Upload final model

.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

checkpoint-13619/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-13619/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.2"
+}

checkpoint-13619/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97bc12fbdaac92089497486b5a187f6f180299da5f0aae7382fc124872994a99
+size 3554214752

checkpoint-13619/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b3d63b2824e1fe2fd6b4e01cd0834852b0550ead2d56bd0c13dd2e32bd21de
+size 7108647615

checkpoint-13619/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce3f1fd7866b93bfea3f328fd35124d6c8818c1dd3b24d163380d4a576714e9
+size 14244

checkpoint-13619/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6962770d8812862319f958df7963fa1c59052ac9b3c63ef08ad0ed8819b1d83
+size 1064

checkpoint-13619/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 1.7978670597076416,
+  "best_model_checkpoint": "./final_model/checkpoint-12000",
+  "epoch": 1.0,
+  "eval_steps": 2000,
+  "global_step": 13619,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07342683016374184,
+      "grad_norm": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 2.9947,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14685366032748368,
+      "grad_norm": 22.25,
+      "learning_rate": 1.8415088358823997e-05,
+      "loss": 2.1746,
+      "step": 2000
+    },
+    {
+      "epoch": 0.14685366032748368,
+      "eval_loss": 2.0493569374084473,
+      "eval_runtime": 80.5369,
+      "eval_samples_per_second": 37.188,
+      "eval_steps_per_second": 4.656,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2202804904912255,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.683017671764799e-05,
+      "loss": 1.9905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.29370732065496735,
+      "grad_norm": 9.875,
+      "learning_rate": 1.5245265076471988e-05,
+      "loss": 1.862,
+      "step": 4000
+    },
+    {
+      "epoch": 0.29370732065496735,
+      "eval_loss": 1.8751747608184814,
+      "eval_runtime": 80.5582,
+      "eval_samples_per_second": 37.178,
+      "eval_steps_per_second": 4.655,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36713415081870915,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3660353435295983e-05,
+      "loss": 1.8178,
+      "step": 5000
+    },
+    {
+      "epoch": 0.440560980982451,
+      "grad_norm": 0.0,
+      "learning_rate": 1.207544179411998e-05,
+      "loss": 1.8136,
+      "step": 6000
+    },
+    {
+      "epoch": 0.440560980982451,
+      "eval_loss": 1.8225841522216797,
+      "eval_runtime": 80.6002,
+      "eval_samples_per_second": 37.159,
+      "eval_steps_per_second": 4.653,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5139878111461929,
+      "grad_norm": 8.625,
+      "learning_rate": 1.0490530152943973e-05,
+      "loss": 1.773,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5874146413099347,
+      "grad_norm": 7.28125,
+      "learning_rate": 8.90561851176797e-06,
+      "loss": 1.7541,
+      "step": 8000
+    },
+    {
+      "epoch": 0.5874146413099347,
+      "eval_loss": 1.805350422859192,
+      "eval_runtime": 80.5746,
+      "eval_samples_per_second": 37.171,
+      "eval_steps_per_second": 4.654,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6608414714736764,
+      "grad_norm": 0.0,
+      "learning_rate": 7.320706870591965e-06,
+      "loss": 1.7789,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7342683016374183,
+      "grad_norm": 9.4375,
+      "learning_rate": 5.73579522941596e-06,
+      "loss": 1.7921,
+      "step": 10000
+    },
+    {
+      "epoch": 0.7342683016374183,
+      "eval_loss": 1.7991890907287598,
+      "eval_runtime": 80.6715,
+      "eval_samples_per_second": 37.126,
+      "eval_steps_per_second": 4.648,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8076951318011601,
+      "grad_norm": 10.0,
+      "learning_rate": 4.1508835882399565e-06,
+      "loss": 1.8039,
+      "step": 11000
+    },
+    {
+      "epoch": 0.881121961964902,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5659719470639515e-06,
+      "loss": 1.7885,
+      "step": 12000
+    },
+    {
+      "epoch": 0.881121961964902,
+      "eval_loss": 1.7978670597076416,
+      "eval_runtime": 80.6067,
+      "eval_samples_per_second": 37.156,
+      "eval_steps_per_second": 4.652,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9545487921286439,
+      "grad_norm": 11.625,
+      "learning_rate": 9.810603058879469e-07,
+      "loss": 1.7692,
+      "step": 13000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 13619,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.583410086646907e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-13619/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495b3dd2bd28860a3ae45a4bc1fe493c9cc591852e6908ca20c2daebe7b70076
+size 5304

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1188b34d7c0ea8984ef8207278891f7a1d27444f8debea1aa1f81a93d4d44d
+size 3554214752

runs/Feb10_19-38-02_501241f6a6c6/events.out.tfevents.1739216284.501241f6a6c6.8329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d19e91f162a622150900c88f2513cf950e035f23edfc91badddf0f0667254d
+size 5175

runs/Feb10_19-42-06_501241f6a6c6/events.out.tfevents.1739216527.501241f6a6c6.11609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5a47f50378cb1f7248d57df577b56c779d32b282524042e5fbee2d8de7adb5
+size 9898

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}