quannh197 commited on
Commit
96986a6
·
verified ·
1 Parent(s): 3bf8271

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 sha256:48cb17aa1f78b09e52a962dd39b69c186b6313e5cbcb85f9867cfd39e6722a57
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:235f8db7df9cab8c8d22892a05458d4127d39ce3246cb234d80203eecebdeb75
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:604b00ba66d9175e2ae3af120ef54f4c6b136097ed0810cf5b0b5c988dc5bd73
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e7d3e1d4b652026a885652fa5488b6b8085ec604d301f90664e821cebcabbc
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab4a38a5f8cb730ad7b7d6266876133f2bd3b82a7a3376ae62ebba181825498
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163020c3a5e3deb0c9f202a04693b11d0b5de442bd4ef423bf0f0a2016603d4d
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": 0.002551834130781499,
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": 20.226,
74
  "eval_steps_per_second": 10.113,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1710846929534976.0,
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": 0.003827751196172249,
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": 20.226,
74
  "eval_steps_per_second": 10.113,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0029771398192450825,
79
+ "grad_norm": 0.35045647621154785,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.605,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0034024455077086655,
86
+ "grad_norm": 0.3555477559566498,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.6754,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003827751196172249,
93
+ "grad_norm": 0.409112811088562,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.6161,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003827751196172249,
100
+ "eval_loss": 0.6577900648117065,
101
+ "eval_runtime": 48.952,
102
+ "eval_samples_per_second": 20.224,
103
+ "eval_steps_per_second": 10.112,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2774346372218880.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null