dimasik87 commited on
Commit
f726108
·
verified ·
1 Parent(s): 78dfc4f

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64d2d0f3a99076efe00b4d963b59518a2bc0cbdc76926db1f7b54dec769c8f0c
3
  size 188784440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72ae97b1dabcd1d7b094c08646e4ba8510ec8e7406f6132dd0fc702d79a4b07
3
  size 188784440
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28228387b3d86a71eafb1839122ef52fe14e8c421f388a2d838e46c3d6dc1954
3
  size 377730170
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a911b06181857a92b920bb85d3cdfa80fca985c7937e50bbdb565e63233e69b
3
  size 377730170
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b77b1f7da4f0c77ec6d9f7bdfb7f8fbd3bce45d80069dfa252b5392b999ebdb9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53fb372c56db8f7a16a1a81f0da1ba4cadbea9f242005a713a4e4aa9740a2981
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8709966540336609,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
- "epoch": 0.049782202862476664,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -89,6 +89,50 @@
89
  "eval_samples_per_second": 14.771,
90
  "eval_steps_per_second": 7.386,
91
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -112,12 +156,12 @@
112
  "should_evaluate": false,
113
  "should_log": false,
114
  "should_save": true,
115
- "should_training_stop": false
116
  },
117
  "attributes": {}
118
  }
119
  },
120
- "total_flos": 1.14344142569472e+16,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8604340553283691,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-30",
4
+ "epoch": 0.07467330429371499,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 14.771,
90
  "eval_steps_per_second": 7.386,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.0522713130056005,
95
+ "grad_norm": 1.4493108987808228,
96
+ "learning_rate": 8.435655349597689e-05,
97
+ "loss": 3.5754,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.059738643434972,
102
+ "grad_norm": 1.3764252662658691,
103
+ "learning_rate": 4.12214747707527e-05,
104
+ "loss": 3.4635,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.06222775357809583,
109
+ "eval_loss": 0.8631235361099243,
110
+ "eval_runtime": 11.5249,
111
+ "eval_samples_per_second": 14.751,
112
+ "eval_steps_per_second": 7.375,
113
+ "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.0672059738643435,
117
+ "grad_norm": 1.310421347618103,
118
+ "learning_rate": 1.0899347581163221e-05,
119
+ "loss": 3.4281,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.07467330429371499,
124
+ "grad_norm": 1.4106675386428833,
125
+ "learning_rate": 0.0,
126
+ "loss": 3.3246,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.07467330429371499,
131
+ "eval_loss": 0.8604340553283691,
132
+ "eval_runtime": 11.5063,
133
+ "eval_samples_per_second": 14.774,
134
+ "eval_steps_per_second": 7.387,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
156
  "should_evaluate": false,
157
  "should_log": false,
158
  "should_save": true,
159
+ "should_training_stop": true
160
  },
161
  "attributes": {}
162
  }
163
  },
164
+ "total_flos": 1.71516213854208e+16,
165
  "train_batch_size": 2,
166
  "trial_name": null,
167
  "trial_params": null