great0001 commited on
Commit
4590bea
·
verified ·
1 Parent(s): 10038be

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 sha256:3d0bd72c7177826f139555a31b1e7d8ef3a57220cfaaa07d1b4d2d392d1c4ada
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5dea9e7e89a6bf18b878a15e13f9282ce800849b126959b875bddf33ad982d3
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0f3aca452a0e14b93077cf247c27e80ab064b55fec1457bd5bf700d19d0ede8
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e490e0d662d181caab427c4e262671341bb4b505334095951eb01cd37ecaec5d
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c82605a01ce7f2425dfa398cab2f93bde1f3b9bfd9a3df554d9fc68721cd00b3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac91903c5cac39d373ba152e89eaf571f71e7cdfdd359d038b6afb1f47557a7
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": 0.000975371860521824,
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": 43.248,
74
  "eval_steps_per_second": 21.632,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 452766958878720.0,
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": 0.001463057790782736,
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": 43.248,
74
  "eval_steps_per_second": 21.632,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0011379338372754612,
79
+ "grad_norm": 2.2147326469421387,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.1623,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0013004958140290985,
86
+ "grad_norm": 2.1398725509643555,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.1486,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.001463057790782736,
93
+ "grad_norm": 1.8721078634262085,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.9405,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.001463057790782736,
100
+ "eval_loss": 2.027778387069702,
101
+ "eval_runtime": 59.9832,
102
+ "eval_samples_per_second": 43.195,
103
+ "eval_steps_per_second": 21.606,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 697505855569920.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null