Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-7B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2025-04-10-02-02-13
+  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. -->
+
+# train_2025-04-10-02-02-13
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the Catsith dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.1
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.4.1
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a84df822da40c46ef05d995091d78db52cd42a1b78456d26f6b2fd5847c1267
+size 80792096

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9950248756218905,
+    "num_input_tokens_seen": 489472,
+    "total_flos": 2.082450075077837e+16,
+    "train_loss": 3.2915359853108725,
+    "train_runtime": 1375.5479,
+    "train_samples_per_second": 4.382,
+    "train_steps_per_second": 0.273
+}

llamaboard_config.yaml

@@ -0,0 +1,78 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen2.5-7B
+top.quantization_bit: none
+top.quantization_method: bnb
+top.rope_scaling: none
+top.template: default
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- Catsith
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-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: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+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:
+- none
+train.resize_vocab: false
+train.reward_model: []
+train.save_steps: 100
+train.swanlab_api_key: ''
+train.swanlab_link: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: false
+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.use_swanlab: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,522 @@
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/vocab.json
+
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/merges.txt
+
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/tokenizer.json
+
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/tokenizer_config.json
+
+[INFO|2025-04-10 02:12:51] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2313 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-04-10 02:12:52] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:12:52] configuration_utils.py:771 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/vocab.json
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/merges.txt
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/tokenizer.json
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/tokenizer_config.json
+
+[INFO|2025-04-10 02:12:52] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-04-10 02:12:53] tokenization_utils_base.py:2313 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-04-10 02:12:53] logging.py:143 >> Loading dataset catsith_output.json...
+
+[INFO|2025-04-10 02:12:58] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:12:58] configuration_utils.py:771 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:12:58] logging.py:143 >> KV cache is disabled during training.
+
+[INFO|2025-04-10 02:12:58] modeling_utils.py:3982 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/model.safetensors.index.json
+
+[INFO|2025-04-10 02:12:58] modeling_utils.py:1633 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-04-10 02:12:58] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "use_cache": false
+}
+
+
+[WARNING|2025-04-10 02:12:58] logging.py:329 >> Sliding Window Attention is enabled but not implemented for `sdpa`; unexpected results may be encountered.
+
+[INFO|2025-04-10 02:13:05] modeling_utils.py:4970 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+[INFO|2025-04-10 02:13:05] modeling_utils.py:4978 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-7B.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+[INFO|2025-04-10 02:13:05] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/generation_config.json
+
+[INFO|2025-04-10 02:13:05] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048
+}
+
+
+[INFO|2025-04-10 02:13:05] logging.py:143 >> Gradient checkpointing enabled.
+
+[INFO|2025-04-10 02:13:05] logging.py:143 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-04-10 02:13:05] logging.py:143 >> Upcasting trainable params to float32.
+
+[INFO|2025-04-10 02:13:05] logging.py:143 >> Fine-tuning method: LoRA
+
+[INFO|2025-04-10 02:13:05] logging.py:143 >> Found linear modules: v_proj,k_proj,gate_proj,down_proj,up_proj,q_proj,o_proj
+
+[INFO|2025-04-10 02:13:06] logging.py:143 >> trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+
+[INFO|2025-04-10 02:13:06] trainer.py:746 >> Using auto half precision backend
+
+[WARNING|2025-04-10 02:13:06] trainer.py:781 >> No label_names provided for model class `PeftModelForCausalLM`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.
+
+[INFO|2025-04-10 02:13:06] trainer.py:2405 >> ***** Running training *****
+
+[INFO|2025-04-10 02:13:06] trainer.py:2406 >>   Num examples = 2,009
+
+[INFO|2025-04-10 02:13:06] trainer.py:2407 >>   Num Epochs = 3
+
+[INFO|2025-04-10 02:13:06] trainer.py:2408 >>   Instantaneous batch size per device = 2
+
+[INFO|2025-04-10 02:13:06] trainer.py:2411 >>   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+[INFO|2025-04-10 02:13:06] trainer.py:2412 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-04-10 02:13:06] trainer.py:2413 >>   Total optimization steps = 375
+
+[INFO|2025-04-10 02:13:06] trainer.py:2414 >>   Number of trainable parameters = 20,185,088
+
+[INFO|2025-04-10 02:13:25] logging.py:143 >> {'loss': 4.5494, 'learning_rate': 4.9978e-05, 'epoch': 0.04, 'throughput': 416.59}
+
+[INFO|2025-04-10 02:13:43] logging.py:143 >> {'loss': 4.5269, 'learning_rate': 4.9912e-05, 'epoch': 0.08, 'throughput': 375.28}
+
+[INFO|2025-04-10 02:14:01] logging.py:143 >> {'loss': 4.0421, 'learning_rate': 4.9803e-05, 'epoch': 0.12, 'throughput': 376.49}
+
+[INFO|2025-04-10 02:14:20] logging.py:143 >> {'loss': 3.8231, 'learning_rate': 4.9650e-05, 'epoch': 0.16, 'throughput': 390.13}
+
