初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/cds_sh1_30
Source: Original Platform

checkpoint-3500/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": 3465,
+  "best_metric": 3.1518795490264893,
+  "best_model_checkpoint": null,
+  "epoch": 7.070707070707071,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00202020202020202,
+      "grad_norm": 27.219696044921875,
+      "learning_rate": 0.0,
+      "loss": 10.3707,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5280556678771973,
+      "learning_rate": 9.88e-05,
+      "loss": 4.8958,
+      "step": 495
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.9314539432525635,
+      "eval_runtime": 29.8878,
+      "eval_samples_per_second": 1062.842,
+      "eval_steps_per_second": 4.182,
+      "step": 495
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.212111234664917,
+      "learning_rate": 9.478678038379531e-05,
+      "loss": 3.6499,
+      "step": 990
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.539745330810547,
+      "eval_runtime": 29.254,
+      "eval_samples_per_second": 1085.869,
+      "eval_steps_per_second": 4.273,
+      "step": 990
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.3252358436584473,
+      "learning_rate": 8.950959488272922e-05,
+      "loss": 3.3793,
+      "step": 1485
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.379368305206299,
+      "eval_runtime": 30.2558,
+      "eval_samples_per_second": 1049.913,
+      "eval_steps_per_second": 4.131,
+      "step": 1485
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.02847957611084,
+      "learning_rate": 8.42324093816631e-05,
+      "loss": 3.2264,
+      "step": 1980
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2874038219451904,
+      "eval_runtime": 30.0535,
+      "eval_samples_per_second": 1056.98,
+      "eval_steps_per_second": 4.159,
+      "step": 1980
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.101438045501709,
+      "learning_rate": 7.895522388059702e-05,
+      "loss": 3.1179,
+      "step": 2475
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.2294254302978516,
+      "eval_runtime": 27.6091,
+      "eval_samples_per_second": 1150.562,
+      "eval_steps_per_second": 4.527,
+      "step": 2475
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.4466798305511475,
+      "learning_rate": 7.367803837953093e-05,
+      "loss": 3.0343,
+      "step": 2970
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.183612585067749,
+      "eval_runtime": 29.4719,
+      "eval_samples_per_second": 1077.841,
+      "eval_steps_per_second": 4.241,
+      "step": 2970
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.7074270248413086,
+      "learning_rate": 6.840085287846483e-05,
+      "loss": 2.9631,
+      "step": 3465
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.1518795490264893,
+      "eval_runtime": 30.1176,
+      "eval_samples_per_second": 1054.732,
+      "eval_steps_per_second": 4.15,
+      "step": 3465
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 5.8416928948224e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}