ClarenceDan commited on
Commit
1572645
·
verified ·
1 Parent(s): 19997bd

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:beba287c1da9986499b08459f83b41439f8c2c5910097deaabda6d234640dfe9
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb1260cbca7e8f93b4e7907ce0435e5f495ab7158207845f17d7422e3b3c2e9
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2e25afba8d8c6d01b3222d0980f2915ef1f50b0c21fa7fc5b2e5aeeb7df6889
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85cd1224a603ff1eea2ffc6a6dbb6e892d689622531690336065c0f999c6654
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda5437f05e2eaed0597b85f69532d5c06b3025917ba7357f9b3d1d946872746
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": 0.00045127202301487317,
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": 58.302,
74
  "eval_steps_per_second": 29.156,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 53422898282496.0,
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": 0.0006769080345223098,
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": 58.302,
74
  "eval_steps_per_second": 29.156,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0005264840268506853,
79
+ "grad_norm": 1.8744231462478638,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.7645,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0006016960306864976,
86
+ "grad_norm": 1.3794890642166138,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.441,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006769080345223098,
93
+ "grad_norm": 1.2784007787704468,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.6678,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006769080345223098,
100
+ "eval_loss": 2.6046085357666016,
101
+ "eval_runtime": 95.0499,
102
+ "eval_samples_per_second": 58.906,
103
+ "eval_steps_per_second": 29.458,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 80134347423744.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null