+[INFO|2025-04-10 02:14:38] logging.py:143 >> {'loss': 3.5978, 'learning_rate': 4.9454e-05, 'epoch': 0.20, 'throughput': 372.36}
+
+[INFO|2025-04-10 02:14:56] logging.py:143 >> {'loss': 3.5563, 'learning_rate': 4.9215e-05, 'epoch': 0.24, 'throughput': 358.30}
+
+[INFO|2025-04-10 02:15:14] logging.py:143 >> {'loss': 3.7193, 'learning_rate': 4.8933e-05, 'epoch': 0.28, 'throughput': 353.55}
+
+[INFO|2025-04-10 02:15:32] logging.py:143 >> {'loss': 3.4887, 'learning_rate': 4.8609e-05, 'epoch': 0.32, 'throughput': 350.40}
+
+[INFO|2025-04-10 02:15:50] logging.py:143 >> {'loss': 3.4482, 'learning_rate': 4.8244e-05, 'epoch': 0.36, 'throughput': 346.39}
+
+[INFO|2025-04-10 02:16:08] logging.py:143 >> {'loss': 3.5251, 'learning_rate': 4.7839e-05, 'epoch': 0.40, 'throughput': 339.62}
+
+[INFO|2025-04-10 02:16:26] logging.py:143 >> {'loss': 3.4091, 'learning_rate': 4.7393e-05, 'epoch': 0.44, 'throughput': 344.36}
+
+[INFO|2025-04-10 02:16:45] logging.py:143 >> {'loss': 3.4556, 'learning_rate': 4.6908e-05, 'epoch': 0.48, 'throughput': 351.95}
+
+[INFO|2025-04-10 02:17:03] logging.py:143 >> {'loss': 3.3753, 'learning_rate': 4.6384e-05, 'epoch': 0.52, 'throughput': 355.56}
+
+[INFO|2025-04-10 02:17:22] logging.py:143 >> {'loss': 3.3786, 'learning_rate': 4.5823e-05, 'epoch': 0.56, 'throughput': 353.28}
+
+[INFO|2025-04-10 02:17:40] logging.py:143 >> {'loss': 3.4089, 'learning_rate': 4.5225e-05, 'epoch': 0.60, 'throughput': 349.53}
+
+[INFO|2025-04-10 02:17:58] logging.py:143 >> {'loss': 3.4508, 'learning_rate': 4.4592e-05, 'epoch': 0.64, 'throughput': 352.33}
+
+[INFO|2025-04-10 02:18:16] logging.py:143 >> {'loss': 3.3330, 'learning_rate': 4.3925e-05, 'epoch': 0.68, 'throughput': 353.37}
+
+[INFO|2025-04-10 02:18:35] logging.py:143 >> {'loss': 3.3651, 'learning_rate': 4.3224e-05, 'epoch': 0.72, 'throughput': 357.01}
+
+[INFO|2025-04-10 02:18:52] logging.py:143 >> {'loss': 3.2850, 'learning_rate': 4.2492e-05, 'epoch': 0.76, 'throughput': 355.97}
+
+[INFO|2025-04-10 02:19:10] logging.py:143 >> {'loss': 3.3726, 'learning_rate': 4.1728e-05, 'epoch': 0.80, 'throughput': 356.11}
+
+[INFO|2025-04-10 02:19:10] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-100
+
+[INFO|2025-04-10 02:19:11] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:19:11] configuration_utils.py:771 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:19:11] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-100/tokenizer_config.json
+
+[INFO|2025-04-10 02:19:11] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-100/special_tokens_map.json
+
+[INFO|2025-04-10 02:19:30] logging.py:143 >> {'loss': 3.3490, 'learning_rate': 4.0936e-05, 'epoch': 0.84, 'throughput': 360.08}
+
+[INFO|2025-04-10 02:19:48] logging.py:143 >> {'loss': 3.3335, 'learning_rate': 4.0115e-05, 'epoch': 0.88, 'throughput': 358.69}
+
+[INFO|2025-04-10 02:20:06] logging.py:143 >> {'loss': 3.3096, 'learning_rate': 3.9268e-05, 'epoch': 0.92, 'throughput': 356.95}
+
+[INFO|2025-04-10 02:20:24] logging.py:143 >> {'loss': 3.2696, 'learning_rate': 3.8396e-05, 'epoch': 0.96, 'throughput': 354.39}
+
+[INFO|2025-04-10 02:20:43] logging.py:143 >> {'loss': 3.3071, 'learning_rate': 3.7500e-05, 'epoch': 1.00, 'throughput': 357.59}
+
+[INFO|2025-04-10 02:21:01] logging.py:143 >> {'loss': 3.8956, 'learning_rate': 3.6582e-05, 'epoch': 1.04, 'throughput': 355.28}
+
+[INFO|2025-04-10 02:21:19] logging.py:143 >> {'loss': 3.2505, 'learning_rate': 3.5644e-05, 'epoch': 1.08, 'throughput': 353.84}
+
+[INFO|2025-04-10 02:21:38] logging.py:143 >> {'loss': 3.2490, 'learning_rate': 3.4688e-05, 'epoch': 1.12, 'throughput': 355.97}
+
+[INFO|2025-04-10 02:21:56] logging.py:143 >> {'loss': 3.1777, 'learning_rate': 3.3714e-05, 'epoch': 1.16, 'throughput': 354.36}
+
+[INFO|2025-04-10 02:22:14] logging.py:143 >> {'loss': 3.2005, 'learning_rate': 3.2725e-05, 'epoch': 1.20, 'throughput': 354.54}
+
+[INFO|2025-04-10 02:22:32] logging.py:143 >> {'loss': 3.1882, 'learning_rate': 3.1723e-05, 'epoch': 1.24, 'throughput': 356.67}
+
+[INFO|2025-04-10 02:22:50] logging.py:143 >> {'loss': 3.2861, 'learning_rate': 3.0709e-05, 'epoch': 1.28, 'throughput': 354.95}
+
+[INFO|2025-04-10 02:23:08] logging.py:143 >> {'loss': 3.2012, 'learning_rate': 2.9685e-05, 'epoch': 1.32, 'throughput': 352.93}
+
+[INFO|2025-04-10 02:23:27] logging.py:143 >> {'loss': 3.1424, 'learning_rate': 2.8652e-05, 'epoch': 1.36, 'throughput': 353.98}
+
+[INFO|2025-04-10 02:23:45] logging.py:143 >> {'loss': 3.1061, 'learning_rate': 2.7613e-05, 'epoch': 1.40, 'throughput': 351.42}
+
+[INFO|2025-04-10 02:24:04] logging.py:143 >> {'loss': 3.1739, 'learning_rate': 2.6570e-05, 'epoch': 1.44, 'throughput': 352.41}
+
+[INFO|2025-04-10 02:24:22] logging.py:143 >> {'loss': 3.1692, 'learning_rate': 2.5524e-05, 'epoch': 1.48, 'throughput': 353.70}
+
+[INFO|2025-04-10 02:24:41] logging.py:143 >> {'loss': 3.2116, 'learning_rate': 2.4476e-05, 'epoch': 1.52, 'throughput': 355.00}
+
+[INFO|2025-04-10 02:24:58] logging.py:143 >> {'loss': 3.3134, 'learning_rate': 2.3430e-05, 'epoch': 1.56, 'throughput': 355.61}
+
+[INFO|2025-04-10 02:25:17] logging.py:143 >> {'loss': 3.2215, 'learning_rate': 2.2387e-05, 'epoch': 1.60, 'throughput': 356.20}
+
+[INFO|2025-04-10 02:25:17] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-200
+
+[INFO|2025-04-10 02:25:17] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:25:17] configuration_utils.py:771 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:25:17] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-200/tokenizer_config.json
+
+[INFO|2025-04-10 02:25:17] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-200/special_tokens_map.json
+
+[INFO|2025-04-10 02:25:36] logging.py:143 >> {'loss': 3.0594, 'learning_rate': 2.1348e-05, 'epoch': 1.64, 'throughput': 354.14}
+
+[INFO|2025-04-10 02:25:55] logging.py:143 >> {'loss': 3.1452, 'learning_rate': 2.0315e-05, 'epoch': 1.68, 'throughput': 356.32}
+
+[INFO|2025-04-10 02:26:14] logging.py:143 >> {'loss': 3.2481, 'learning_rate': 1.9291e-05, 'epoch': 1.72, 'throughput': 356.70}
