CoolFace
Apppublic

young141319/TextClassification

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes
trainer_state.json85 linesDownload Raw Back to experiments
1{
2  "best_metric": null,
3  "best_model_checkpoint": null,
4  "epoch": 2.0,
5  "eval_steps": 500,
6  "global_step": 3046,
7  "is_hyper_param_search": false,
8  "is_local_process_zero": true,
9  "is_world_process_zero": true,
10  "log_history": [
11    {
12      "epoch": 0.3282994090610637,
13      "grad_norm": 1.8659716844558716,
14      "learning_rate": 1.6717005909389364e-05,
15      "loss": 0.525,
16      "step": 500
17    },
18    {
19      "epoch": 0.6565988181221274,
20      "grad_norm": 10.984637260437012,
21      "learning_rate": 1.3434011818778727e-05,
22      "loss": 0.5687,
23      "step": 1000
24    },
25    {
26      "epoch": 0.9848982271831911,
27      "grad_norm": 0.7922234535217285,
28      "learning_rate": 1.0151017728168092e-05,
29      "loss": 0.5625,
30      "step": 1500
31    },
32    {
33      "epoch": 1.3131976362442548,
34      "grad_norm": 0.5657962560653687,
35      "learning_rate": 6.868023637557453e-06,
36      "loss": 0.4698,
37      "step": 2000
38    },
39    {
40      "epoch": 1.6414970453053184,
41      "grad_norm": 0.17007100582122803,
42      "learning_rate": 3.585029546946816e-06,
43      "loss": 0.4719,
44      "step": 2500
45    },
46    {
47      "epoch": 1.9697964543663822,
48      "grad_norm": 8.285143852233887,
49      "learning_rate": 3.020354563361786e-07,
50      "loss": 0.4245,
51      "step": 3000
52    },
53    {
54      "epoch": 2.0,
55      "step": 3046,
56      "total_flos": 801173163571200.0,
57      "train_loss": 0.5036318572978009,
58      "train_runtime": 908.996,
59      "train_samples_per_second": 13.399,
60      "train_steps_per_second": 3.351
61    }
62  ],
63  "logging_steps": 500,
64  "max_steps": 3046,
65  "num_input_tokens_seen": 0,
66  "num_train_epochs": 2,
67  "save_steps": 500,
68  "stateful_callbacks": {
69    "TrainerControl": {
70      "args": {
71        "should_epoch_stop": false,
72        "should_evaluate": false,
73        "should_log": false,
74        "should_save": true,
75        "should_training_stop": true
76      },
77      "attributes": {}
78    }
79  },
80  "total_flos": 801173163571200.0,
81  "train_batch_size": 4,
82  "trial_name": null,
83  "trial_params": null
84}
85