Hugging Face's logo

stefanj0
/
t5gemma-math-corrector

PEFT
Safetensors
Transformers
lora
Model card Files
xet
 Community
stefanj0 commited on
Commit
e3d84a2
·
verified ·
1 Parent(s): 6509e5b

Training in progress, step 400, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +40 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb7edc022a38beb145ffb51c73bf9826a63972fa7eb7866f4c9659074c1a8c43
3
  size 8297288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4fb84457a91c5de153894c7ca0e8bf12972e85157cdf5d915e11430fc00bf59
3
  size 8297288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ff0ff603551669ef970f84399569e9870a0c8597521fcef27f66df3c6f5ef22
3
  size 16761163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46556fd5ff967ca9fb9f57dd94cffedd6630e12727c0a2e7a94c9a92581e7161
3
  size 16761163
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc90d0ce81a109e8e9dd4fc59d9ed7b59e19eb969b6e5c7939731348099ada0d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8147cce07a8085109be600ca968db3999ae311b31412161d0086e0673fa99dee
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc079ff01029f23f0ea697b8a7da7f71ea1510cb9be263645b8bef9dfeb3f70
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c6fc74fad2fa82ce5e6158544172660f4d56e9b794ecdcdf74960d2ac0a30e
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66df8c272ec6ea7fc32240052101ceb1261559eaab8e63c8d4d99dac2464379a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219ab60ad4ef7e10902c21765a32ad47d5cfe315598bf972b3280f68906cb5f2
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 200,
3
  "best_metric": 0.6018396615982056,
4
  "best_model_checkpoint": "./t5gemma-math-corrector/checkpoint-200",
5
- "epoch": 0.6415396952686447,
6
  "eval_steps": 200,
7
- "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -44,6 +44,42 @@
44
  "eval_samples_per_second": 50.454,
45
  "eval_steps_per_second": 12.71,
46
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 50,
@@ -58,7 +94,7 @@
58
  "early_stopping_threshold": 0.0
59
  },
60
  "attributes": {
61
- "early_stopping_patience_counter": 0
62
  }
63
  },
64
  "TrainerControl": {
@@ -72,7 +108,7 @@
72
  "attributes": {}
73
  }
74
  },
75
- "total_flos": 773230008729600.0,
76
  "train_batch_size": 4,
77
  "trial_name": null,
78
  "trial_params": null
 
2
  "best_global_step": 200,
3
  "best_metric": 0.6018396615982056,
4
  "best_model_checkpoint": "./t5gemma-math-corrector/checkpoint-200",
5
+ "epoch": 1.2822774659182037,
6
  "eval_steps": 200,
7
+ "global_step": 400,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 50.454,
45
  "eval_steps_per_second": 12.71,
46
  "step": 200
47
+ },
48
+ {
49
+ "epoch": 0.8019246190858059,
50
+ "grad_norm": 0.2022608071565628,
51
+ "learning_rate": 8.15914489311164e-05,
52
+ "loss": 0.0064,
53
+ "step": 250
54
+ },
55
+ {
56
+ "epoch": 0.9623095429029671,
57
+ "grad_norm": 0.8748292922973633,
58
+ "learning_rate": 7.565320665083135e-05,
59
+ "loss": 0.0047,
60
+ "step": 300
61
+ },
62
+ {
63
+ "epoch": 1.1218925421010426,
64
+ "grad_norm": 0.28713762760162354,
65
+ "learning_rate": 6.971496437054633e-05,
66
+ "loss": 0.0025,
67
+ "step": 350
68
+ },
69
+ {
70
+ "epoch": 1.2822774659182037,
71
+ "grad_norm": 0.16400396823883057,
72
+ "learning_rate": 6.377672209026129e-05,
73
+ "loss": 0.0029,
74
+ "step": 400
75
+ },
76
+ {
77
+ "epoch": 1.2822774659182037,
78
+ "eval_loss": 1.9704385995864868,
79
+ "eval_runtime": 5.1665,
80
+ "eval_samples_per_second": 50.711,
81
+ "eval_steps_per_second": 12.775,
82
+ "step": 400
83
  }
84
  ],
85
  "logging_steps": 50,
 
94
  "early_stopping_threshold": 0.0
95
  },
96
  "attributes": {
97
+ "early_stopping_patience_counter": 1
98
  }
99
  },
100
  "TrainerControl": {
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 1545010211192832.0,
112
  "train_batch_size": 4,
113
  "trial_name": null,
114
  "trial_params": null