+
+[INFO|2025-04-10 02:26:34] logging.py:143 >> {'loss': 3.1269, 'learning_rate': 1.8277e-05, 'epoch': 1.76, 'throughput': 359.85}
+
+[INFO|2025-04-10 02:26:52] logging.py:143 >> {'loss': 3.1888, 'learning_rate': 1.7275e-05, 'epoch': 1.80, 'throughput': 360.92}
+
+[INFO|2025-04-10 02:27:10] logging.py:143 >> {'loss': 3.2137, 'learning_rate': 1.6286e-05, 'epoch': 1.84, 'throughput': 359.60}
+
+[INFO|2025-04-10 02:27:28] logging.py:143 >> {'loss': 3.1926, 'learning_rate': 1.5312e-05, 'epoch': 1.88, 'throughput': 358.00}
+
+[INFO|2025-04-10 02:27:46] logging.py:143 >> {'loss': 3.2949, 'learning_rate': 1.4356e-05, 'epoch': 1.92, 'throughput': 357.75}
+
+[INFO|2025-04-10 02:28:04] logging.py:143 >> {'loss': 3.1559, 'learning_rate': 1.3418e-05, 'epoch': 1.96, 'throughput': 356.64}
+
+[INFO|2025-04-10 02:28:22] logging.py:143 >> {'loss': 3.1411, 'learning_rate': 1.2500e-05, 'epoch': 2.00, 'throughput': 355.99}
+
+[INFO|2025-04-10 02:28:40] logging.py:143 >> {'loss': 3.5418, 'learning_rate': 1.1604e-05, 'epoch': 2.04, 'throughput': 354.77}
+
+[INFO|2025-04-10 02:28:58] logging.py:143 >> {'loss': 3.0061, 'learning_rate': 1.0732e-05, 'epoch': 2.08, 'throughput': 354.05}
+
+[INFO|2025-04-10 02:29:16] logging.py:143 >> {'loss': 3.1020, 'learning_rate': 9.8850e-06, 'epoch': 2.12, 'throughput': 352.60}
+
+[INFO|2025-04-10 02:29:34] logging.py:143 >> {'loss': 2.9862, 'learning_rate': 9.0644e-06, 'epoch': 2.16, 'throughput': 351.35}
+
+[INFO|2025-04-10 02:29:53] logging.py:143 >> {'loss': 3.0803, 'learning_rate': 8.2717e-06, 'epoch': 2.20, 'throughput': 352.72}
+
+[INFO|2025-04-10 02:30:11] logging.py:143 >> {'loss': 3.1944, 'learning_rate': 7.5084e-06, 'epoch': 2.24, 'throughput': 352.51}
+
+[INFO|2025-04-10 02:30:29] logging.py:143 >> {'loss': 3.1717, 'learning_rate': 6.7758e-06, 'epoch': 2.28, 'throughput': 354.26}
+
+[INFO|2025-04-10 02:30:49] logging.py:143 >> {'loss': 3.2106, 'learning_rate': 6.0751e-06, 'epoch': 2.32, 'throughput': 355.43}
+
+[INFO|2025-04-10 02:31:07] logging.py:143 >> {'loss': 3.0577, 'learning_rate': 5.4077e-06, 'epoch': 2.36, 'throughput': 356.33}
+
+[INFO|2025-04-10 02:31:25] logging.py:143 >> {'loss': 3.1227, 'learning_rate': 4.7746e-06, 'epoch': 2.40, 'throughput': 356.28}
+
+[INFO|2025-04-10 02:31:25] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-300
+
+[INFO|2025-04-10 02:31:25] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:31:25] configuration_utils.py:771 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:31:25] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-300/tokenizer_config.json
+
+[INFO|2025-04-10 02:31:25] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-300/special_tokens_map.json
+
+[INFO|2025-04-10 02:31:44] logging.py:143 >> {'loss': 3.1015, 'learning_rate': 4.1770e-06, 'epoch': 2.44, 'throughput': 355.52}
+
+[INFO|2025-04-10 02:32:02] logging.py:143 >> {'loss': 3.0393, 'learning_rate': 3.6159e-06, 'epoch': 2.48, 'throughput': 355.42}
+
+[INFO|2025-04-10 02:32:20] logging.py:143 >> {'loss': 2.9964, 'learning_rate': 3.0923e-06, 'epoch': 2.52, 'throughput': 354.97}
+
+[INFO|2025-04-10 02:32:38] logging.py:143 >> {'loss': 3.1617, 'learning_rate': 2.6072e-06, 'epoch': 2.56, 'throughput': 355.40}
+
+[INFO|2025-04-10 02:32:58] logging.py:143 >> {'loss': 3.0388, 'learning_rate': 2.1614e-06, 'epoch': 2.60, 'throughput': 356.66}
+
+[INFO|2025-04-10 02:33:16] logging.py:143 >> {'loss': 3.1580, 'learning_rate': 1.7556e-06, 'epoch': 2.64, 'throughput': 356.13}
+
+[INFO|2025-04-10 02:33:34] logging.py:143 >> {'loss': 3.0348, 'learning_rate': 1.3906e-06, 'epoch': 2.68, 'throughput': 356.25}
+
+[INFO|2025-04-10 02:33:52] logging.py:143 >> {'loss': 3.1515, 'learning_rate': 1.0670e-06, 'epoch': 2.72, 'throughput': 355.61}
+
+[INFO|2025-04-10 02:34:11] logging.py:143 >> {'loss': 3.0978, 'learning_rate': 7.8542e-07, 'epoch': 2.76, 'throughput': 356.26}
+
+[INFO|2025-04-10 02:34:29] logging.py:143 >> {'loss': 3.0510, 'learning_rate': 5.4631e-07, 'epoch': 2.80, 'throughput': 356.49}
+
+[INFO|2025-04-10 02:34:47] logging.py:143 >> {'loss': 3.0632, 'learning_rate': 3.5010e-07, 'epoch': 2.84, 'throughput': 356.36}
+
+[INFO|2025-04-10 02:35:05] logging.py:143 >> {'loss': 3.0875, 'learning_rate': 1.9713e-07, 'epoch': 2.88, 'throughput': 355.21}
+
+[INFO|2025-04-10 02:35:23] logging.py:143 >> {'loss': 3.1218, 'learning_rate': 8.7679e-08, 'epoch': 2.92, 'throughput': 356.10}
+
+[INFO|2025-04-10 02:35:42] logging.py:143 >> {'loss': 3.0581, 'learning_rate': 2.1929e-08, 'epoch': 2.96, 'throughput': 357.04}
+
+[INFO|2025-04-10 02:36:00] logging.py:143 >> {'loss': 2.9967, 'learning_rate': 0.0000e+00, 'epoch': 3.00, 'throughput': 356.12}
+
+[INFO|2025-04-10 02:36:00] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-375
+
+[INFO|2025-04-10 02:36:01] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:36:01] configuration_utils.py:771 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:36:01] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-375/tokenizer_config.json
+
+[INFO|2025-04-10 02:36:01] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/checkpoint-375/special_tokens_map.json
+
+[INFO|2025-04-10 02:36:02] trainer.py:2657 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-04-10 02:36:02] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13
+
+[INFO|2025-04-10 02:36:02] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2.5-7B/snapshots/d149729398750b98c0af14eb82c78cfe92750796/config.json
+
+[INFO|2025-04-10 02:36:02] configuration_utils.py:771 >> Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-04-10 02:36:02] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/tokenizer_config.json
+
+[INFO|2025-04-10 02:36:02] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13/special_tokens_map.json
+
+[WARNING|2025-04-10 02:36:02] logging.py:148 >> No metric eval_loss to plot.
+
+[WARNING|2025-04-10 02:36:02] logging.py:148 >> No metric eval_accuracy to plot.
