ClarenceDan commited on
Commit
79cfd3b
·
verified ·
1 Parent(s): bfe61eb

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:e9b3c0b11caeb6fc62a18593d8ebaa21368a7e637f3a4487aa05e05bf41524e8
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c77791fbc182362cd1a07c9dedd264b33f506b618d4fec18e81af3e4fc7338
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acb8212600331bcd9d0514b37face03806f019c76ebf4f6a2164994a3ff07960
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90afdab94686cdecead995aa4f5d6b8ff7969cdf67ea620fd34509c1c85fd7a7
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af5d8915c382105692ed749d9b6188f0a4abba79bdfb71cd3d9dfe9637ef600
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": 0.0008983380745620602,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 10.147,
74
  "eval_steps_per_second": 5.075,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1099405738377216.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0013475071118430903,
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,
 
73
  "eval_samples_per_second": 10.147,
74
  "eval_steps_per_second": 5.075,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0010480610869890701,
79
+ "grad_norm": 7.179202079772949,
80
+ "learning_rate": 0.00014,
81
+ "loss": 13.0076,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0011977840994160803,
86
+ "grad_norm": 7.2814178466796875,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.1482,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013475071118430903,
93
+ "grad_norm": 8.782493591308594,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.904,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013475071118430903,
100
+ "eval_loss": 2.6142091751098633,
101
+ "eval_runtime": 209.0104,
102
+ "eval_samples_per_second": 13.459,
103
+ "eval_steps_per_second": 6.732,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1588030510989312.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null