bhandariKaran/postsathi

1{
2  "best_global_step": null,
3  "best_metric": null,
4  "best_model_checkpoint": null,
5  "epoch": 2.0,
6  "eval_steps": 500,
7  "global_step": 58,
8  "is_hyper_param_search": false,
9  "is_local_process_zero": true,
10  "is_world_process_zero": true,
11  "log_history": [
12    {
13      "epoch": 1.0,
14      "eval_loss": 1.1150346994400024,
15      "eval_runtime": 122.43,
16      "eval_samples_per_second": 0.408,
17      "eval_steps_per_second": 0.408,
18      "step": 29
19    },
20    {
21      "epoch": 1.7483296213808464,
22      "grad_norm": 0.7534334659576416,
23      "learning_rate": 8.509577338238255e-05,
24      "loss": 1.5057997131347656,
25      "step": 50
26    },
27    {
28      "epoch": 2.0,
29      "eval_loss": 0.9727531671524048,
30      "eval_runtime": 124.2168,
31      "eval_samples_per_second": 0.403,
32      "eval_steps_per_second": 0.403,
33      "step": 58
34    }
35  ],
36  "logging_steps": 50,
37  "max_steps": 87,
38  "num_input_tokens_seen": 0,
39  "num_train_epochs": 3,
40  "save_steps": 500,
41  "stateful_callbacks": {
42    "TrainerControl": {
43      "args": {
44        "should_epoch_stop": false,
45        "should_evaluate": false,
46        "should_log": false,
47        "should_save": true,
48        "should_training_stop": false
49      },
50      "attributes": {}
51    }
52  },
53  "total_flos": 1628649410826240.0,
54  "train_batch_size": 1,
55  "trial_name": null,
56  "trial_params": null
57}
58