+
+[INFO|2025-04-10 02:36:02] modelcard.py:449 >> 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 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% 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: ' + system_message + '<|endoftext|>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9950248756218905,
+    "num_input_tokens_seen": 489472,
+    "total_flos": 2.082450075077837e+16,
+    "train_loss": 3.2915359853108725,
+    "train_runtime": 1375.5479,
+    "train_samples_per_second": 4.382,
+    "train_steps_per_second": 0.273
+}

trainer_log.jsonl

@@ -0,0 +1,76 @@
+{"current_steps": 5, "total_steps": 375, "loss": 4.5494, "lr": 4.997807075247146e-05, "epoch": 0.03980099502487562, "percentage": 1.33, "elapsed_time": "0:00:19", "remaining_time": "0:23:49", "throughput": 416.59, "total_tokens": 8048}
+{"current_steps": 10, "total_steps": 375, "loss": 4.5269, "lr": 4.991232148123761e-05, "epoch": 0.07960199004975124, "percentage": 2.67, "elapsed_time": "0:00:37", "remaining_time": "0:22:41", "throughput": 375.28, "total_tokens": 14000}
+{"current_steps": 15, "total_steps": 375, "loss": 4.0421, "lr": 4.980286753286195e-05, "epoch": 0.11940298507462686, "percentage": 4.0, "elapsed_time": "0:00:55", "remaining_time": "0:22:05", "throughput": 376.49, "total_tokens": 20800}
+{"current_steps": 20, "total_steps": 375, "loss": 3.8231, "lr": 4.964990092676263e-05, "epoch": 0.15920398009950248, "percentage": 5.33, "elapsed_time": "0:01:14", "remaining_time": "0:21:59", "throughput": 390.13, "total_tokens": 28992}
+{"current_steps": 25, "total_steps": 375, "loss": 3.5978, "lr": 4.9453690018345144e-05, "epoch": 0.19900497512437812, "percentage": 6.67, "elapsed_time": "0:01:32", "remaining_time": "0:21:30", "throughput": 372.36, "total_tokens": 34336}
+{"current_steps": 30, "total_steps": 375, "loss": 3.5563, "lr": 4.9214579028215776e-05, "epoch": 0.23880597014925373, "percentage": 8.0, "elapsed_time": "0:01:50", "remaining_time": "0:21:06", "throughput": 358.3, "total_tokens": 39456}
+{"current_steps": 35, "total_steps": 375, "loss": 3.7193, "lr": 4.893298743830168e-05, "epoch": 0.27860696517412936, "percentage": 9.33, "elapsed_time": "0:02:08", "remaining_time": "0:20:44", "throughput": 353.55, "total_tokens": 45280}
+{"current_steps": 40, "total_steps": 375, "loss": 3.4887, "lr": 4.860940925593703e-05, "epoch": 0.31840796019900497, "percentage": 10.67, "elapsed_time": "0:02:25", "remaining_time": "0:20:21", "throughput": 350.4, "total_tokens": 51104}
+{"current_steps": 45, "total_steps": 375, "loss": 3.4482, "lr": 4.8244412147206284e-05, "epoch": 0.3582089552238806, "percentage": 12.0, "elapsed_time": "0:02:43", "remaining_time": "0:19:59", "throughput": 346.39, "total_tokens": 56672}
+{"current_steps": 50, "total_steps": 375, "loss": 3.5251, "lr": 4.783863644106502e-05, "epoch": 0.39800995024875624, "percentage": 13.33, "elapsed_time": "0:03:01", "remaining_time": "0:19:40", "throughput": 339.62, "total_tokens": 61680}
+{"current_steps": 55, "total_steps": 375, "loss": 3.4091, "lr": 4.7392794005985326e-05, "epoch": 0.43781094527363185, "percentage": 14.67, "elapsed_time": "0:03:20", "remaining_time": "0:19:24", "throughput": 344.36, "total_tokens": 68928}
+{"current_steps": 60, "total_steps": 375, "loss": 3.4556, "lr": 4.690766700109659e-05, "epoch": 0.47761194029850745, "percentage": 16.0, "elapsed_time": "0:03:38", "remaining_time": "0:19:09", "throughput": 351.95, "total_tokens": 77056}
+{"current_steps": 65, "total_steps": 375, "loss": 3.3753, "lr": 4.638410650401267e-05, "epoch": 0.5174129353233831, "percentage": 17.33, "elapsed_time": "0:03:57", "remaining_time": "0:18:51", "throughput": 355.56, "total_tokens": 84368}
+{"current_steps": 70, "total_steps": 375, "loss": 3.3786, "lr": 4.5823031017752485e-05, "epoch": 0.5572139303482587, "percentage": 18.67, "elapsed_time": "0:04:15", "remaining_time": "0:18:33", "throughput": 353.28, "total_tokens": 90272}
+{"current_steps": 75, "total_steps": 375, "loss": 3.4089, "lr": 4.522542485937369e-05, "epoch": 0.5970149253731343, "percentage": 20.0, "elapsed_time": "0:04:33", "remaining_time": "0:18:14", "throughput": 349.53, "total_tokens": 95600}
+{"current_steps": 80, "total_steps": 375, "loss": 3.4508, "lr": 4.4592336433146e-05, "epoch": 0.6368159203980099, "percentage": 21.33, "elapsed_time": "0:04:52", "remaining_time": "0:17:57", "throughput": 352.33, "total_tokens": 102928}
+{"current_steps": 85, "total_steps": 375, "loss": 3.333, "lr": 4.3924876391293915e-05, "epoch": 0.6766169154228856, "percentage": 22.67, "elapsed_time": "0:05:10", "remaining_time": "0:17:38", "throughput": 353.37, "total_tokens": 109584}
+{"current_steps": 90, "total_steps": 375, "loss": 3.3651, "lr": 4.3224215685535294e-05, "epoch": 0.7164179104477612, "percentage": 24.0, "elapsed_time": "0:05:28", "remaining_time": "0:17:20", "throughput": 357.01, "total_tokens": 117312}
+{"current_steps": 95, "total_steps": 375, "loss": 3.285, "lr": 4.249158351283414e-05, "epoch": 0.7562189054726368, "percentage": 25.33, "elapsed_time": "0:05:46", "remaining_time": "0:17:01", "throughput": 355.97, "total_tokens": 123312}
+{"current_steps": 100, "total_steps": 375, "loss": 3.3726, "lr": 4.172826515897146e-05, "epoch": 0.7960199004975125, "percentage": 26.67, "elapsed_time": "0:06:04", "remaining_time": "0:16:41", "throughput": 356.11, "total_tokens": 129664}
+{"current_steps": 105, "total_steps": 375, "loss": 3.349, "lr": 4.093559974371725e-05, "epoch": 0.835820895522388, "percentage": 28.0, "elapsed_time": "0:06:23", "remaining_time": "0:16:26", "throughput": 360.08, "total_tokens": 138128}
+{"current_steps": 110, "total_steps": 375, "loss": 3.3335, "lr": 4.011497787155938e-05, "epoch": 0.8756218905472637, "percentage": 29.33, "elapsed_time": "0:06:41", "remaining_time": "0:16:07", "throughput": 358.69, "total_tokens": 144064}
+{"current_steps": 115, "total_steps": 375, "loss": 3.3096, "lr": 3.92678391921108e-05, "epoch": 0.9154228855721394, "percentage": 30.67, "elapsed_time": "0:06:59", "remaining_time": "0:15:48", "throughput": 356.95, "total_tokens": 149760}
+{"current_steps": 120, "total_steps": 375, "loss": 3.2696, "lr": 3.8395669874474915e-05, "epoch": 0.9552238805970149, "percentage": 32.0, "elapsed_time": "0:07:17", "remaining_time": "0:15:29", "throughput": 354.39, "total_tokens": 155088}
+{"current_steps": 125, "total_steps": 375, "loss": 3.3071, "lr": 3.7500000000000003e-05, "epoch": 0.9950248756218906, "percentage": 33.33, "elapsed_time": "0:07:36", "remaining_time": "0:15:13", "throughput": 357.59, "total_tokens": 163328}
+{"current_steps": 130, "total_steps": 375, "loss": 3.8956, "lr": 3.6582400877996546e-05, "epoch": 1.0398009950248757, "percentage": 34.67, "elapsed_time": "0:07:55", "remaining_time": "0:14:55", "throughput": 355.28, "total_tokens": 168832}
+{"current_steps": 135, "total_steps": 375, "loss": 3.2505, "lr": 3.564448228912682e-05, "epoch": 1.0796019900497513, "percentage": 36.0, "elapsed_time": "0:08:13", "remaining_time": "0:14:36", "throughput": 353.84, "total_tokens": 174544}
+{"current_steps": 140, "total_steps": 375, "loss": 3.249, "lr": 3.4687889661302576e-05, "epoch": 1.1194029850746268, "percentage": 37.33, "elapsed_time": "0:08:31", "remaining_time": "0:14:19", "throughput": 355.97, "total_tokens": 182176}
