sirr commited on
Commit
75c368f
·
1 Parent(s): 5f487a7

Training in progress, step 150, 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:c0bd0423f52b2a4aa9999fcb90b0a2327c152a576fb3f60e026f2cfc949f6300
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1e27a71880448a4f86a29c01358f223b55768acfc39b9394a1f6d80ffe0b37
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a96f42badf9b67315c31925b377e840ac7c69b9c01cafb1c78f5bfc292689af7
3
  size 20523679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e8fd351f477bcbea6e1c6d5a8f0efdee9ab4b085921def577b901a3b42cb2d
3
  size 20523679
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e6133cfbe6b203260730d5cda99c4eaf547dfefa4c1613ec36cb62426fa8631
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98cee008296b651fc8b131d00e95bdcd9cf0797f8de2621cdaa91df84478a7f9
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ed82c0bba951f973ce48f993359fb52fe391d6fd123375d0ee031a60ee5b54
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e756cf8f535e6353e9e0153cfd62f3373a6886e42dca75c868e102fd3633051e
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": 1.25,
5
  "eval_steps": 25,
6
- "global_step": 125,
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": 1.85,
73
  "eval_steps_per_second": 0.157,
74
  "step": 125
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
76
  ],
77
  "logging_steps": 25,
78
  "max_steps": 200,
79
  "num_train_epochs": 2,
80
  "save_steps": 25,
81
- "total_flos": 2.0762635272192e+16,
82
  "trial_name": null,
83
  "trial_params": null
84
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.5,
5
  "eval_steps": 25,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
72
  "eval_samples_per_second": 1.85,
73
  "eval_steps_per_second": 0.157,
74
  "step": 125
75
+ },
76
+ {
77
+ "epoch": 1.5,
78
+ "learning_rate": 0.0001,
79
+ "loss": 0.5296,
80
+ "step": 150
81
+ },
82
+ {
83
+ "epoch": 1.5,
84
+ "eval_runtime": 216.4796,
85
+ "eval_samples_per_second": 1.848,
86
+ "eval_steps_per_second": 0.157,
87
+ "step": 150
88
  }
89
  ],
90
  "logging_steps": 25,
91
  "max_steps": 200,
92
  "num_train_epochs": 2,
93
  "save_steps": 25,
94
+ "total_flos": 2.49151623266304e+16,
95
  "trial_name": null,
96
  "trial_params": null
97
  }