Aivesa commited on
Commit
d79209a
·
verified ·
1 Parent(s): af4af12

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 sha256:132bfd1885b3e582262defd33e2a8aed63391de03abdd6e612ec5840911ac627
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300030c64a040eebdce7f56bfbb07229963377af5de43cf442518036da1e52ff
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae92c6a01b2979cf89dd6c75b438bf1d70417f8627bfdabbfaacc9634016818b
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd397d678e4bb5cbc2e8ffd54ce508b0c82866e5a3709438b6b0abb48d037b2
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57c112d728db58d29f71bf4e1a6ae26adace414e49ebf93dab769a4c16e64e9b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbb4cc74a9123e469cd1f379297969ebdc6fd5c7772857ffca5080eff9696a3
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": 0.00010633725747351538,
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": 19.013,
66
  "eval_steps_per_second": 9.506,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 1029889327104000.0,
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": 0.00015950588621027308,
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": 19.013,
66
  "eval_steps_per_second": 9.506,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00012406013371910128,
71
+ "grad_norm": 1.4571468830108643,
72
+ "learning_rate": 0.00014,
73
+ "loss": 1.1742,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.00014178300996468718,
78
+ "grad_norm": 1.365078091621399,
79
+ "learning_rate": 0.00016,
80
+ "loss": 1.3437,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.00015950588621027308,
85
+ "grad_norm": 1.2348759174346924,
86
+ "learning_rate": 0.00018,
87
+ "loss": 1.1785,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.00015950588621027308,
92
+ "eval_loss": 1.2093638181686401,
93
+ "eval_runtime": 1246.7289,
94
+ "eval_samples_per_second": 19.056,
95
+ "eval_steps_per_second": 9.528,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1606627350282240.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null