+{"current_steps": 145, "total_steps": 375, "loss": 3.1777, "lr": 3.3714301183045385e-05, "epoch": 1.1592039800995024, "percentage": 38.67, "elapsed_time": "0:08:49", "remaining_time": "0:14:00", "throughput": 354.36, "total_tokens": 187680}
+{"current_steps": 150, "total_steps": 375, "loss": 3.2005, "lr": 3.272542485937369e-05, "epoch": 1.199004975124378, "percentage": 40.0, "elapsed_time": "0:09:07", "remaining_time": "0:13:41", "throughput": 354.54, "total_tokens": 194176}
+{"current_steps": 155, "total_steps": 375, "loss": 3.1882, "lr": 3.172299551538164e-05, "epoch": 1.2388059701492538, "percentage": 41.33, "elapsed_time": "0:09:26", "remaining_time": "0:13:23", "throughput": 356.67, "total_tokens": 201904}
+{"current_steps": 160, "total_steps": 375, "loss": 3.2861, "lr": 3.0708771752766394e-05, "epoch": 1.2786069651741294, "percentage": 42.67, "elapsed_time": "0:09:44", "remaining_time": "0:13:04", "throughput": 354.95, "total_tokens": 207344}
+{"current_steps": 165, "total_steps": 375, "loss": 3.2012, "lr": 2.9684532864643122e-05, "epoch": 1.3184079601990049, "percentage": 44.0, "elapsed_time": "0:10:02", "remaining_time": "0:12:46", "throughput": 352.93, "total_tokens": 212480}
+{"current_steps": 170, "total_steps": 375, "loss": 3.1424, "lr": 2.8652075714060295e-05, "epoch": 1.3582089552238805, "percentage": 45.33, "elapsed_time": "0:10:21", "remaining_time": "0:12:28", "throughput": 353.98, "total_tokens": 219840}
+{"current_steps": 175, "total_steps": 375, "loss": 3.1061, "lr": 2.761321158169134e-05, "epoch": 1.3980099502487562, "percentage": 46.67, "elapsed_time": "0:10:38", "remaining_time": "0:12:10", "throughput": 351.42, "total_tokens": 224544}
+{"current_steps": 180, "total_steps": 375, "loss": 3.1739, "lr": 2.656976298823284e-05, "epoch": 1.4378109452736318, "percentage": 48.0, "elapsed_time": "0:10:57", "remaining_time": "0:11:52", "throughput": 352.41, "total_tokens": 231760}
+{"current_steps": 185, "total_steps": 375, "loss": 3.1692, "lr": 2.5523560497083926e-05, "epoch": 1.4776119402985075, "percentage": 49.33, "elapsed_time": "0:11:15", "remaining_time": "0:11:34", "throughput": 353.7, "total_tokens": 239056}
+{"current_steps": 190, "total_steps": 375, "loss": 3.2116, "lr": 2.447643950291608e-05, "epoch": 1.517412935323383, "percentage": 50.67, "elapsed_time": "0:11:34", "remaining_time": "0:11:16", "throughput": 355.0, "total_tokens": 246576}
+{"current_steps": 195, "total_steps": 375, "loss": 3.3134, "lr": 2.3430237011767167e-05, "epoch": 1.5572139303482588, "percentage": 52.0, "elapsed_time": "0:11:52", "remaining_time": "0:10:57", "throughput": 355.61, "total_tokens": 253360}
+{"current_steps": 200, "total_steps": 375, "loss": 3.2215, "lr": 2.238678841830867e-05, "epoch": 1.5970149253731343, "percentage": 53.33, "elapsed_time": "0:12:10", "remaining_time": "0:10:39", "throughput": 356.2, "total_tokens": 260240}
+{"current_steps": 205, "total_steps": 375, "loss": 3.0594, "lr": 2.1347924285939714e-05, "epoch": 1.63681592039801, "percentage": 54.67, "elapsed_time": "0:12:29", "remaining_time": "0:10:21", "throughput": 354.14, "total_tokens": 265520}
+{"current_steps": 210, "total_steps": 375, "loss": 3.1452, "lr": 2.031546713535688e-05, "epoch": 1.6766169154228856, "percentage": 56.0, "elapsed_time": "0:12:49", "remaining_time": "0:10:04", "throughput": 356.32, "total_tokens": 274144}
+{"current_steps": 215, "total_steps": 375, "loss": 3.2481, "lr": 1.9291228247233605e-05, "epoch": 1.716417910447761, "percentage": 57.33, "elapsed_time": "0:13:07", "remaining_time": "0:09:46", "throughput": 356.7, "total_tokens": 281024}
+{"current_steps": 220, "total_steps": 375, "loss": 3.1269, "lr": 1.827700448461836e-05, "epoch": 1.756218905472637, "percentage": 58.67, "elapsed_time": "0:13:27", "remaining_time": "0:09:28", "throughput": 359.85, "total_tokens": 290608}
+{"current_steps": 225, "total_steps": 375, "loss": 3.1888, "lr": 1.7274575140626318e-05, "epoch": 1.7960199004975124, "percentage": 60.0, "elapsed_time": "0:13:45", "remaining_time": "0:09:10", "throughput": 360.92, "total_tokens": 298064}
+{"current_steps": 230, "total_steps": 375, "loss": 3.2137, "lr": 1.6285698816954624e-05, "epoch": 1.835820895522388, "percentage": 61.33, "elapsed_time": "0:14:03", "remaining_time": "0:08:52", "throughput": 359.6, "total_tokens": 303456}
+{"current_steps": 235, "total_steps": 375, "loss": 3.1926, "lr": 1.5312110338697426e-05, "epoch": 1.8756218905472637, "percentage": 62.67, "elapsed_time": "0:14:21", "remaining_time": "0:08:33", "throughput": 358.0, "total_tokens": 308528}
+{"current_steps": 240, "total_steps": 375, "loss": 3.2949, "lr": 1.4355517710873184e-05, "epoch": 1.9154228855721394, "percentage": 64.0, "elapsed_time": "0:14:39", "remaining_time": "0:08:14", "throughput": 357.75, "total_tokens": 314816}
+{"current_steps": 245, "total_steps": 375, "loss": 3.1559, "lr": 1.3417599122003464e-05, "epoch": 1.955223880597015, "percentage": 65.33, "elapsed_time": "0:14:57", "remaining_time": "0:07:56", "throughput": 356.64, "total_tokens": 320224}
+{"current_steps": 250, "total_steps": 375, "loss": 3.1411, "lr": 1.2500000000000006e-05, "epoch": 1.9950248756218905, "percentage": 66.67, "elapsed_time": "0:15:15", "remaining_time": "0:07:37", "throughput": 355.99, "total_tokens": 326032}
+{"current_steps": 255, "total_steps": 375, "loss": 3.5418, "lr": 1.1604330125525079e-05, "epoch": 2.0398009950248754, "percentage": 68.0, "elapsed_time": "0:15:34", "remaining_time": "0:07:19", "throughput": 354.77, "total_tokens": 331440}
+{"current_steps": 260, "total_steps": 375, "loss": 3.0061, "lr": 1.0732160807889211e-05, "epoch": 2.0796019900497513, "percentage": 69.33, "elapsed_time": "0:15:51", "remaining_time": "0:07:01", "throughput": 354.05, "total_tokens": 337056}
+{"current_steps": 265, "total_steps": 375, "loss": 3.102, "lr": 9.88502212844063e-06, "epoch": 2.1194029850746268, "percentage": 70.67, "elapsed_time": "0:16:10", "remaining_time": "0:06:42", "throughput": 352.6, "total_tokens": 342064}
+{"current_steps": 270, "total_steps": 375, "loss": 2.9862, "lr": 9.064400256282757e-06, "epoch": 2.1592039800995027, "percentage": 72.0, "elapsed_time": "0:16:28", "remaining_time": "0:06:24", "throughput": 351.35, "total_tokens": 347152}
+{"current_steps": 275, "total_steps": 375, "loss": 3.0803, "lr": 8.271734841028553e-06, "epoch": 2.199004975124378, "percentage": 73.33, "elapsed_time": "0:16:46", "remaining_time": "0:06:06", "throughput": 352.72, "total_tokens": 355152}
+{"current_steps": 280, "total_steps": 375, "loss": 3.1944, "lr": 7.508416487165862e-06, "epoch": 2.2388059701492535, "percentage": 74.67, "elapsed_time": "0:17:05", "remaining_time": "0:05:47", "throughput": 352.51, "total_tokens": 361328}
+{"current_steps": 285, "total_steps": 375, "loss": 3.1717, "lr": 6.775784314464717e-06, "epoch": 2.2786069651741294, "percentage": 76.0, "elapsed_time": "0:17:23", "remaining_time": "0:05:29", "throughput": 354.26, "total_tokens": 369648}
