jssky commited on
Commit
3bfbafc
1 Parent(s): e630dd1

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 sha256:8b91a26c76be8588b28984eda809f9a80329aff727d37fa714f14f4e8e79def3
3
  size 200068512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e392b092eab174fe8893a606c083e7fa88d4a609eb04e3b96ed5370d3e6d511
3
  size 200068512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:965e7369cd488492c478eca7f12c9d15ef54a668cd92b417b66099beb4c2f505
3
  size 102030196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0646c1c88ccaaa1f6830a797935a91e876612c121058e60bb730dc49a77fcc
3
  size 102030196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc47c3a1464826449c4b706b5a992ed4ba8b7c1085ff4feb0c933558ef732feb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd4269677e3d335673fbcee71e5b78f83433b7173960adf0a51d212c7727af18
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": 0.0004929548535513289,
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": 4.283,
74
  "eval_steps_per_second": 4.283,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4601366169255936.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0007394322803269934,
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": 4.283,
74
  "eval_steps_per_second": 4.283,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0005751139958098837,
79
+ "grad_norm": 1.472562313079834,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.8744,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0006572731380684385,
86
+ "grad_norm": 0.7952223420143127,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.4751,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0007394322803269934,
93
+ "grad_norm": 1.635096788406372,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.863,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0007394322803269934,
100
+ "eval_loss": 0.9735259413719177,
101
+ "eval_runtime": 599.4848,
102
+ "eval_samples_per_second": 4.275,
103
+ "eval_steps_per_second": 4.275,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6902049253883904.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null