Hugging Face's logo

filipesantoscv11
/
e913668d-907c-4372-b6be-e98f019104ed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
filipesantoscv11 commited on
Commit
e5c6ff3
·
verified ·
1 Parent(s): 17c0485

Training in progress, step 20, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +40 -3
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a99e4b71ea57d5dfd637c8af4145423a4425283bb3e660d6fc3f3e4636b8b43
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e4cf0a14390d8c3cec2477094799900764970c6a2458451fd1ced00c131dac
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ea466d511e1a2e2d438975c20dfe662dadf3a666bef7933c7d8b8612870b5b4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2721d9797680bada7824495ced0fb99bce5e40e55f13ebe900c47ed6b7a447
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.013821700069108501,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 54.63,
53
  "eval_steps_per_second": 27.405,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +108,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 514684386017280.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.027643400138217002,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 54.63,
53
  "eval_steps_per_second": 27.405,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.0165860400829302,
58
+ "grad_norm": NaN,
59
+ "learning_rate": 9.755282581475769e-05,
60
+ "loss": 0.0,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.02073255010366275,
65
+ "grad_norm": NaN,
66
+ "learning_rate": 8.535533905932738e-05,
67
+ "loss": 0.0,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.02073255010366275,
72
+ "eval_loss": NaN,
73
+ "eval_runtime": 5.5966,
74
+ "eval_samples_per_second": 54.497,
75
+ "eval_steps_per_second": 27.338,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.0248790601243953,
80
+ "grad_norm": NaN,
81
+ "learning_rate": 6.545084971874738e-05,
82
+ "loss": 0.0,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.027643400138217002,
87
+ "eval_loss": NaN,
88
+ "eval_runtime": 5.504,
89
+ "eval_samples_per_second": 55.415,
90
+ "eval_steps_per_second": 27.798,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 1029368772034560.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null