flytech commited on
Commit
77ceeca
·
1 Parent(s): a57e1a1

Training in progress, step 600, 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:e61644999d20947b325c32c729fc35461ccfe86753d680cc7eddfe8f525ac6ab
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f333d800cd7c383c7a8320063438832839ce7fece3931ad8b890f0413c4a555
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e6289a4d857f2fca98577d7d6c5dfee43f2bd6b301cdef3d618b986e89d6f0a
3
  size 20524127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb3bdd870afd194a2689ca3346517401bb1df3a346d5b0c4250e169b35ce542
3
  size 20524127
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9cb949c8ad1fdceaf96981759b8ff42882e1cbc3455d7d289052761730e50f4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a51cf2740940fbaca46f09a810eeca0eb86be9f79d7d359cd271462beefad583
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3fb62e1a686af03a6294538f23b0512dc4df0d77f62afb535a9f3732c29458d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0b2196e2f29a6683acf49e9b6eb98e7393791df29402c783d469811f16cf26
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.567398119122257,
5
  "eval_steps": 100,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -72,13 +72,26 @@
72
  "eval_samples_per_second": 1.757,
73
  "eval_steps_per_second": 0.221,
74
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
76
  ],
77
  "logging_steps": 100,
78
  "max_steps": 957,
79
  "num_train_epochs": 3,
80
  "save_steps": 100,
81
- "total_flos": 8.300901581822362e+16,
82
  "trial_name": null,
83
  "trial_params": null
84
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8808777429467085,
5
  "eval_steps": 100,
6
+ "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
72
  "eval_samples_per_second": 1.757,
73
  "eval_steps_per_second": 0.221,
74
  "step": 500
75
+ },
76
+ {
77
+ "epoch": 1.88,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.5462,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 1.88,
84
+ "eval_runtime": 512.6885,
85
+ "eval_samples_per_second": 1.755,
86
+ "eval_steps_per_second": 0.22,
87
+ "step": 600
88
  }
89
  ],
90
  "logging_steps": 100,
91
  "max_steps": 957,
92
  "num_train_epochs": 3,
93
  "save_steps": 100,
94
+ "total_flos": 9.961912403597722e+16,
95
  "trial_name": null,
96
  "trial_params": null
97
  }