nadejdatarabukina commited on
Commit
de98024
·
verified ·
1 Parent(s): 2578d4e

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3158685c8cb677569c23421c5ca94001d4f9624a779bc88c0fc0c839b26e3cef
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e824e8e7184d8b84e62bcb22cb841c4b434f354b082619010391e6fc1c36459c
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:540d177efd8f8629d10d519af0b2038268af3b4d0ee62ac3d54b4a6ff7c85233
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56c322420167cd2bfe7b24c0ec5219370383bcd704c581d91262ca3c306a5ff
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae8d4065d911ba11f2f51fe3d3db409db35e37fa178d3f4d6e23c646987dad6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
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": 0.01799370220422852,
5
  "eval_steps": 7,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,28 @@
73
  "learning_rate": 8.954715367323468e-05,
74
  "loss": 2.1973,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +109,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 7418872835604480.0,
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": 0.02249212775528565,
5
  "eval_steps": 7,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 8.954715367323468e-05,
74
  "loss": 2.1973,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.018893387314439947,
79
+ "grad_norm": 4.213700771331787,
80
+ "learning_rate": 3.308693936411421e-05,
81
+ "loss": 2.3979,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.018893387314439947,
86
+ "eval_loss": 2.188023805618286,
87
+ "eval_runtime": 60.3275,
88
+ "eval_samples_per_second": 7.758,
89
+ "eval_steps_per_second": 3.879,
90
+ "step": 21
91
+ },
92
+ {
93
+ "epoch": 0.021592442645074223,
94
+ "grad_norm": 2.784543037414551,
95
+ "learning_rate": 2.1852399266194314e-06,
96
+ "loss": 2.3244,
97
+ "step": 24
98
  }
99
  ],
100
  "logging_steps": 3,
 
109
  "should_evaluate": false,
110
  "should_log": false,
111
  "should_save": true,
112
+ "should_training_stop": true
113
  },
114
  "attributes": {}
115
  }
116
  },
117
+ "total_flos": 9273591044505600.0,
118
  "train_batch_size": 2,
119
  "trial_name": null,
120
  "trial_params": null