kostiantynk commited on
Commit
97cb996
·
verified ·
1 Parent(s): cb1baa2

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:e85a2a99268b466862c8e9e7e9ed2b4f7ff9315ed84fe5aa27a08c8a4af4c837
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eab753fcca0017f33f104e2b8f09de8b52fe1a13837e52b5883c4c5e10d0192
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3ca78baf3dace1d75f8cffcf53fe611bbcee21affa2125362c46459787c840f
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8a185cd101dab3d5102dee4d622c95c5f7122ee3ce7eb2ad1159e637c37c62
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e040e56b57fd535dc546900c35ef1062c130f252452b7ab3123fc13c917dfa43
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afdcebae8560a2d6cbef8990b206835b56f148729a2a93b18893f76e81bcddbb
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": 0.01957585644371941,
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": 45.699,
74
  "eval_steps_per_second": 22.849,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 67133327278080.0,
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": 0.02936378466557912,
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": 45.699,
74
  "eval_steps_per_second": 22.849,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.022838499184339316,
79
+ "grad_norm": 0.8054418563842773,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8589,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.026101141924959218,
86
+ "grad_norm": 0.853880763053894,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.0009,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.02936378466557912,
93
+ "grad_norm": 0.7069666981697083,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.282,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.02936378466557912,
100
+ "eval_loss": 1.6430575847625732,
101
+ "eval_runtime": 2.8832,
102
+ "eval_samples_per_second": 45.089,
103
+ "eval_steps_per_second": 22.544,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 97822848319488.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null