kostiantynk commited on
Commit
e1cfd67
·
verified ·
1 Parent(s): a89d001

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:c9c4d4367d33848509559e64c70d136b04dbe3299c9725b2aeeeed1b1b3e0725
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef8de12bbb3bd05fdf8548f5f5c22f0f20bc23a1c8d3e2787acda427cb47d81
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314d31f77788b408a47e0587ee8a9f4d7c12e27dab88d6c3a11bd91921e8f50a
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de4ad621bfb9357c5be79a8a088b7decb8e3e19f06cf48e5aca23eb6fb0c8d87
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ab38f29dda544c1b38df51e18795bd51fd042e0475e338e0801f2540eb736d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af5d8915c382105692ed749d9b6188f0a4abba79bdfb71cd3d9dfe9637ef600
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": 0.00010633725747351538,
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": 31.716,
74
  "eval_steps_per_second": 15.858,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1029889327104000.0,
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": 0.00015950588621027308,
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": 31.716,
74
  "eval_steps_per_second": 15.858,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00012406013371910128,
79
+ "grad_norm": 0.7685911655426025,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.0244,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00014178300996468718,
86
+ "grad_norm": 1.1620005369186401,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.2182,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00015950588621027308,
93
+ "grad_norm": 1.1282984018325806,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.1027,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00015950588621027308,
100
+ "eval_loss": 1.106915831565857,
101
+ "eval_runtime": 749.5623,
102
+ "eval_samples_per_second": 31.696,
103
+ "eval_steps_per_second": 15.848,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1606627350282240.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null