ClarenceDan commited on
Commit
2855243
·
verified ·
1 Parent(s): 9e0a009

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 sha256:96d025ee7fc1fddeb31e05fd710ad2881aa3105da2f578f296c14bcf5c1d370c
3
  size 556856304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77c836d16a4615a05b0f4f10e84e7fed1c5a2cc38d7bbbdad0b3bcd44da71b6
3
  size 556856304
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8146958e3d5a26523a1e179da1d84116cf5270a0d2c52d2434411895f8205d27
3
  size 21599060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9477da2f772e6008a21d93101c1713cd80e6bafe77a21aeeb866df5b32777f
3
  size 21599060
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd49a6a29158781827d1be6769bd03cd9113fe49c3067ab42e96e4723594e1a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a35eeaee2fc6ff5eb7293ee55ff68f802ce990682daebb0cbe7616b4bd61689f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.020100502512562814,
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": 51.538,
74
  "eval_steps_per_second": 25.769,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 424417060454400.0,
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": 0.03015075376884422,
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": 51.538,
74
  "eval_steps_per_second": 25.769,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.023450586264656615,
79
+ "grad_norm": 2.288501024246216,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.8796,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.02680067001675042,
86
+ "grad_norm": 2.6295199394226074,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.7079,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.03015075376884422,
93
+ "grad_norm": 2.4342594146728516,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.0453,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.03015075376884422,
100
+ "eval_loss": 1.0322495698928833,
101
+ "eval_runtime": 2.4292,
102
+ "eval_samples_per_second": 51.869,
103
+ "eval_steps_per_second": 25.934,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 620301857587200.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null