ClarenceDan commited on
Commit
a00f666
·
verified ·
1 Parent(s): dfbfa57

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 sha256:140296219b33c9794999c1a928649aa1038d51ce1e5f3bdb207d21c4a093ef03
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623fbf5cb703bbc48c2ca785edc9ba025b56e71a2e6584994a1617c853388c28
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ad3d65ede943bebdd7641182abba9c2354fdff59e9ace49a67d2359f574f7f
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d84d475f06ba3337cf990ad8ef9c5214a1e799b58e3c640f5dfe12a4826a895
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2016bcdd9ab3768f545f9d12095da67be199dcc219634b31be42ed5524ee23f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9a65387ba1ec6c284b308cada9b73ceeb24869d32fa7f81a3120b72b695c1d6
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": 0.00018017206432142696,
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": 12.661,
74
  "eval_steps_per_second": 6.33,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3324514381332480.0,
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": 0.0002702580964821404,
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": 12.661,
74
  "eval_steps_per_second": 6.33,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00021020074170833146,
79
+ "grad_norm": 0.24719107151031494,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.361,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00024022941909523595,
86
+ "grad_norm": 0.3021886944770813,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.2602,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002702580964821404,
93
+ "grad_norm": 0.5306755304336548,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.2036,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002702580964821404,
100
+ "eval_loss": 0.23427625000476837,
101
+ "eval_runtime": 1094.894,
102
+ "eval_samples_per_second": 12.807,
103
+ "eval_steps_per_second": 6.403,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 4986771571998720.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null