] 2024-08-29 20:59:15,181 >> tokenizer config file saved in saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2711] 2024-08-29 20:59:15,182 >> Special tokens file saved in saves/Mistral-7B-v0.1-Chat/lora/mistral_physs/special_tokens_map.json
+
+[WARNING|ploting.py:89] 2024-08-29 20:59:15,318 >> No metric eval_loss to plot.
+
+[WARNING|ploting.py:89] 2024-08-29 20:59:15,318 >> No metric eval_accuracy to plot.
+
+[INFO|modelcard.py:449] 2024-08-29 20:59:15,320 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9984,
+    "num_input_tokens_seen": 5111808,
+    "total_flos": 2.1873318928633037e+17,
+    "train_loss": 0.5760276004289969,
+    "train_runtime": 1768.2955,
+    "train_samples_per_second": 5.655,
+    "train_steps_per_second": 0.088
+}

trainer_log.jsonl

@@ -0,0 +1,32 @@
+{"current_steps": 5, "total_steps": 156, "loss": 0.678, "learning_rate": 2.9924022525939684e-05, "epoch": 0.032, "percentage": 3.21, "elapsed_time": "0:00:56", "remaining_time": "0:28:41", "throughput": 2874.51, "total_tokens": 163840}
+{"current_steps": 10, "total_steps": 156, "loss": 0.6551, "learning_rate": 2.9696859780634016e-05, "epoch": 0.064, "percentage": 6.41, "elapsed_time": "0:01:53", "remaining_time": "0:27:39", "throughput": 2882.14, "total_tokens": 327680}
+{"current_steps": 15, "total_steps": 156, "loss": 0.6372, "learning_rate": 2.9320812997628184e-05, "epoch": 0.096, "percentage": 9.62, "elapsed_time": "0:02:50", "remaining_time": "0:26:40", "throughput": 2885.94, "total_tokens": 491520}
+{"current_steps": 20, "total_steps": 156, "loss": 0.6201, "learning_rate": 2.8799691654882365e-05, "epoch": 0.128, "percentage": 12.82, "elapsed_time": "0:03:47", "remaining_time": "0:25:43", "throughput": 2886.5, "total_tokens": 655360}
+{"current_steps": 25, "total_steps": 156, "loss": 0.5965, "learning_rate": 2.8138774883503317e-05, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:04:43", "remaining_time": "0:24:45", "throughput": 2889.67, "total_tokens": 819200}
+{"current_steps": 30, "total_steps": 156, "loss": 0.5959, "learning_rate": 2.7344757988404845e-05, "epoch": 0.192, "percentage": 19.23, "elapsed_time": "0:05:40", "remaining_time": "0:23:48", "throughput": 2889.27, "total_tokens": 983040}
+{"current_steps": 35, "total_steps": 156, "loss": 0.6006, "learning_rate": 2.6425684622660387e-05, "epoch": 0.224, "percentage": 22.44, "elapsed_time": "0:06:36", "remaining_time": "0:22:51", "throughput": 2891.08, "total_tokens": 1146880}
+{"current_steps": 40, "total_steps": 156, "loss": 0.594, "learning_rate": 2.5390865302643993e-05, "epoch": 0.256, "percentage": 25.64, "elapsed_time": "0:07:33", "remaining_time": "0:21:54", "throughput": 2891.9, "total_tokens": 1310720}
+{"current_steps": 45, "total_steps": 156, "loss": 0.5825, "learning_rate": 2.425078308942815e-05, "epoch": 0.288, "percentage": 28.85, "elapsed_time": "0:08:29", "remaining_time": "0:20:57", "throughput": 2892.01, "total_tokens": 1474560}
+{"current_steps": 50, "total_steps": 156, "loss": 0.5871, "learning_rate": 2.3016987391917016e-05, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:09:26", "remaining_time": "0:20:01", "throughput": 2891.34, "total_tokens": 1638400}
+{"current_steps": 55, "total_steps": 156, "loss": 0.5771, "learning_rate": 2.1701976967524388e-05, "epoch": 0.352, "percentage": 35.26, "elapsed_time": "0:10:23", "remaining_time": "0:19:04", "throughput": 2890.51, "total_tokens": 1802240}
+{"current_steps": 60, "total_steps": 156, "loss": 0.5544, "learning_rate": 2.0319073305638035e-05, "epoch": 0.384, "percentage": 38.46, "elapsed_time": "0:11:19", "remaining_time": "0:18:07", "throughput": 2891.57, "total_tokens": 1966080}
+{"current_steps": 65, "total_steps": 156, "loss": 0.5768, "learning_rate": 1.888228567653781e-05, "epoch": 0.416, "percentage": 41.67, "elapsed_time": "0:12:16", "remaining_time": "0:17:11", "throughput": 2892.08, "total_tokens": 2129920}
