初始化项目，由ModelHub XC社区提供模型

Model: abharadwaj123/sqlstorm-grpo-plan8192
Source: Original Platform

checkpoint-12/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-12/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.3.0"
+}

checkpoint-12/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed250bb930901325437e50b2b5edbab58f1e4f6743afe9c6694d696135fcc1fd
+size 6425529112

checkpoint-12/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849c7a8f7db3c85f7ab0a8228f72f5d6f2e771af657bda892b6b54a86aca12a0
+size 17210089

checkpoint-12/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-12/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.48,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.175,
+      "completions/max_length": 6298.7,
+      "completions/max_terminated_length": 4670.0,
+      "completions/mean_length": 3769.95,
+      "completions/mean_terminated_length": 2954.4666748046875,
+      "completions/min_length": 1554.8,
+      "completions/min_terminated_length": 1554.8,
+      "entropy": 4.061883237212896,
+      "epoch": 0.4,
+      "frac_reward_zero_std": 0.05,
+      "grad_norm": 0.3359375,
+      "learning_rate": 2.5e-06,
+      "loss": -0.07856913208961487,
+      "num_tokens": 166764.0,
+      "reward": 0.6544295579195023,
+      "reward_std": 0.040438423810701354,
+      "rewards/reward_func/mean": 0.6544295579195023,
+      "rewards/reward_func/std": 0.04043842608807609,
+      "step": 10,
+      "step_time": 292.8999413277721
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 12,
+  "num_input_tokens_seen": 210353,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd0777ba7dc2ef8d504066fe46d1b754448e30cfb2b6ab178c7c529bdfa7cf5
+size 6929