Upload 19 files

.gitattributes

@@ -56,3 +56,4 @@ checkpoint-12400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-12600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-12800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-13000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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": 0.9106271944801982,
+    "num_input_tokens_seen": 209169736,
+    "total_flos": 4.491687216116306e+17,
+    "train_loss": 0.0,
+    "train_runtime": 0.037,
+    "train_samples_per_second": 2778031.466,
+    "train_steps_per_second": 347243.798
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.3"
+}

llamaboard_config.yaml

@@ -0,0 +1,78 @@
+top.booster: auto
+top.checkpoint_path: null
+top.finetuning_type: full
+top.model_name: Qwen2.5-0.5B-Instruct
+top.quantization_bit: none
+top.quantization_method: hqq
+top.rope_scaling: none
+top.template: qwen
+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: 1
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- prithivMLmods/Deepthink-Reasoning-Ins
+- open-thoughts/OpenThoughts-114k
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "sgd"}'
+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: 1e-4
+train.logging_steps: 1
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: polynomial
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '57000000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '1.0'
+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: null
+train.save_steps: 200
+train.swanlab_api_key: ''
+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: 1
+train.warmup_steps: 0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a003460ee2d09a514ffd981bec68fa668c4aa67f533a96b0612e203edee59c
+size 1976163472

running_log.txt

@@ -0,0 +1,237 @@
+[INFO|2025-02-22 11:20:55] configuration_utils.py:696 >> loading configuration file config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\config.json
+
+[INFO|2025-02-22 11:20:55] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file vocab.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\vocab.json
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file merges.txt from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\merges.txt
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer.json
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer_config.json
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-02-22 11:20:56] configuration_utils.py:696 >> loading configuration file config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\config.json
+
+[INFO|2025-02-22 11:20:56] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file vocab.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\vocab.json
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file merges.txt from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\merges.txt
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer.json
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer_config.json
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-02-22 11:20:56] logging.py:157 >> Add <|im_end|> to stop words.
+
+[INFO|2025-02-22 11:20:56] logging.py:157 >> Loading dataset prithivMLmods/Deepthink-Reasoning-Ins...
+
+[INFO|2025-02-22 11:21:19] logging.py:157 >> Loading dataset open-thoughts/OpenThoughts-114k...
+
+[INFO|2025-02-22 11:27:18] configuration_utils.py:696 >> loading configuration file config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\config.json
+
+[INFO|2025-02-22 11:27:18] configuration_utils.py:768 >> Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+[INFO|2025-02-22 11:27:18] modeling_utils.py:3904 >> loading weights file model.safetensors from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\model.safetensors
+
+[INFO|2025-02-22 11:27:18] modeling_utils.py:1582 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-02-22 11:27:18] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+[INFO|2025-02-22 11:27:21] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+[INFO|2025-02-22 11:27:21] modeling_utils.py:4896 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-0.5B-Instruct.
+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|2025-02-22 11:27:22] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\generation_config.json
+
+[INFO|2025-02-22 11:27:22] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8
+}
+
+
+[INFO|2025-02-22 11:27:22] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-02-22 11:27:22] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-02-22 11:27:22] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-02-22 11:27:22] logging.py:157 >> Fine-tuning method: Full
+
+[INFO|2025-02-22 11:27:22] logging.py:157 >> trainable params: 494,032,768 || all params: 494,032,768 || trainable%: 100.0000
+
+[INFO|2025-02-22 11:27:22] trainer.py:741 >> Using auto half precision backend
+
+[INFO|2025-02-22 11:27:22] trainer.py:2775 >> Loading model from saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\checkpoint-13000.
+
+[WARNING|2025-02-22 11:27:23] trainer.py:3018 >> There were missing keys in the checkpoint model loaded: ['lm_head.weight'].
+
+[INFO|2025-02-22 11:27:23] trainer.py:2369 >> ***** Running training *****
+
+[INFO|2025-02-22 11:27:23] trainer.py:2370 >>   Num examples = 102,787
+
+[INFO|2025-02-22 11:27:23] trainer.py:2371 >>   Num Epochs = 1
+
+[INFO|2025-02-22 11:27:23] trainer.py:2372 >>   Instantaneous batch size per device = 1
+
+[INFO|2025-02-22 11:27:23] trainer.py:2375 >>   Total train batch size (w. parallel, distributed & accumulation) = 8
+
+[INFO|2025-02-22 11:27:23] trainer.py:2376 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-02-22 11:27:23] trainer.py:2377 >>   Total optimization steps = 12,848
+
+[INFO|2025-02-22 11:27:23] trainer.py:2378 >>   Number of trainable parameters = 494,032,768
+
+[INFO|2025-02-22 11:27:23] trainer.py:2400 >>   Continuing training from checkpoint, will skip to saved global_step
+
+[INFO|2025-02-22 11:27:23] trainer.py:2401 >>   Continuing training from epoch 1
+
+[INFO|2025-02-22 11:27:23] trainer.py:2402 >>   Continuing training from global step 13000
+
+[INFO|2025-02-22 11:27:23] trainer.py:2404 >>   Will skip the first 1 epochs then the first 1216 batches in the first epoch.
+
+[INFO|2025-02-22 11:27:23] trainer.py:2643 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-02-22 11:27:23] trainer.py:3910 >> Saving model checkpoint to saves\Qwen2.5-0.5B-Instruct\full\20-02-2025
+
+[INFO|2025-02-22 11:27:23] configuration_utils.py:420 >> Configuration saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\config.json
+
+[INFO|2025-02-22 11:27:23] configuration_utils.py:909 >> Configuration saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\generation_config.json
+
+[INFO|2025-02-22 11:27:25] modeling_utils.py:2988 >> Model weights saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\model.safetensors
+
+[INFO|2025-02-22 11:27:25] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\tokenizer_config.json
+
+[INFO|2025-02-22 11:27:25] tokenization_utils_base.py:2500 >> Special tokens file saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\special_tokens_map.json
+
+[WARNING|2025-02-22 11:27:26] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-02-22 11:27:26] trainer.py:4226 >> 
+***** Running Evaluation *****
+
+[INFO|2025-02-22 11:27:26] trainer.py:4228 >>   Num examples = 11421
+
+[INFO|2025-02-22 11:27:26] trainer.py:4231 >>   Batch size = 1
+

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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 tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9106271944801982,
+    "num_input_tokens_seen": 209169736,
+    "total_flos": 4.491687216116306e+17,
+    "train_loss": 0.0,
+    "train_runtime": 0.037,
+    "train_samples_per_second": 2778031.466,
+    "train_steps_per_second": 347243.798
+}

training_args.yaml

@@ -0,0 +1,33 @@
+bf16: true
+cutoff_len: 2048
+dataset: prithivMLmods/Deepthink-Reasoning-Ins,open-thoughts/OpenThoughts-114k
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+eval_steps: 200
+eval_strategy: steps
+finetuning_type: full
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 0.0001
+logging_steps: 1
+lr_scheduler_type: polynomial
+max_grad_norm: 1.0
+max_samples: 57000000
+model_name_or_path: Qwen/Qwen2.5-0.5B-Instruct
+num_train_epochs: 1.0
+optim: sgd
+output_dir: saves\Qwen2.5-0.5B-Instruct\full\20-02-2025
+packing: false
+per_device_eval_batch_size: 1
+per_device_train_batch_size: 1
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 200
+stage: sft
+template: qwen
+trust_remote_code: true
+val_size: 1
+warmup_steps: 0