philip-hightech commited on
Commit
b130abf
·
verified ·
1 Parent(s): e5335de

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 sha256:72814693ff4ba6cc51fabaceb6f87afb2a31c2245cc9aa71e8b3a5aa472098b9
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc269dcda211d22c71d626222f1ceefbf2ad832310bb888ad32e736d89814bb
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5861ef96e72bff732f7abf2eafb62f2bc28793427e65b240ae13a3bd18666e83
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776dd1fe3dde1ad33936a85613c4d25efd1536681be81eac2627229ac9c2ac3f
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ba291346724fb793dde7743a37a5130c6eef9adfeff80468448ee6bf2d971d5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d3566a6eddc2a82b7fedc46f9816ab34410dc4ef3e9211eda74f6d684c344b5
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": 9.833848927495851e-05,
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": 17.414,
74
  "eval_steps_per_second": 8.707,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1590605053427712.0,
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": 0.00014750773391243778,
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": 17.414,
74
  "eval_steps_per_second": 8.707,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0001147282374874516,
79
+ "grad_norm": 1.8790661096572876,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.5038,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0001311179856999447,
86
+ "grad_norm": 2.056502342224121,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.1962,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00014750773391243778,
93
+ "grad_norm": 1.2043896913528442,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7013,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00014750773391243778,
100
+ "eval_loss": 1.8729199171066284,
101
+ "eval_runtime": 1474.8493,
102
+ "eval_samples_per_second": 17.419,
103
+ "eval_steps_per_second": 8.709,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2360252659924992.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null