Aivesa commited on
Commit
d6ab0f2
·
verified ·
1 Parent(s): 32c3428

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 sha256:2535575b2c08801d1970153e249ecce5d31c50146a4bc1a1d5f143b97408537c
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f05ca6b5c548e1523a60d420f1494556c9f1f9603be9d688b89f6a952e8fb1
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c6244550a7ac3b7d709661bf184ce50caf24a083e4fc77f4450a355853edd8d
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476ea86efae19fce14debbd2ea3a6ecc0f8779bbb220a0a5788a6a8f9af33035
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db09b140128a78da98f28da6f39e290e9550692345a1a0d0f7ed1cbb8aa74cc3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed657ca35a3b26ab39201e05f010d681b5d27ca2e383b370948911cf5bec9601
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": 0.0012791131482172361,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 17.719,
66
  "eval_steps_per_second": 8.864,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 194578955108352.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.001918669722325854,
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,
 
65
  "eval_samples_per_second": 17.719,
66
  "eval_steps_per_second": 8.864,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0014922986729201087,
71
+ "grad_norm": 1.2520461082458496,
72
+ "learning_rate": 0.00014,
73
+ "loss": 1.1799,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0017054841976229813,
78
+ "grad_norm": 0.7413159608840942,
79
+ "learning_rate": 0.00016,
80
+ "loss": 1.1628,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.001918669722325854,
85
+ "grad_norm": 0.740929126739502,
86
+ "learning_rate": 0.00018,
87
+ "loss": 1.0792,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.001918669722325854,
92
+ "eval_loss": 1.0034116506576538,
93
+ "eval_runtime": 110.8915,
94
+ "eval_samples_per_second": 17.81,
95
+ "eval_steps_per_second": 8.91,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 291868432662528.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null