初始化项目，由ModelHub XC社区提供模型

Model: christinakopi/thinkprm-full-trl
Source: Original Platform

checkpoint-96/chat_template.jinja

@@ -0,0 +1 @@
+{% 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 %}

checkpoint-96/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-96/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": [
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "5.5.0"
+}

checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f9c059687a03a4e06639ac7491380843bf59ec2c7e6e803f0fa60ae395c5cf
+size 3554214752

checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1d8d8d133716e4cc980be5c28c30fbe5ffdd8bf60b7d244738e8543e52425d
+size 7108644139

checkpoint-96/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03269e9b7ea16cd98a78d6ea7a50b8454cbd266a053c02f734d27c4d0056b89d
+size 15024

checkpoint-96/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4509495bd2a081212bbe15f7d1784af338aff3aadb1c5fe444c3f44626992d0
+size 15024

checkpoint-96/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104638f895e79f68373b82e8ca745e8070a37851d21a073a0fa5ae1db47649d6
+size 15024

checkpoint-96/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765f109d2f595ccad091f8175cdf531d159f08de0ff5196e08c6bb1d0ceda0d5
+size 15024

checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45fa5872c6b94546611865552c748b8465c292687e6f6f8c42dfe9aff51ed39
+size 1064

checkpoint-96/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
+size 11421911

checkpoint-96/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

checkpoint-96/trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.4654052224010229,
+      "epoch": 0.32,
+      "grad_norm": 0.048828125,
+      "learning_rate": 6e-05,
+      "loss": 0.30594801902770996,
+      "mean_token_accuracy": 0.9038856193423271,
+      "num_tokens": 460568.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.42793196588754656,
+      "epoch": 0.64,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 6e-05,
+      "loss": 0.2569255828857422,
+      "mean_token_accuracy": 0.9156977899372578,
+      "num_tokens": 916064.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.41921926364302636,
+      "epoch": 0.96,
+      "grad_norm": 0.043701171875,
+      "learning_rate": 6e-05,
+      "loss": 0.26015210151672363,
+      "mean_token_accuracy": 0.9139690645039081,
+      "num_tokens": 1373088.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.38780535757541656,
+      "epoch": 1.256,
+      "grad_norm": 0.042724609375,
+      "learning_rate": 6e-05,
+      "loss": 0.1978880524635315,
+      "mean_token_accuracy": 0.9332824486332971,
+      "num_tokens": 1799690.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.3551080597564578,
+      "epoch": 1.576,
+      "grad_norm": 0.041259765625,
+      "learning_rate": 6e-05,
+      "loss": 0.18691558837890626,
+      "mean_token_accuracy": 0.9357104673981667,
+      "num_tokens": 2257096.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.34900726228952406,
+      "epoch": 1.896,
+      "grad_norm": 0.042236328125,
+      "learning_rate": 6e-05,
+      "loss": 0.1920093059539795,
+      "mean_token_accuracy": 0.9355965360999108,
+      "num_tokens": 2710250.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.32550016951722066,
+      "epoch": 2.192,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 6e-05,
+      "loss": 0.16194652318954467,
+      "mean_token_accuracy": 0.945790433400386,
+      "num_tokens": 3126379.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.2879067212343216,
+      "epoch": 2.512,
+      "grad_norm": 0.040771484375,
+      "learning_rate": 6e-05,
+      "loss": 0.14068626165390014,
+      "mean_token_accuracy": 0.951568552851677,
+      "num_tokens": 3590470.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.27728699781000615,
+      "epoch": 2.832,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 6e-05,
+      "loss": 0.134770405292511,
+      "mean_token_accuracy": 0.9545286163687706,
+      "num_tokens": 4047880.0,
+      "step": 90
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "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": 3.97466818052096e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6ba99fbb102272b4ce278ab05ae0e477eb8ff8bab9f89f281c9f2c3dce6e1d
+size 5304