flytech commited on
Commit
dd3b924
1 Parent(s): fc246ef

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528a1cb84c1fa9945abbc969e94dfcc649bbfcdffde5ed1d0bbfb31a6bc945cf
3
  size 14708920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff2942e086fee64e229a4e2a26064062a784e94d190c2b6770488551814df5f
3
  size 14708920
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7867bb45f4fa0e7f5e4cc0ff28d910219ddfc1fd0301ca0e70a496143cd3e296
3
  size 7601989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3326d984fd9d9dbf90e3668982e4a493b4d0bc8c2a550626cf01b411a0383ec4
3
  size 7601989
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b945e413c47252104d7d309ecd70b494c59b461206abacd8f0ee381044585e6
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9025cc4e0da6c63c9bfa2164c686a6228c0b57e1cfeed81ad3255941a7fe7b0
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30b719cdc1f0ed508178a52385f5ad66b1ee8902b555924a5affd41a8c371317
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f2ca6113578d7efef90342397e73138a7a92da90251edb146063c752147788
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": 1.50564617314931,
5
  "eval_steps": 200,
6
- "global_step": 800,
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": 2.228,
60
  "eval_steps_per_second": 0.279,
61
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 200,
65
  "max_steps": 1593,
66
  "num_train_epochs": 3,
67
  "save_steps": 200,
68
- "total_flos": 1.7867105116009267e+17,
69
  "trial_name": null,
70
  "trial_params": null
71
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8820577164366374,
5
  "eval_steps": 200,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 2.228,
60
  "eval_steps_per_second": 0.279,
61
  "step": 800
62
+ },
63
+ {
64
+ "epoch": 1.88,
65
+ "learning_rate": 2e-05,
66
+ "loss": 0.6491,
67
+ "step": 1000
68
+ },
69
+ {
70
+ "epoch": 1.88,
71
+ "eval_runtime": 1014.137,
72
+ "eval_samples_per_second": 2.219,
73
+ "eval_steps_per_second": 0.278,
74
+ "step": 1000
75
  }
76
  ],
77
  "logging_steps": 200,
78
  "max_steps": 1593,
79
  "num_train_epochs": 3,
80
  "save_steps": 200,
81
+ "total_flos": 2.2334346732679987e+17,
82
  "trial_name": null,
83
  "trial_params": null
84
  }