llama-factory/saves/internlm2_5-7b-chat/checkpoint-105/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5970149253731343,
  "eval_steps": 35,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 5.805906295776367,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 10.5536,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 7.361557960510254,
      "learning_rate": 2.857142857142857e-05,
      "loss": 10.4859,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 9.014820098876953,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 9.3188,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 10.094988822937012,
      "learning_rate": 5.714285714285714e-05,
      "loss": 6.6553,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 15.287639617919922,
      "learning_rate": 7.142857142857143e-05,
      "loss": 3.4581,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.3499271869659424,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.5521,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.5600136518478394,
      "learning_rate": 0.0001,
      "loss": 0.3823,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.35117578506469727,
      "eval_runtime": 230.9383,
      "eval_samples_per_second": 10.825,
      "eval_steps_per_second": 10.825,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 3.365349531173706,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.363,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 1.3274873495101929,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.3428,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.2516767978668213,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.349,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 1.22030770778656,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.3336,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 1.0675277709960938,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.3486,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 1.42255699634552,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2993,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 2.10113787651062,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3257,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.2916417121887207,
      "eval_runtime": 231.0131,
      "eval_samples_per_second": 10.822,
      "eval_steps_per_second": 10.822,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 1.51693594455719,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.3209,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 1.0357732772827148,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2859,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.8819968104362488,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.3123,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.9069387316703796,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.273,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.9045886993408203,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.2927,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 1.3000465631484985,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.2767,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.7296444177627563,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2834,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.28583231568336487,
      "eval_runtime": 230.4985,
      "eval_samples_per_second": 10.846,
      "eval_steps_per_second": 10.846,
      "step": 105
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8703638991929344e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}