sirr commited on
Commit
fe59400
·
1 Parent(s): b9c0aac

Training in progress, step 125, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78cc7f4de672c480450afd7b2ecc815f1a648886726cf5200264464ac63a58c3
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bd0423f52b2a4aa9999fcb90b0a2327c152a576fb3f60e026f2cfc949f6300
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:039637b8b389137879b303679fa583684724a9b94a0142e14cdaeabb5b2054f0
3
  size 20523679
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96f42badf9b67315c31925b377e840ac7c69b9c01cafb1c78f5bfc292689af7
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:bdb439cc7745e50177086dc51c98138686500e54700396db181a6a504f1ce367
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6133cfbe6b203260730d5cda99c4eaf547dfefa4c1613ec36cb62426fa8631
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eac50daf1bc36d76b3b1e01379287cfbfcbbe7ebea9864f699ceb21bbe636b01
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ed82c0bba951f973ce48f993359fb52fe391d6fd123375d0ee031a60ee5b54
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": 1.0,
5
  "eval_steps": 25,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,13 +59,26 @@
59
  "eval_samples_per_second": 1.846,
60
  "eval_steps_per_second": 0.157,
61
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 25,
65
  "max_steps": 200,
66
  "num_train_epochs": 2,
67
  "save_steps": 25,
68
- "total_flos": 1.66101082177536e+16,
69
  "trial_name": null,
70
  "trial_params": null
71
  }
 
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,
 
59
  "eval_samples_per_second": 1.846,
60
  "eval_steps_per_second": 0.157,
61
  "step": 100
62
+ },
63
+ {
64
+ "epoch": 1.25,
65
+ "learning_rate": 0.0001,
66
+ "loss": 0.4976,
67
+ "step": 125
68
+ },
69
+ {
70
+ "epoch": 1.25,
71
+ "eval_runtime": 216.1906,
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
  }