初始化项目，由ModelHub XC社区提供模型

Model: Michnik/jarvis-1b-trained
Source: Original Platform

last-checkpoint/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0002653961269416215,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.6539612694162147e-05,
+      "grad_norm": 11.25,
+      "learning_rate": 1.8e-05,
+      "loss": 9.487161254882812,
+      "step": 10
+    },
+    {
+      "epoch": 5.3079225388324294e-05,
+      "grad_norm": 9.3125,
+      "learning_rate": 3.8e-05,
+      "loss": 9.404236602783204,
+      "step": 20
+    },
+    {
+      "epoch": 7.961883808248645e-05,
+      "grad_norm": 9.5625,
+      "learning_rate": 5.8e-05,
+      "loss": 9.108424377441406,
+      "step": 30
+    },
+    {
+      "epoch": 0.00010615845077664859,
+      "grad_norm": 2.484375,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 7.820616912841797,
+      "step": 40
+    },
+    {
+      "epoch": 0.00013269806347081074,
+      "grad_norm": 2.546875,
+      "learning_rate": 9.8e-05,
+      "loss": 7.00987548828125,
+      "step": 50
+    },
+    {
+      "epoch": 0.0001592376761649729,
+      "grad_norm": 5.34375,
+      "learning_rate": 0.000118,
+      "loss": 6.811207580566406,
+      "step": 60
+    },
+    {
+      "epoch": 0.00018577728885913502,
+      "grad_norm": 1.75,
+      "learning_rate": 0.000138,
+      "loss": 6.862815093994141,
+      "step": 70
+    },
+    {
+      "epoch": 0.00021231690155329718,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 6.837502288818359,
+      "step": 80
+    },
+    {
+      "epoch": 0.00023885651424745933,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 6.851012420654297,
+      "step": 90
+    },
+    {
+      "epoch": 0.0002653961269416215,
+      "grad_norm": 1.875,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 6.771617126464844,
+      "step": 100
+    },
+    {
+      "epoch": 0.0002653961269416215,
+      "eval_loss": 7.0674147605896,
+      "eval_runtime": 117.7328,
+      "eval_samples_per_second": 84.938,
+      "eval_steps_per_second": 10.617,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 376796,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2242948735746048.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}