+{"current_steps": 70, "total_steps": 156, "loss": 0.5534, "learning_rate": 1.7406169212866405e-05, "epoch": 0.448, "percentage": 44.87, "elapsed_time": "0:13:13", "remaining_time": "0:16:14", "throughput": 2891.55, "total_tokens": 2293760}
+{"current_steps": 75, "total_steps": 156, "loss": 0.5597, "learning_rate": 1.5905677461334292e-05, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:14:09", "remaining_time": "0:15:17", "throughput": 2891.32, "total_tokens": 2457600}
+{"current_steps": 80, "total_steps": 156, "loss": 0.571, "learning_rate": 1.4396010898358778e-05, "epoch": 0.512, "percentage": 51.28, "elapsed_time": "0:15:06", "remaining_time": "0:14:21", "throughput": 2891.43, "total_tokens": 2621440}
+{"current_steps": 85, "total_steps": 156, "loss": 0.5572, "learning_rate": 1.2892462944223613e-05, "epoch": 0.544, "percentage": 54.49, "elapsed_time": "0:16:03", "remaining_time": "0:13:24", "throughput": 2891.18, "total_tokens": 2785280}
+{"current_steps": 90, "total_steps": 156, "loss": 0.5686, "learning_rate": 1.1410265035686639e-05, "epoch": 0.576, "percentage": 57.69, "elapsed_time": "0:16:59", "remaining_time": "0:12:27", "throughput": 2892.41, "total_tokens": 2949120}
+{"current_steps": 95, "total_steps": 156, "loss": 0.5525, "learning_rate": 9.964432326500933e-06, "epoch": 0.608, "percentage": 60.9, "elapsed_time": "0:17:56", "remaining_time": "0:11:31", "throughput": 2892.02, "total_tokens": 3112960}
+{"current_steps": 100, "total_steps": 156, "loss": 0.5594, "learning_rate": 8.569611578954186e-06, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:18:53", "remaining_time": "0:10:34", "throughput": 2891.69, "total_tokens": 3276800}
+{"current_steps": 105, "total_steps": 156, "loss": 0.5709, "learning_rate": 7.239932787335147e-06, "epoch": 0.672, "percentage": 67.31, "elapsed_time": "0:19:50", "remaining_time": "0:09:38", "throughput": 2890.41, "total_tokens": 3440640}
+{"current_steps": 110, "total_steps": 156, "loss": 0.5555, "learning_rate": 5.988866036430314e-06, "epoch": 0.704, "percentage": 70.51, "elapsed_time": "0:20:46", "remaining_time": "0:08:41", "throughput": 2890.93, "total_tokens": 3604480}
+{"current_steps": 115, "total_steps": 156, "loss": 0.5597, "learning_rate": 4.829085045121636e-06, "epoch": 0.736, "percentage": 73.72, "elapsed_time": "0:21:43", "remaining_time": "0:07:44", "throughput": 2891.4, "total_tokens": 3768320}
+{"current_steps": 120, "total_steps": 156, "loss": 0.5432, "learning_rate": 3.772338777433482e-06, "epoch": 0.768, "percentage": 76.92, "elapsed_time": "0:22:40", "remaining_time": "0:06:48", "throughput": 2890.92, "total_tokens": 3932160}
+{"current_steps": 125, "total_steps": 156, "loss": 0.5363, "learning_rate": 2.829332421651404e-06, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:23:36", "remaining_time": "0:05:51", "throughput": 2891.26, "total_tokens": 4096000}
+{"current_steps": 130, "total_steps": 156, "loss": 0.5582, "learning_rate": 2.0096189432334194e-06, "epoch": 0.832, "percentage": 83.33, "elapsed_time": "0:24:33", "remaining_time": "0:04:54", "throughput": 2891.48, "total_tokens": 4259840}
+{"current_steps": 135, "total_steps": 156, "loss": 0.5539, "learning_rate": 1.321502310118649e-06, "epoch": 0.864, "percentage": 86.54, "elapsed_time": "0:25:29", "remaining_time": "0:03:57", "throughput": 2891.37, "total_tokens": 4423680}
+{"current_steps": 140, "total_steps": 156, "loss": 0.5529, "learning_rate": 7.719533707928178e-07, "epoch": 0.896, "percentage": 89.74, "elapsed_time": "0:26:26", "remaining_time": "0:03:01", "throughput": 2891.6, "total_tokens": 4587520}
+{"current_steps": 145, "total_steps": 156, "loss": 0.5584, "learning_rate": 3.665392372935922e-07, "epoch": 0.928, "percentage": 92.95, "elapsed_time": "0:27:23", "remaining_time": "0:02:04", "throughput": 2891.86, "total_tokens": 4751360}