+{"current_steps": 290, "total_steps": 375, "loss": 3.2106, "lr": 6.075123608706093e-06, "epoch": 2.318407960199005, "percentage": 77.33, "elapsed_time": "0:17:42", "remaining_time": "0:05:11", "throughput": 355.43, "total_tokens": 377664}
+{"current_steps": 295, "total_steps": 375, "loss": 3.0577, "lr": 5.4076635668540075e-06, "epoch": 2.3582089552238807, "percentage": 78.67, "elapsed_time": "0:18:00", "remaining_time": "0:04:53", "throughput": 356.33, "total_tokens": 385184}
+{"current_steps": 300, "total_steps": 375, "loss": 3.1227, "lr": 4.7745751406263165e-06, "epoch": 2.398009950248756, "percentage": 80.0, "elapsed_time": "0:18:18", "remaining_time": "0:04:34", "throughput": 356.28, "total_tokens": 391536}
+{"current_steps": 305, "total_steps": 375, "loss": 3.1015, "lr": 4.176968982247514e-06, "epoch": 2.4378109452736316, "percentage": 81.33, "elapsed_time": "0:18:37", "remaining_time": "0:04:16", "throughput": 355.52, "total_tokens": 397408}
+{"current_steps": 310, "total_steps": 375, "loss": 3.0393, "lr": 3.6158934959873353e-06, "epoch": 2.4776119402985075, "percentage": 82.67, "elapsed_time": "0:18:55", "remaining_time": "0:03:58", "throughput": 355.42, "total_tokens": 403712}
+{"current_steps": 315, "total_steps": 375, "loss": 2.9964, "lr": 3.092332998903416e-06, "epoch": 2.517412935323383, "percentage": 84.0, "elapsed_time": "0:19:13", "remaining_time": "0:03:39", "throughput": 354.97, "total_tokens": 409632}
+{"current_steps": 320, "total_steps": 375, "loss": 3.1617, "lr": 2.6072059940146775e-06, "epoch": 2.557213930348259, "percentage": 85.33, "elapsed_time": "0:19:32", "remaining_time": "0:03:21", "throughput": 355.4, "total_tokens": 416704}
+{"current_steps": 325, "total_steps": 375, "loss": 3.0388, "lr": 2.1613635589349756e-06, "epoch": 2.5970149253731343, "percentage": 86.67, "elapsed_time": "0:19:51", "remaining_time": "0:03:03", "throughput": 356.66, "total_tokens": 425056}
+{"current_steps": 330, "total_steps": 375, "loss": 3.158, "lr": 1.7555878527937164e-06, "epoch": 2.6368159203980097, "percentage": 88.0, "elapsed_time": "0:20:09", "remaining_time": "0:02:44", "throughput": 356.13, "total_tokens": 430816}
+{"current_steps": 335, "total_steps": 375, "loss": 3.0348, "lr": 1.3905907440629752e-06, "epoch": 2.6766169154228856, "percentage": 89.33, "elapsed_time": "0:20:27", "remaining_time": "0:02:26", "throughput": 356.25, "total_tokens": 437456}
+{"current_steps": 340, "total_steps": 375, "loss": 3.1515, "lr": 1.067012561698319e-06, "epoch": 2.716417910447761, "percentage": 90.67, "elapsed_time": "0:20:45", "remaining_time": "0:02:08", "throughput": 355.61, "total_tokens": 442976}
+{"current_steps": 345, "total_steps": 375, "loss": 3.0978, "lr": 7.854209717842231e-07, "epoch": 2.756218905472637, "percentage": 92.0, "elapsed_time": "0:21:05", "remaining_time": "0:01:50", "throughput": 356.26, "total_tokens": 450688}
+{"current_steps": 350, "total_steps": 375, "loss": 3.051, "lr": 5.463099816548579e-07, "epoch": 2.7960199004975124, "percentage": 93.33, "elapsed_time": "0:21:22", "remaining_time": "0:01:31", "throughput": 356.49, "total_tokens": 457344}
+{"current_steps": 355, "total_steps": 375, "loss": 3.0632, "lr": 3.5009907323737825e-07, "epoch": 2.835820895522388, "percentage": 94.67, "elapsed_time": "0:21:40", "remaining_time": "0:01:13", "throughput": 356.36, "total_tokens": 463584}
+{"current_steps": 360, "total_steps": 375, "loss": 3.0875, "lr": 1.9713246713805588e-07, "epoch": 2.8756218905472637, "percentage": 96.0, "elapsed_time": "0:21:58", "remaining_time": "0:00:54", "throughput": 355.21, "total_tokens": 468400}
+{"current_steps": 365, "total_steps": 375, "loss": 3.1218, "lr": 8.767851876239074e-08, "epoch": 2.9154228855721396, "percentage": 97.33, "elapsed_time": "0:22:17", "remaining_time": "0:00:36", "throughput": 356.1, "total_tokens": 476128}
+{"current_steps": 370, "total_steps": 375, "loss": 3.0581, "lr": 2.192924752854042e-08, "epoch": 2.955223880597015, "percentage": 98.67, "elapsed_time": "0:22:36", "remaining_time": "0:00:18", "throughput": 357.04, "total_tokens": 484320}
+{"current_steps": 375, "total_steps": 375, "loss": 2.9967, "lr": 0.0, "epoch": 2.9950248756218905, "percentage": 100.0, "elapsed_time": "0:22:54", "remaining_time": "0:00:00", "throughput": 356.12, "total_tokens": 489472}
+{"current_steps": 375, "total_steps": 375, "epoch": 2.9950248756218905, "percentage": 100.0, "elapsed_time": "0:22:55", "remaining_time": "0:00:00", "throughput": 355.84, "total_tokens": 489472}

trainer_state.json

@@ -0,0 +1,643 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9950248756218905,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03980099502487562,
+      "grad_norm": 1.660474181175232,
+      "learning_rate": 4.997807075247146e-05,
+      "loss": 4.5494,
+      "num_input_tokens_seen": 8048,
+      "step": 5
+    },
+    {
+      "epoch": 0.07960199004975124,
+      "grad_norm": 1.2094064950942993,
+      "learning_rate": 4.991232148123761e-05,
+      "loss": 4.5269,
+      "num_input_tokens_seen": 14000,
+      "step": 10
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 2.039947032928467,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 4.0421,
+      "num_input_tokens_seen": 20800,
+      "step": 15
+    },
+    {
+      "epoch": 0.15920398009950248,
+      "grad_norm": 1.0324708223342896,
+      "learning_rate": 4.964990092676263e-05,
+      "loss": 3.8231,
+      "num_input_tokens_seen": 28992,
+      "step": 20
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 0.9932226538658142,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 3.5978,
+      "num_input_tokens_seen": 34336,
+      "step": 25
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 1.027048945426941,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 3.5563,
+      "num_input_tokens_seen": 39456,
+      "step": 30
+    },
+    {
+      "epoch": 0.27860696517412936,
+      "grad_norm": 1.1643048524856567,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 3.7193,
+      "num_input_tokens_seen": 45280,
+      "step": 35
+    },
+    {
+      "epoch": 0.31840796019900497,
+      "grad_norm": 0.9160460829734802,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 3.4887,
+      "num_input_tokens_seen": 51104,
+      "step": 40
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 0.8983442783355713,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 3.4482,
+      "num_input_tokens_seen": 56672,
+      "step": 45
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 1.1248815059661865,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 3.5251,
+      "num_input_tokens_seen": 61680,
+      "step": 50
+    },
+    {
+      "epoch": 0.43781094527363185,
+      "grad_norm": 0.7155267596244812,
+      "learning_rate": 4.7392794005985326e-05,
+      "loss": 3.4091,
+      "num_input_tokens_seen": 68928,
+      "step": 55
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 0.987359881401062,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 3.4556,
+      "num_input_tokens_seen": 77056,
+      "step": 60
+    },
+    {
+      "epoch": 0.5174129353233831,
+      "grad_norm": 0.8892150521278381,
+      "learning_rate": 4.638410650401267e-05,
+      "loss": 3.3753,
+      "num_input_tokens_seen": 84368,
