File size: 3,217 Bytes
44af54e
 
 
55c8d6e
44af54e
55c8d6e
44af54e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92eecf2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5bae453
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55c8d6e
 
 
 
 
 
 
44af54e
 
 
 
 
 
 
 
 
 
 
 
 
 
55c8d6e
44af54e
 
 
 
55c8d6e
44af54e
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00014832558950151478,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4832558950151478e-05,
      "grad_norm": 0.5195764303207397,
      "learning_rate": 2e-05,
      "loss": 1.4502,
      "step": 1
    },
    {
      "epoch": 1.4832558950151478e-05,
      "eval_loss": 1.6685941219329834,
      "eval_runtime": 4220.9321,
      "eval_samples_per_second": 6.725,
      "eval_steps_per_second": 3.363,
      "step": 1
    },
    {
      "epoch": 2.9665117900302956e-05,
      "grad_norm": 0.3675019443035126,
      "learning_rate": 4e-05,
      "loss": 1.5582,
      "step": 2
    },
    {
      "epoch": 4.449767685045443e-05,
      "grad_norm": 0.33625102043151855,
      "learning_rate": 6e-05,
      "loss": 1.5239,
      "step": 3
    },
    {
      "epoch": 4.449767685045443e-05,
      "eval_loss": 1.6688132286071777,
      "eval_runtime": 4203.5845,
      "eval_samples_per_second": 6.753,
      "eval_steps_per_second": 3.377,
      "step": 3
    },
    {
      "epoch": 5.933023580060591e-05,
      "grad_norm": 0.5512273907661438,
      "learning_rate": 8e-05,
      "loss": 1.607,
      "step": 4
    },
    {
      "epoch": 7.416279475075739e-05,
      "grad_norm": 0.3602822422981262,
      "learning_rate": 0.0001,
      "loss": 1.7489,
      "step": 5
    },
    {
      "epoch": 8.899535370090886e-05,
      "grad_norm": 0.2666824460029602,
      "learning_rate": 0.00012,
      "loss": 1.5206,
      "step": 6
    },
    {
      "epoch": 8.899535370090886e-05,
      "eval_loss": 1.6630691289901733,
      "eval_runtime": 4200.132,
      "eval_samples_per_second": 6.759,
      "eval_steps_per_second": 3.379,
      "step": 6
    },
    {
      "epoch": 0.00010382791265106034,
      "grad_norm": 0.4554048180580139,
      "learning_rate": 0.00014,
      "loss": 1.6983,
      "step": 7
    },
    {
      "epoch": 0.00011866047160121182,
      "grad_norm": 0.33600732684135437,
      "learning_rate": 0.00016,
      "loss": 1.4306,
      "step": 8
    },
    {
      "epoch": 0.0001334930305513633,
      "grad_norm": 0.3740876019001007,
      "learning_rate": 0.00018,
      "loss": 1.5837,
      "step": 9
    },
    {
      "epoch": 0.0001334930305513633,
      "eval_loss": 1.642859697341919,
      "eval_runtime": 4200.056,
      "eval_samples_per_second": 6.759,
      "eval_steps_per_second": 3.379,
      "step": 9
    },
    {
      "epoch": 0.00014832558950151478,
      "grad_norm": 0.38908034563064575,
      "learning_rate": 0.0002,
      "loss": 1.6273,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2058737544069120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}