Hugging Face's logo

limernyou
/
starcoder-peft-conti

PEFT
Safetensors
Model card Files
xet
 Community
starcoder-peft-conti
File size: 1,619 Bytes
c901f39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 0.14176353812217712,
      "learning_rate": 0.0004,
      "loss": 1.1525,
      "step": 25
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.1460508555173874,
      "learning_rate": 0.0004998852503731983,
      "loss": 1.047,
      "step": 50
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.2368021011352539,
      "learning_rate": 0.0004993848168027977,
      "loss": 0.8529,
      "step": 75
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.14488168060779572,
      "learning_rate": 0.0004984880506341147,
      "loss": 0.9756,
      "step": 100
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.9470569491386414,
      "eval_runtime": 845.9115,
      "eval_samples_per_second": 1.297,
      "eval_steps_per_second": 0.021,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0079315433619456e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}