kostiantynk commited on
Commit
2535ce9
·
verified ·
1 Parent(s): 9eeffc3

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:e4c2bad8f568426c54aae952b35bb9ba60e61d05e874d3d9025713134dd9c00e
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece205fa67a6f6ade664b084c9703f21d20255ea5f904358ce8691f99923b1e8
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf127dc0ebb3b50b6d3a871c0ede031dd390d461a7cd52d1960cb475d01974b
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a043dcfd31cba4de100be0982215390b91161d01df9431724f086aad731bb84
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aae9d006e82da52965e04ac49ff693de4fef6907a5399da8829f5b4c7ba08fcd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d39fb12ea6f2c20be6b5f3a72a7252abad25cc5b58318a939a5ab64512566d
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": 0.00298804780876494,
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": 18.517,
74
  "eval_steps_per_second": 9.258,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1436675532128256.0,
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": 0.004482071713147411,
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": 18.517,
74
  "eval_steps_per_second": 9.258,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0034860557768924302,
79
+ "grad_norm": 1.0134755373001099,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.4683,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00398406374501992,
86
+ "grad_norm": 0.830837607383728,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.5534,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004482071713147411,
93
+ "grad_norm": 0.8642377853393555,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.5087,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004482071713147411,
100
+ "eval_loss": 2.5361790657043457,
101
+ "eval_runtime": 45.6708,
102
+ "eval_samples_per_second": 18.524,
103
+ "eval_steps_per_second": 9.262,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2257632979058688.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null