+      "step": 65
+    },
+    {
+      "epoch": 0.5572139303482587,
+      "grad_norm": 0.7842346429824829,
+      "learning_rate": 4.5823031017752485e-05,
+      "loss": 3.3786,
+      "num_input_tokens_seen": 90272,
+      "step": 70
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 1.263541579246521,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 3.4089,
+      "num_input_tokens_seen": 95600,
+      "step": 75
+    },
+    {
+      "epoch": 0.6368159203980099,
+      "grad_norm": 1.5767709016799927,
+      "learning_rate": 4.4592336433146e-05,
+      "loss": 3.4508,
+      "num_input_tokens_seen": 102928,
+      "step": 80
+    },
+    {
+      "epoch": 0.6766169154228856,
+      "grad_norm": 1.70329749584198,
+      "learning_rate": 4.3924876391293915e-05,
+      "loss": 3.333,
+      "num_input_tokens_seen": 109584,
+      "step": 85
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 1.2080343961715698,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 3.3651,
+      "num_input_tokens_seen": 117312,
+      "step": 90
+    },
+    {
+      "epoch": 0.7562189054726368,
+      "grad_norm": 1.652740478515625,
+      "learning_rate": 4.249158351283414e-05,
+      "loss": 3.285,
+      "num_input_tokens_seen": 123312,
+      "step": 95
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 1.2327072620391846,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 3.3726,
+      "num_input_tokens_seen": 129664,
+      "step": 100
+    },
+    {
+      "epoch": 0.835820895522388,
+      "grad_norm": 0.9110429286956787,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 3.349,
+      "num_input_tokens_seen": 138128,
+      "step": 105
+    },
+    {
+      "epoch": 0.8756218905472637,
+      "grad_norm": 1.3581809997558594,
+      "learning_rate": 4.011497787155938e-05,
+      "loss": 3.3335,
+      "num_input_tokens_seen": 144064,
+      "step": 110
+    },
+    {
+      "epoch": 0.9154228855721394,
+      "grad_norm": 1.4135611057281494,
+      "learning_rate": 3.92678391921108e-05,
+      "loss": 3.3096,
+      "num_input_tokens_seen": 149760,
+      "step": 115
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 1.2543668746948242,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 3.2696,
+      "num_input_tokens_seen": 155088,
+      "step": 120
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 1.23209547996521,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 3.3071,
+      "num_input_tokens_seen": 163328,
+      "step": 125
+    },
+    {
+      "epoch": 1.0398009950248757,
+      "grad_norm": 1.7540336847305298,
+      "learning_rate": 3.6582400877996546e-05,
+      "loss": 3.8956,
+      "num_input_tokens_seen": 168832,
+      "step": 130
+    },
+    {
+      "epoch": 1.0796019900497513,
+      "grad_norm": 1.619620680809021,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 3.2505,
+      "num_input_tokens_seen": 174544,
+      "step": 135
+    },
+    {
+      "epoch": 1.1194029850746268,
+      "grad_norm": 1.514601230621338,
+      "learning_rate": 3.4687889661302576e-05,
+      "loss": 3.249,
+      "num_input_tokens_seen": 182176,
+      "step": 140
+    },
+    {
+      "epoch": 1.1592039800995024,
+      "grad_norm": 1.6307106018066406,
+      "learning_rate": 3.3714301183045385e-05,
+      "loss": 3.1777,
+      "num_input_tokens_seen": 187680,
+      "step": 145
+    },
+    {
+      "epoch": 1.199004975124378,
+      "grad_norm": 2.23348331451416,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 3.2005,
+      "num_input_tokens_seen": 194176,
+      "step": 150
+    },
+    {
+      "epoch": 1.2388059701492538,
+      "grad_norm": 2.122501850128174,
+      "learning_rate": 3.172299551538164e-05,
+      "loss": 3.1882,
+      "num_input_tokens_seen": 201904,
+      "step": 155
+    },
+    {
+      "epoch": 1.2786069651741294,
+      "grad_norm": 1.8795195817947388,
+      "learning_rate": 3.0708771752766394e-05,
+      "loss": 3.2861,
+      "num_input_tokens_seen": 207344,
+      "step": 160
+    },
+    {
+      "epoch": 1.3184079601990049,
+      "grad_norm": 2.0966134071350098,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 3.2012,
+      "num_input_tokens_seen": 212480,
+      "step": 165
+    },
+    {
+      "epoch": 1.3582089552238805,
+      "grad_norm": 1.3658726215362549,
+      "learning_rate": 2.8652075714060295e-05,
+      "loss": 3.1424,
+      "num_input_tokens_seen": 219840,
+      "step": 170
+    },
+    {
+      "epoch": 1.3980099502487562,
+      "grad_norm": 1.7803125381469727,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 3.1061,
+      "num_input_tokens_seen": 224544,
+      "step": 175
+    },
+    {
+      "epoch": 1.4378109452736318,
+      "grad_norm": 2.324481964111328,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 3.1739,
+      "num_input_tokens_seen": 231760,
+      "step": 180
+    },
+    {
+      "epoch": 1.4776119402985075,
+      "grad_norm": 1.5387252569198608,
+      "learning_rate": 2.5523560497083926e-05,
+      "loss": 3.1692,
+      "num_input_tokens_seen": 239056,
+      "step": 185
+    },
+    {
+      "epoch": 1.517412935323383,
+      "grad_norm": 2.545790433883667,
+      "learning_rate": 2.447643950291608e-05,
+      "loss": 3.2116,
+      "num_input_tokens_seen": 246576,
+      "step": 190
+    },
+    {
+      "epoch": 1.5572139303482588,
+      "grad_norm": 1.913610577583313,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 3.3134,
+      "num_input_tokens_seen": 253360,
+      "step": 195
+    },
+    {
+      "epoch": 1.5970149253731343,
+      "grad_norm": 2.4905383586883545,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 3.2215,
+      "num_input_tokens_seen": 260240,
+      "step": 200
+    },
+    {
+      "epoch": 1.63681592039801,
+      "grad_norm": 2.024183511734009,
+      "learning_rate": 2.1347924285939714e-05,
+      "loss": 3.0594,
+      "num_input_tokens_seen": 265520,
+      "step": 205
+    },
+    {
+      "epoch": 1.6766169154228856,
+      "grad_norm": 1.0908023118972778,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 3.1452,
+      "num_input_tokens_seen": 274144,
+      "step": 210
+    },
+    {
+      "epoch": 1.716417910447761,
+      "grad_norm": 1.8009971380233765,
+      "learning_rate": 1.9291228247233605e-05,
+      "loss": 3.2481,
+      "num_input_tokens_seen": 281024,
+      "step": 215
+    },
+    {
+      "epoch": 1.756218905472637,
+      "grad_norm": 2.282066583633423,
+      "learning_rate": 1.827700448461836e-05,
+      "loss": 3.1269,
+      "num_input_tokens_seen": 290608,
+      "step": 220
+    },
+    {
+      "epoch": 1.7960199004975124,
+      "grad_norm": 1.8747786283493042,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 3.1888,
+      "num_input_tokens_seen": 298064,
+      "step": 225
+    },
+    {
+      "epoch": 1.835820895522388,
+      "grad_norm": 2.49768328666687,
+      "learning_rate": 1.6285698816954624e-05,
+      "loss": 3.2137,
+      "num_input_tokens_seen": 303456,
+      "step": 230
+    },
+    {
+      "epoch": 1.8756218905472637,
+      "grad_norm": 1.6736963987350464,
+      "learning_rate": 1.5312110338697426e-05,
+      "loss": 3.1926,
