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/sft-lora/checkpoint-45/trainer_state.json
+++ b/adapters/sft-lora/checkpoint-45/trainer_state.json
@@ -0,0 +1,146 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 20,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.46982616782188413,
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.9415351152420044,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.166135025024414,
+      "mean_token_accuracy": 0.8076520800590515,
+      "num_tokens": 59002.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.681049507856369,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.8071348071098328,
+      "learning_rate": 0.00029929974520764727,
+      "loss": 0.7030046463012696,
+      "mean_token_accuracy": 0.849864411354065,
+      "num_tokens": 120432.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.9322404026985168,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6664227247238159,
+      "learning_rate": 0.0002964661618243908,
+      "loss": 0.878734016418457,
+      "mean_token_accuracy": 0.8135401248931885,
+      "num_tokens": 179678.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.8074370503425599,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.6451402306556702,
+      "learning_rate": 0.0002914967719886614,
+      "loss": 0.8701633453369141,
+      "mean_token_accuracy": 0.8204897165298461,
+      "num_tokens": 240600.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "eval_entropy": 0.8143169482549032,
+      "eval_loss": 0.924848735332489,
+      "eval_mean_token_accuracy": 0.803371528784434,
+      "eval_num_tokens": 240600.0,
+      "eval_runtime": 1.6201,
+      "eval_samples_per_second": 45.676,
+      "eval_steps_per_second": 1.852,
+      "step": 20
+    },
+    {
+      "entropy": 0.7912694752216339,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.4144524037837982,
+      "learning_rate": 0.0002844640405943555,
+      "loss": 0.8696941375732422,
+      "mean_token_accuracy": 0.8263819813728333,
+      "num_tokens": 301638.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.9237359523773193,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5862515568733215,
+      "learning_rate": 0.00027547052070153396,
+      "loss": 0.9361928939819336,
+      "mean_token_accuracy": 0.8028241634368897,
+      "num_tokens": 359243.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.6837044417858124,
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.4594927728176117,
+      "learning_rate": 0.0002646473580818772,
+      "loss": 0.6992801666259766,
+      "mean_token_accuracy": 0.8513208270072937,
+      "num_tokens": 417098.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.8795680403709412,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.5710228681564331,
+      "learning_rate": 0.00025215237881801955,
+      "loss": 0.9085055351257324,
+      "mean_token_accuracy": 0.8098101854324341,
+      "num_tokens": 480008.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_entropy": 0.8618650635083517,
+      "eval_loss": 0.9124361872673035,
+      "eval_mean_token_accuracy": 0.8028692404429117,
+      "eval_num_tokens": 480008.0,
+      "eval_runtime": 1.6251,
+      "eval_samples_per_second": 45.535,
+      "eval_steps_per_second": 1.846,
+      "step": 40
+    },
+    {
+      "entropy": 0.8452938675880433,
+      "epoch": 1.0,
+      "grad_norm": 0.789717972278595,
+      "learning_rate": 0.00023816778784387094,
+      "loss": 0.8828925132751465,
+      "mean_token_accuracy": 0.8208261251449585,
+      "num_tokens": 530794.0,
+      "step": 45
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 135,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1952299008000000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}