VERSIL91 commited on
Commit
d265a04
·
verified ·
1 Parent(s): 8de007b

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175611924e56ceb6e6006129c6939abb5d86acd4c17f1dd037f7ab6e32eaf45d
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1065c61b38279d6fd72babd656255a9059642caa17ee44f4bede883bb1a1527c
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ebbe51251b88048676d80cc2dd8611e9f63b139d2cbde8d66c23469d599d5d6
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2677c3d7da9719b322ba605fc61d4e99121a980db2b7a575146e85cbf7f7a01
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
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": 0.019176987614862164,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 45.292,
74
  "eval_steps_per_second": 22.689,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4182326510616576.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.028765481422293248,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 45.292,
74
  "eval_steps_per_second": 22.689,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.022373152217339192,
79
+ "grad_norm": 2.880462646484375,
80
+ "learning_rate": 7e-05,
81
+ "loss": 5.6402,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.02556931681981622,
86
+ "grad_norm": 4.132447719573975,
87
+ "learning_rate": 8e-05,
88
+ "loss": 5.5549,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.028765481422293248,
93
+ "grad_norm": 2.7458152770996094,
94
+ "learning_rate": 9e-05,
95
+ "loss": 5.3865,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.028765481422293248,
100
+ "eval_loss": 5.598178863525391,
101
+ "eval_runtime": 11.6299,
102
+ "eval_samples_per_second": 45.314,
103
+ "eval_steps_per_second": 22.7,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6273489765924864.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null