+      "num_input_tokens_seen": 308528,
+      "step": 235
+    },
+    {
+      "epoch": 1.9154228855721394,
+      "grad_norm": 1.7098288536071777,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 3.2949,
+      "num_input_tokens_seen": 314816,
+      "step": 240
+    },
+    {
+      "epoch": 1.955223880597015,
+      "grad_norm": 1.8934247493743896,
+      "learning_rate": 1.3417599122003464e-05,
+      "loss": 3.1559,
+      "num_input_tokens_seen": 320224,
+      "step": 245
+    },
+    {
+      "epoch": 1.9950248756218905,
+      "grad_norm": 1.7036914825439453,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 3.1411,
+      "num_input_tokens_seen": 326032,
+      "step": 250
+    },
+    {
+      "epoch": 2.0398009950248754,
+      "grad_norm": 2.040653705596924,
+      "learning_rate": 1.1604330125525079e-05,
+      "loss": 3.5418,
+      "num_input_tokens_seen": 331440,
+      "step": 255
+    },
+    {
+      "epoch": 2.0796019900497513,
+      "grad_norm": 2.3218231201171875,
+      "learning_rate": 1.0732160807889211e-05,
+      "loss": 3.0061,
+      "num_input_tokens_seen": 337056,
+      "step": 260
+    },
+    {
+      "epoch": 2.1194029850746268,
+      "grad_norm": 1.8058701753616333,
+      "learning_rate": 9.88502212844063e-06,
+      "loss": 3.102,
+      "num_input_tokens_seen": 342064,
+      "step": 265
+    },
+    {
+      "epoch": 2.1592039800995027,
+      "grad_norm": 2.413458824157715,
+      "learning_rate": 9.064400256282757e-06,
+      "loss": 2.9862,
+      "num_input_tokens_seen": 347152,
+      "step": 270
+    },
+    {
+      "epoch": 2.199004975124378,
+      "grad_norm": 2.1168735027313232,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 3.0803,
+      "num_input_tokens_seen": 355152,
+      "step": 275
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 2.024158239364624,
+      "learning_rate": 7.508416487165862e-06,
+      "loss": 3.1944,
+      "num_input_tokens_seen": 361328,
+      "step": 280
+    },
+    {
+      "epoch": 2.2786069651741294,
+      "grad_norm": 1.3230586051940918,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 3.1717,
+      "num_input_tokens_seen": 369648,
+      "step": 285
+    },
+    {
+      "epoch": 2.318407960199005,
+      "grad_norm": 1.2918930053710938,
+      "learning_rate": 6.075123608706093e-06,
+      "loss": 3.2106,
+      "num_input_tokens_seen": 377664,
+      "step": 290
+    },
+    {
+      "epoch": 2.3582089552238807,
+      "grad_norm": 2.0795865058898926,
+      "learning_rate": 5.4076635668540075e-06,
+      "loss": 3.0577,
+      "num_input_tokens_seen": 385184,
+      "step": 295
+    },
+    {
+      "epoch": 2.398009950248756,
+      "grad_norm": 1.6303638219833374,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 3.1227,
+      "num_input_tokens_seen": 391536,
+      "step": 300
+    },
+    {
+      "epoch": 2.4378109452736316,
+      "grad_norm": 1.9387825727462769,
+      "learning_rate": 4.176968982247514e-06,
+      "loss": 3.1015,
+      "num_input_tokens_seen": 397408,
+      "step": 305
+    },
+    {
+      "epoch": 2.4776119402985075,
+      "grad_norm": 1.4628335237503052,
+      "learning_rate": 3.6158934959873353e-06,
+      "loss": 3.0393,
+      "num_input_tokens_seen": 403712,
+      "step": 310
+    },
+    {
+      "epoch": 2.517412935323383,
+      "grad_norm": 1.7818697690963745,
+      "learning_rate": 3.092332998903416e-06,
+      "loss": 2.9964,
+      "num_input_tokens_seen": 409632,
+      "step": 315
+    },
+    {
+      "epoch": 2.557213930348259,
+      "grad_norm": 2.8102335929870605,
+      "learning_rate": 2.6072059940146775e-06,
+      "loss": 3.1617,
+      "num_input_tokens_seen": 416704,
+      "step": 320
+    },
+    {
+      "epoch": 2.5970149253731343,
+      "grad_norm": 1.5898032188415527,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 3.0388,
+      "num_input_tokens_seen": 425056,
+      "step": 325
+    },
+    {
+      "epoch": 2.6368159203980097,
+      "grad_norm": 2.6500918865203857,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 3.158,
+      "num_input_tokens_seen": 430816,
+      "step": 330
+    },
+    {
+      "epoch": 2.6766169154228856,
+      "grad_norm": 2.318143844604492,
+      "learning_rate": 1.3905907440629752e-06,
+      "loss": 3.0348,
+      "num_input_tokens_seen": 437456,
+      "step": 335
+    },
+    {
+      "epoch": 2.716417910447761,
+      "grad_norm": 2.366307020187378,
+      "learning_rate": 1.067012561698319e-06,
+      "loss": 3.1515,
+      "num_input_tokens_seen": 442976,
+      "step": 340
+    },
+    {
+      "epoch": 2.756218905472637,
+      "grad_norm": 1.3784323930740356,
+      "learning_rate": 7.854209717842231e-07,
+      "loss": 3.0978,
+      "num_input_tokens_seen": 450688,
+      "step": 345
+    },
+    {
+      "epoch": 2.7960199004975124,
+      "grad_norm": 1.7502210140228271,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 3.051,
+      "num_input_tokens_seen": 457344,
+      "step": 350
+    },
+    {
+      "epoch": 2.835820895522388,
+      "grad_norm": 1.6103492975234985,
+      "learning_rate": 3.5009907323737825e-07,
+      "loss": 3.0632,
+      "num_input_tokens_seen": 463584,
+      "step": 355
+    },
+    {
+      "epoch": 2.8756218905472637,
+      "grad_norm": 3.220888376235962,
+      "learning_rate": 1.9713246713805588e-07,
+      "loss": 3.0875,
+      "num_input_tokens_seen": 468400,
+      "step": 360
+    },
+    {
+      "epoch": 2.9154228855721396,
+      "grad_norm": 1.726335048675537,
+      "learning_rate": 8.767851876239074e-08,
+      "loss": 3.1218,
+      "num_input_tokens_seen": 476128,
+      "step": 365
+    },
+    {
+      "epoch": 2.955223880597015,
+      "grad_norm": 3.062647819519043,
+      "learning_rate": 2.192924752854042e-08,
+      "loss": 3.0581,
+      "num_input_tokens_seen": 484320,
+      "step": 370
+    },
+    {
+      "epoch": 2.9950248756218905,
+      "grad_norm": 1.9430413246154785,
+      "learning_rate": 0.0,
+      "loss": 2.9967,
+      "num_input_tokens_seen": 489472,
+      "step": 375
+    },
+    {
+      "epoch": 2.9950248756218905,
+      "num_input_tokens_seen": 489472,
+      "step": 375,
+      "total_flos": 2.082450075077837e+16,
+      "train_loss": 3.2915359853108725,
+      "train_runtime": 1375.5479,
+      "train_samples_per_second": 4.382,
+      "train_steps_per_second": 0.273
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 375,
+  "num_input_tokens_seen": 489472,
+  "num_train_epochs": 3,
+  "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": 2.082450075077837e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269a2dc811c0028db8d3c0ba72f8179fa9423f0d690cf0e7ff5fc6a4779243c1
+size 5688

training_args.yaml

@@ -0,0 +1,33 @@
+bf16: true
+cutoff_len: 2048
+dataset: Catsith
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-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: 100000
+model_name_or_path: Qwen/Qwen2.5-7B
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2.5-7B/lora/train_2025-04-10-02-02-13
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+template: default
+trust_remote_code: true
+warmup_steps: 0