Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_metamath_40k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
oh_v3-1_only_metamath_40k
File size: 2,266 Bytes 
4bca4b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.891566265060241,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.642570281124498,
      "grad_norm": 3.008957806586854,
      "learning_rate": 5e-06,
      "loss": 0.4671,
      "step": 10
    },
    {
      "epoch": 0.963855421686747,
      "eval_loss": 0.33529338240623474,
      "eval_runtime": 74.8385,
      "eval_samples_per_second": 5.599,
      "eval_steps_per_second": 0.361,
      "step": 15
    },
    {
      "epoch": 1.285140562248996,
      "grad_norm": 1.4278343000102331,
      "learning_rate": 5e-06,
      "loss": 0.3359,
      "step": 20
    },
    {
      "epoch": 1.927710843373494,
      "grad_norm": 0.9256547137281664,
      "learning_rate": 5e-06,
      "loss": 0.3019,
      "step": 30
    },
    {
      "epoch": 1.9919678714859437,
      "eval_loss": 0.2970140278339386,
      "eval_runtime": 74.8069,
      "eval_samples_per_second": 5.601,
      "eval_steps_per_second": 0.361,
      "step": 31
    },
    {
      "epoch": 2.570281124497992,
      "grad_norm": 1.8739185721481015,
      "learning_rate": 5e-06,
      "loss": 0.2815,
      "step": 40
    },
    {
      "epoch": 2.891566265060241,
      "eval_loss": 0.2824314832687378,
      "eval_runtime": 74.7028,
      "eval_samples_per_second": 5.609,
      "eval_steps_per_second": 0.361,
      "step": 45
    },
    {
      "epoch": 2.891566265060241,
      "step": 45,
      "total_flos": 75324331130880.0,
      "train_loss": 0.33777744240230984,
      "train_runtime": 12667.2664,
      "train_samples_per_second": 1.885,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 10,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 75324331130880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}