Best000 commited on
Commit
9c4df58
·
verified ·
1 Parent(s): 15cbebe

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:ff1466b861d587d8d4ca4d3c0343544c6a645b0c7a50bc9daf70b174e8889c08
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70fdda0557ed81baedb1ab86da3de4d7996cb20a05b406e06eebfc4f994edd0c
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7792834970f7b9d1e8110b5c6ef4f47e07282aaf9d3444408829d12a09b1a6a
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86096d1138ea845baeba49d6556d7ca988b15980a2b01409d1949bd76bcaaccf
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e465eb0265e76c1c3121bcc183ba1f1604238c641718592811ee2b5b90c7fa47
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": 0.00021894214453830574,
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": 24.362,
74
  "eval_steps_per_second": 12.182,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1267309624688640.0,
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": 0.00032841321680745865,
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": 24.362,
74
  "eval_steps_per_second": 12.182,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0002554325019613567,
79
+ "grad_norm": 1.836844563484192,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9654,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00029192285938440767,
86
+ "grad_norm": 1.6875149011611938,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.8015,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00032841321680745865,
93
+ "grad_norm": 0.9613115787506104,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7253,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00032841321680745865,
100
+ "eval_loss": 1.612996220588684,
101
+ "eval_runtime": 663.2626,
102
+ "eval_samples_per_second": 17.397,
103
+ "eval_steps_per_second": 8.699,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1953769004728320.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null