初始化项目，由ModelHub XC社区提供模型

Model: karthik-2905/AL1-model-B Source: Original Platform
2026-09-03 14:24:17 +08:00
commit 1cf36b6e22
144 changed files with 10291 additions and 0 deletions
--- a/adapters/sweep-1e4/checkpoint-5/trainer_state.json
+++ b/adapters/sweep-1e4/checkpoint-5/trainer_state.json
@@ -0,0 +1,117 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 2,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5484622716903687,
+      "epoch": 0.2,
+      "grad_norm": 4.282809734344482,
+      "learning_rate": 0.0,
+      "loss": 1.4888970851898193,
+      "mean_token_accuracy": 0.7744107842445374,
+      "num_tokens": 11224.0,
+      "step": 1
+    },
+    {
+      "entropy": 0.42378363013267517,
+      "epoch": 0.4,
+      "grad_norm": 5.2397661209106445,
+      "learning_rate": 0.0001,
+      "loss": 1.1912707090377808,
+      "mean_token_accuracy": 0.82523512840271,
+      "num_tokens": 22945.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.4,
+      "eval_entropy": 0.5841028889020284,
+      "eval_loss": 1.3228631019592285,
+      "eval_mean_token_accuracy": 0.7661338647206625,
+      "eval_num_tokens": 22945.0,
+      "eval_runtime": 1.6102,
+      "eval_samples_per_second": 45.956,
+      "eval_steps_per_second": 1.863,
+      "step": 2
+    },
+    {
+      "entropy": 0.42866313457489014,
+      "epoch": 0.6,
+      "grad_norm": 3.391592025756836,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.156782865524292,
+      "mean_token_accuracy": 0.8099516034126282,
+      "num_tokens": 33789.0,
+      "step": 3
+    },
+    {
+      "entropy": 0.7180255055427551,
+      "epoch": 0.8,
+      "grad_norm": 3.040031671524048,
+      "learning_rate": 5e-05,
+      "loss": 1.3655576705932617,
+      "mean_token_accuracy": 0.7426273226737976,
+      "num_tokens": 45381.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.8,
+      "eval_entropy": 0.6125266949335734,
+      "eval_loss": 1.1156907081604004,
+      "eval_mean_token_accuracy": 0.7740189035733541,
+      "eval_num_tokens": 45381.0,
+      "eval_runtime": 1.6088,
+      "eval_samples_per_second": 45.997,
+      "eval_steps_per_second": 1.865,
+      "step": 4
+    },
+    {
+      "entropy": 0.5204336047172546,
+      "epoch": 1.0,
+      "grad_norm": 3.008509397506714,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1955260038375854,
+      "mean_token_accuracy": 0.7777777910232544,
+      "num_tokens": 49937.0,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.6165028810501099,
+      "eval_loss": 1.0987825393676758,
+      "eval_mean_token_accuracy": 0.7757837176322937,
+      "eval_num_tokens": 49937.0,
+      "eval_runtime": 1.6071,
+      "eval_samples_per_second": 46.047,
+      "eval_steps_per_second": 1.867,
+      "step": 5
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 194982543360000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}