+{"current_steps": 150, "total_steps": 156, "loss": 0.5503, "learning_rate": 1.0936688852919042e-07, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:28:19", "remaining_time": "0:01:07", "throughput": 2891.99, "total_tokens": 4915200}
+{"current_steps": 155, "total_steps": 156, "loss": 0.5549, "learning_rate": 3.0415652272480776e-09, "epoch": 0.992, "percentage": 99.36, "elapsed_time": "0:29:16", "remaining_time": "0:00:11", "throughput": 2892.02, "total_tokens": 5079040}
+{"current_steps": 156, "total_steps": 156, "epoch": 0.9984, "percentage": 100.0, "elapsed_time": "0:29:28", "remaining_time": "0:00:00", "throughput": 2890.82, "total_tokens": 5111808}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.3039781153202057,
+      "learning_rate": 2.9924022525939684e-05,
+      "loss": 0.678,
+      "num_input_tokens_seen": 163840,
+      "step": 5
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.2683364450931549,
+      "learning_rate": 2.9696859780634016e-05,
+      "loss": 0.6551,
+      "num_input_tokens_seen": 327680,
+      "step": 10
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.246008038520813,
+      "learning_rate": 2.9320812997628184e-05,
+      "loss": 0.6372,
+      "num_input_tokens_seen": 491520,
+      "step": 15
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.23320266604423523,
+      "learning_rate": 2.8799691654882365e-05,
+      "loss": 0.6201,
+      "num_input_tokens_seen": 655360,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.24441155791282654,
+      "learning_rate": 2.8138774883503317e-05,
+      "loss": 0.5965,
+      "num_input_tokens_seen": 819200,
+      "step": 25
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.2341088205575943,
+      "learning_rate": 2.7344757988404845e-05,
+      "loss": 0.5959,
+      "num_input_tokens_seen": 983040,
+      "step": 30
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.23481066524982452,
+      "learning_rate": 2.6425684622660387e-05,
+      "loss": 0.6006,
+      "num_input_tokens_seen": 1146880,
+      "step": 35
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.2456846982240677,
+      "learning_rate": 2.5390865302643993e-05,
+      "loss": 0.594,
+      "num_input_tokens_seen": 1310720,
+      "step": 40
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.25728079676628113,
+      "learning_rate": 2.425078308942815e-05,
+      "loss": 0.5825,
+      "num_input_tokens_seen": 1474560,
+      "step": 45
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2505452334880829,
+      "learning_rate": 2.3016987391917016e-05,
+      "loss": 0.5871,
+      "num_input_tokens_seen": 1638400,
+      "step": 50
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.27519550919532776,
+      "learning_rate": 2.1701976967524388e-05,
+      "loss": 0.5771,
+      "num_input_tokens_seen": 1802240,
+      "step": 55
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.2705497741699219,
+      "learning_rate": 2.0319073305638035e-05,
+      "loss": 0.5544,
+      "num_input_tokens_seen": 1966080,
+      "step": 60
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.2861919701099396,
+      "learning_rate": 1.888228567653781e-05,
+      "loss": 0.5768,
+      "num_input_tokens_seen": 2129920,
+      "step": 65
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.29395216703414917,
+      "learning_rate": 1.7406169212866405e-05,
+      "loss": 0.5534,
+      "num_input_tokens_seen": 2293760,
+      "step": 70
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.285727322101593,
+      "learning_rate": 1.5905677461334292e-05,
+      "loss": 0.5597,
+      "num_input_tokens_seen": 2457600,
+      "step": 75
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.30645114183425903,
+      "learning_rate": 1.4396010898358778e-05,
+      "loss": 0.571,
+      "num_input_tokens_seen": 2621440,
+      "step": 80
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.2912521958351135,
+      "learning_rate": 1.2892462944223613e-05,
+      "loss": 0.5572,
+      "num_input_tokens_seen": 2785280,
