checkpoint-50/trainer_state.json

{
  "best_metric": 0.66251701,
  "best_model_checkpoint": "/home/talos/Downloads/swift/output/qwen2-vl-7b-instruct/v1-20240906-214917/checkpoint-50",
  "epoch": 0.11871197507048524,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "acc": 0.43273938,
      "epoch": 0.0023742395014097048,
      "grad_norm": 2.6836464405059814,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 3.39143324,
      "memory(GiB)": 17.6,
      "step": 1,
      "train_speed(iter/s)": 0.109554
    },
    {
      "acc": 0.42630106,
      "epoch": 0.011871197507048523,
      "grad_norm": 2.722611904144287,
      "learning_rate": 2.272727272727273e-05,
      "loss": 3.6675992,
      "memory(GiB)": 18.52,
      "step": 5,
      "train_speed(iter/s)": 0.11712
    },
    {
      "acc": 0.4359364,
      "epoch": 0.023742395014097046,
      "grad_norm": 2.5712335109710693,
      "learning_rate": 4.545454545454546e-05,
      "loss": 3.49505234,
      "memory(GiB)": 18.52,
      "step": 10,
      "train_speed(iter/s)": 0.118467
    },
    {
      "acc": 0.52706037,
      "epoch": 0.03561359252114557,
      "grad_norm": 3.1658146381378174,
      "learning_rate": 6.818181818181818e-05,
      "loss": 2.71751995,
      "memory(GiB)": 18.52,
      "step": 15,
      "train_speed(iter/s)": 0.118777
    },
    {
      "acc": 0.63293548,
      "epoch": 0.04748479002819409,
      "grad_norm": 2.9896538257598877,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.89354668,
      "memory(GiB)": 18.52,
      "step": 20,
      "train_speed(iter/s)": 0.118991
    },
    {
      "acc": 0.66501107,
      "epoch": 0.05935598753524262,
      "grad_norm": 4.480954647064209,
      "learning_rate": 9.998605186060137e-05,
      "loss": 1.68407936,
      "memory(GiB)": 18.52,
      "step": 25,
      "train_speed(iter/s)": 0.119136
    },
    {
      "acc": 0.75791483,
      "epoch": 0.07122718504229114,
      "grad_norm": 2.67279314994812,
      "learning_rate": 9.990084141112673e-05,
      "loss": 1.15793657,
      "memory(GiB)": 18.52,
      "step": 30,
      "train_speed(iter/s)": 0.119299
    },
    {
      "acc": 0.78989563,
      "epoch": 0.08309838254933967,
      "grad_norm": 2.6674764156341553,
      "learning_rate": 9.973830136604067e-05,
      "loss": 0.96687098,
      "memory(GiB)": 18.52,
      "step": 35,
      "train_speed(iter/s)": 0.119309
    },
    {
      "acc": 0.78122487,
      "epoch": 0.09496958005638818,
      "grad_norm": 5.596856117248535,
      "learning_rate": 9.949868360798893e-05,
      "loss": 1.00073462,
      "memory(GiB)": 18.52,
      "step": 40,
      "train_speed(iter/s)": 0.119402
    },
    {
      "acc": 0.84813137,
      "epoch": 0.10684077756343671,
      "grad_norm": 2.6154444217681885,
      "learning_rate": 9.918235946426388e-05,
      "loss": 0.66644673,
      "memory(GiB)": 18.52,
      "step": 45,
      "train_speed(iter/s)": 0.119479
    },
    {
      "acc": 0.81814995,
      "epoch": 0.11871197507048524,
      "grad_norm": 3.085695743560791,
      "learning_rate": 9.878981913137179e-05,
      "loss": 0.72966509,
      "memory(GiB)": 18.52,
      "step": 50,
      "train_speed(iter/s)": 0.119439
    },
    {
      "epoch": 0.11871197507048524,
      "eval_acc": 0.8361565032549488,
      "eval_loss": 0.6625170111656189,
      "eval_runtime": 164.2627,
      "eval_samples_per_second": 4.56,
      "eval_steps_per_second": 4.56,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 421,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4545111068791808e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}