kokovova commited on
Commit
bde5814
·
verified ·
1 Parent(s): ea29068

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:a1151790881d72a0c9aae3018127f13bd480036895137272840c8ad9d29daa25
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b15febd7d916a385013eeb33d2c031f58dcd271c824fc0bc43daf13e45dad40
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0e02a97dd420652bc09048614b14b09dd80b036cebbf1eef575bf1bc78d3235
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd989543def4bf0105e353cef8f6bfc51c77e97da20743e4dbd2f9afcb08f75
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8077dc599d0e2178961c634ebb1554fd0bb63f56537a068f9b3ec5adbcb0bb0f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef369758a441a46aad70b0a46986242bcc74d362c91bb2673df39add4e7fafc1
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": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.008457553652605984,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 1.5591,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
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": 1.066014263476224e+16,
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": 0.012686330478908976,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 1.5591,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.008880431335236283,
79
+ "grad_norm": 0.9134187698364258,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 1.4547,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.01014906438312718,
86
+ "grad_norm": 0.9056223034858704,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 1.4131,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.01014906438312718,
93
+ "eval_loss": 1.4413870573043823,
94
+ "eval_runtime": 86.9195,
95
+ "eval_samples_per_second": 11.459,
96
+ "eval_steps_per_second": 5.729,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.011417697431018078,
101
+ "grad_norm": 0.7665942311286926,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 1.3923,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.012686330478908976,
108
+ "grad_norm": 1.1542731523513794,
109
+ "learning_rate": 0.0,
110
+ "loss": 1.5591,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1.578362204061696e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null