初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/cds_o_fr_13 Source: Original Platform
2026-06-04 10:55:17 +08:00
commit 0eeb6eecd7
308 changed files with 1692832 additions and 0 deletions
--- a/checkpoint-1160/trainer_state.json
+++ b/checkpoint-1160/trainer_state.json
@@ -0,0 +1,161 @@
+{
+  "best_global_step": 1160,
+  "best_metric": 2.907557487487793,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_o_fr_13/checkpoint-1160",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 32.2354736328125,
+      "learning_rate": 0.0,
+      "loss": 9.7326,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.26012122631073,
+      "learning_rate": 2.88e-05,
+      "loss": 5.8188,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.1781511306762695,
+      "eval_runtime": 4.3842,
+      "eval_samples_per_second": 803.562,
+      "eval_steps_per_second": 3.193,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0639448165893555,
+      "learning_rate": 5.7799999999999995e-05,
+      "loss": 3.6451,
+      "step": 290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.4042274951934814,
+      "eval_runtime": 4.6134,
+      "eval_samples_per_second": 763.65,
+      "eval_steps_per_second": 3.035,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9253916144371033,
+      "learning_rate": 8.680000000000001e-05,
+      "loss": 3.2742,
+      "step": 435
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.1871676445007324,
+      "eval_runtime": 4.7952,
+      "eval_samples_per_second": 734.687,
+      "eval_steps_per_second": 2.92,
+      "step": 435
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8254706263542175,
+      "learning_rate": 9.668067226890756e-05,
+      "loss": 3.1065,
+      "step": 580
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.0691733360290527,
+      "eval_runtime": 4.4368,
+      "eval_samples_per_second": 794.047,
+      "eval_steps_per_second": 3.155,
+      "step": 580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7847094535827637,
+      "learning_rate": 9.058823529411765e-05,
+      "loss": 3.0059,
+      "step": 725
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.00063157081604,
+      "eval_runtime": 4.5738,
+      "eval_samples_per_second": 770.265,
+      "eval_steps_per_second": 3.061,
+      "step": 725
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.82077956199646,
+      "learning_rate": 8.449579831932774e-05,
+      "loss": 2.9407,
+      "step": 870
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.95955753326416,
+      "eval_runtime": 4.664,
+      "eval_samples_per_second": 755.368,
+      "eval_steps_per_second": 3.002,
+      "step": 870
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7905252575874329,
+      "learning_rate": 7.840336134453782e-05,
+      "loss": 2.8903,
+      "step": 1015
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.929441452026367,
+      "eval_runtime": 4.4917,
+      "eval_samples_per_second": 784.335,
+      "eval_steps_per_second": 3.117,
+      "step": 1015
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.8253563642501831,
+      "learning_rate": 7.23109243697479e-05,
+      "loss": 2.8492,
+      "step": 1160
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.907557487487793,
+      "eval_runtime": 4.4334,
+      "eval_samples_per_second": 794.644,
+      "eval_steps_per_second": 3.158,
+      "step": 1160
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2900,
+  "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": 1.9327249022976e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}