Hugging Face's logo

RodrigoSalazar-U
/
T-Translator-llama-mix-ep5-checkpoint

Safetensors
Model card Files Community
T-Translator-llama-mix-ep5-checkpoint
File size: 3,368 Bytes 
086516e
 
 
631732d
086516e
631732d
086516e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce84aee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
631732d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
086516e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
631732d
086516e
 
 
 
 
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
137
138
139
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8280430582390285,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05520287054926856,
      "grad_norm": 1.2856197357177734,
      "learning_rate": 1.1037527593818985e-05,
      "loss": 0.7609,
      "step": 100
    },
    {
      "epoch": 0.11040574109853712,
      "grad_norm": 1.0077331066131592,
      "learning_rate": 2.207505518763797e-05,
      "loss": 0.5552,
      "step": 200
    },
    {
      "epoch": 0.1656086116478057,
      "grad_norm": 1.2774763107299805,
      "learning_rate": 3.311258278145696e-05,
      "loss": 0.5229,
      "step": 300
    },
    {
      "epoch": 0.22081148219707425,
      "grad_norm": 1.3611174821853638,
      "learning_rate": 4.415011037527594e-05,
      "loss": 0.5191,
      "step": 400
    },
    {
      "epoch": 0.2760143527463428,
      "grad_norm": 1.112617015838623,
      "learning_rate": 5.518763796909493e-05,
      "loss": 0.5068,
      "step": 500
    },
    {
      "epoch": 0.3312172232956114,
      "grad_norm": 1.1730616092681885,
      "learning_rate": 6.622516556291392e-05,
      "loss": 0.4895,
      "step": 600
    },
    {
      "epoch": 0.3864200938448799,
      "grad_norm": 1.1149307489395142,
      "learning_rate": 7.726269315673289e-05,
      "loss": 0.5044,
      "step": 700
    },
    {
      "epoch": 0.4416229643941485,
      "grad_norm": 1.1326206922531128,
      "learning_rate": 8.830022075055188e-05,
      "loss": 0.5081,
      "step": 800
    },
    {
      "epoch": 0.49682583494341703,
      "grad_norm": 1.1592661142349243,
      "learning_rate": 9.933774834437086e-05,
      "loss": 0.5024,
      "step": 900
    },
    {
      "epoch": 0.5520287054926856,
      "grad_norm": 1.4300315380096436,
      "learning_rate": 9.996717238759354e-05,
      "loss": 0.5078,
      "step": 1000
    },
    {
      "epoch": 0.6072315760419542,
      "grad_norm": 1.3841311931610107,
      "learning_rate": 9.986022415440564e-05,
      "loss": 0.5091,
      "step": 1100
    },
    {
      "epoch": 0.6624344465912227,
      "grad_norm": 1.3825188875198364,
      "learning_rate": 9.967918047007774e-05,
      "loss": 0.4915,
      "step": 1200
    },
    {
      "epoch": 0.7176373171404913,
      "grad_norm": 1.248660683631897,
      "learning_rate": 9.942431037699172e-05,
      "loss": 0.5049,
      "step": 1300
    },
    {
      "epoch": 0.7728401876897598,
      "grad_norm": 1.2805066108703613,
      "learning_rate": 9.909599262824883e-05,
      "loss": 0.4787,
      "step": 1400
    },
    {
      "epoch": 0.8280430582390285,
      "grad_norm": 1.5455862283706665,
      "learning_rate": 9.869471512481871e-05,
      "loss": 0.4844,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 9055,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.944410411838996e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}