kostiantynk-out commited on
Commit
c98df9f
·
verified ·
1 Parent(s): a85bb04

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:fabb1498a40b5b902e19b4c04b48775020f0a4efcad0f615d68081456bd7f70d
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e6a19a90c6a9a5f3f6ab9fb47df04e74dd83c5f5bb729827ce3206cf27e22a
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f70ec39ff8682bbd829f3233c18d6b8fdc0e4f66ffe46969221c69987db54f02
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e3e452ac26f16ff4f6f2648092b9c103cfc67e604343992cf03ffe19cfdec32
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d535d91cb488f359eba4014dbef366efc23fdf15f3e817cbecb2688aaf399c87
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e75bea88fbc370ab33b3e1bfa175560e2af9ca52839627e9a58cea5883f1ec18
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": 9.937888198757764e-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": 21.02,
74
  "eval_steps_per_second": 10.51,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 820048664985600.0,
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": 0.00014906832298136645,
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": 21.02,
74
  "eval_steps_per_second": 10.51,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00011594202898550724,
79
+ "grad_norm": 0.32047656178474426,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.4038,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00013250517598343685,
86
+ "grad_norm": 0.4309922754764557,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.694,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00014906832298136645,
93
+ "grad_norm": 0.38406458497047424,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7324,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00014906832298136645,
100
+ "eval_loss": 1.6416521072387695,
101
+ "eval_runtime": 1209.7696,
102
+ "eval_samples_per_second": 21.013,
103
+ "eval_steps_per_second": 10.507,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1271075430727680.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null