+      "step": 85
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.3027022182941437,
+      "learning_rate": 1.1410265035686639e-05,
+      "loss": 0.5686,
+      "num_input_tokens_seen": 2949120,
+      "step": 90
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.32110294699668884,
+      "learning_rate": 9.964432326500933e-06,
+      "loss": 0.5525,
+      "num_input_tokens_seen": 3112960,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.31834056973457336,
+      "learning_rate": 8.569611578954186e-06,
+      "loss": 0.5594,
+      "num_input_tokens_seen": 3276800,
+      "step": 100
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.3223641812801361,
+      "learning_rate": 7.239932787335147e-06,
+      "loss": 0.5709,
+      "num_input_tokens_seen": 3440640,
+      "step": 105
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.32236120104789734,
+      "learning_rate": 5.988866036430314e-06,
+      "loss": 0.5555,
+      "num_input_tokens_seen": 3604480,
+      "step": 110
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.32125550508499146,
+      "learning_rate": 4.829085045121636e-06,
+      "loss": 0.5597,
+      "num_input_tokens_seen": 3768320,
+      "step": 115
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.325810968875885,
+      "learning_rate": 3.772338777433482e-06,
+      "loss": 0.5432,
+      "num_input_tokens_seen": 3932160,
+      "step": 120
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.32014375925064087,
+      "learning_rate": 2.829332421651404e-06,
+      "loss": 0.5363,
+      "num_input_tokens_seen": 4096000,
+      "step": 125
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.32001549005508423,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.5582,
+      "num_input_tokens_seen": 4259840,
+      "step": 130
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.33245849609375,
+      "learning_rate": 1.321502310118649e-06,
+      "loss": 0.5539,
+      "num_input_tokens_seen": 4423680,
+      "step": 135
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.3493448495864868,
+      "learning_rate": 7.719533707928178e-07,
+      "loss": 0.5529,
+      "num_input_tokens_seen": 4587520,
+      "step": 140
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.3279431462287903,
+      "learning_rate": 3.665392372935922e-07,
+      "loss": 0.5584,
+      "num_input_tokens_seen": 4751360,
+      "step": 145
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3298741281032562,
+      "learning_rate": 1.0936688852919042e-07,
+      "loss": 0.5503,
+      "num_input_tokens_seen": 4915200,
+      "step": 150
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.33253204822540283,
+      "learning_rate": 3.0415652272480776e-09,
+      "loss": 0.5549,
+      "num_input_tokens_seen": 5079040,
+      "step": 155
+    },
+    {
+      "epoch": 0.9984,
+      "num_input_tokens_seen": 5111808,
+      "step": 156,
+      "total_flos": 2.1873318928633037e+17,
+      "train_loss": 0.5760276004289969,
+      "train_runtime": 1768.2955,
+      "train_samples_per_second": 5.655,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 156,
+  "num_input_tokens_seen": 5111808,
+  "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": 2.1873318928633037e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d873c6ea94c48195922f46796afd4fcd5262029afc0aa21fb929e23ac19d481
+size 5368

training_args.yaml

@@ -0,0 +1,32 @@
+cutoff_len: 512
+dataset: physics
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+fp16: true
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 3.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 10000
+model_name_or_path: mistralai/Mistral-7B-Instruct-v0.1
+num_train_epochs: 1.0
+optim: adamw_torch
+output_dir: saves/Mistral-7B-v0.1-Chat/lora/mistral_physs
+packing: false
+per_device_train_batch_size: 8
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+template: mistral
+warmup_steps: 0