Hugging Face's logo

ngocquangt2k46
/
5de7b49b-4dff-4a17-9193-6d28cb60bf62

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5de7b49b-4dff-4a17-9193-6d28cb60bf62
File size: 4,049 Bytes 
d6619c0
 
 
c7f5d9a
d6619c0
c7f5d9a
d6619c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67037ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7f5d9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d6619c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7f5d9a
d6619c0
 
 
 
 
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08491066690252963,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0056607111268353084,
      "grad_norm": 0.24056661128997803,
      "learning_rate": 1e-05,
      "loss": 10.4071,
      "step": 1
    },
    {
      "epoch": 0.0056607111268353084,
      "eval_loss": 10.435810089111328,
      "eval_runtime": 7.8807,
      "eval_samples_per_second": 75.501,
      "eval_steps_per_second": 37.814,
      "step": 1
    },
    {
      "epoch": 0.011321422253670617,
      "grad_norm": 0.2668295204639435,
      "learning_rate": 2e-05,
      "loss": 10.4373,
      "step": 2
    },
    {
      "epoch": 0.016982133380505925,
      "grad_norm": 0.23038893938064575,
      "learning_rate": 3e-05,
      "loss": 10.4385,
      "step": 3
    },
    {
      "epoch": 0.022642844507341234,
      "grad_norm": 0.2281711995601654,
      "learning_rate": 4e-05,
      "loss": 10.4232,
      "step": 4
    },
    {
      "epoch": 0.028303555634176542,
      "grad_norm": 0.2743370532989502,
      "learning_rate": 5e-05,
      "loss": 10.4297,
      "step": 5
    },
    {
      "epoch": 0.028303555634176542,
      "eval_loss": 10.434837341308594,
      "eval_runtime": 7.8713,
      "eval_samples_per_second": 75.591,
      "eval_steps_per_second": 37.859,
      "step": 5
    },
    {
      "epoch": 0.03396426676101185,
      "grad_norm": 0.23880141973495483,
      "learning_rate": 6e-05,
      "loss": 10.4333,
      "step": 6
    },
    {
      "epoch": 0.03962497788784716,
      "grad_norm": 0.2584647536277771,
      "learning_rate": 7e-05,
      "loss": 10.4085,
      "step": 7
    },
    {
      "epoch": 0.04528568901468247,
      "grad_norm": 0.22347287833690643,
      "learning_rate": 8e-05,
      "loss": 10.4365,
      "step": 8
    },
    {
      "epoch": 0.05094640014151778,
      "grad_norm": 0.25124576687812805,
      "learning_rate": 9e-05,
      "loss": 10.4249,
      "step": 9
    },
    {
      "epoch": 0.056607111268353084,
      "grad_norm": 0.25805941224098206,
      "learning_rate": 0.0001,
      "loss": 10.4151,
      "step": 10
    },
    {
      "epoch": 0.056607111268353084,
      "eval_loss": 10.431522369384766,
      "eval_runtime": 7.8709,
      "eval_samples_per_second": 75.595,
      "eval_steps_per_second": 37.861,
      "step": 10
    },
    {
      "epoch": 0.062267822395188396,
      "grad_norm": 0.24282322824001312,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.4583,
      "step": 11
    },
    {
      "epoch": 0.0679285335220237,
      "grad_norm": 0.22543445229530334,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.416,
      "step": 12
    },
    {
      "epoch": 0.073589244648859,
      "grad_norm": 0.2722141444683075,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.4259,
      "step": 13
    },
    {
      "epoch": 0.07924995577569433,
      "grad_norm": 0.26514723896980286,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.4125,
      "step": 14
    },
    {
      "epoch": 0.08491066690252963,
      "grad_norm": 0.23801234364509583,
      "learning_rate": 5e-05,
      "loss": 10.4257,
      "step": 15
    },
    {
      "epoch": 0.08491066690252963,
      "eval_loss": 10.427189826965332,
      "eval_runtime": 7.8704,
      "eval_samples_per_second": 75.6,
      "eval_steps_per_second": 37.863,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 12552587182080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}