great0001 commited on
Commit
98e24fc
·
verified ·
1 Parent(s): 5d87b6e

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:ba37e32677dcb19fc4c6ddea7b3d5a2a95073e0296ccbddcf5ed46bb38dd2088
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aef014b61a64471b541cbcb669550c8212aa8494ad80487f53e442533b399bc
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3363fa3cde3fc5d28c563fb40447a37b5684fc288261a9d246f4cc25fc50decb
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9656d5ed081dd89f0dc64003de05cf4cdd67eb6b1c64dbcd5b28864fc8b20ba0
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d096002160b6f6344e44b161020fd5f8176aab00ff00fe8c5ea42cb9ad318a93
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebb3a935f103fde8d7d593f6c636206ae47877a48e671f781108f4a0a6cbb96
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": 9.622092323975848e-05,
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": 127.337,
74
  "eval_steps_per_second": 63.669,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 20575590285312.0,
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": 0.00014433138485963774,
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": 127.337,
74
  "eval_steps_per_second": 63.669,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00011225774377971823,
79
+ "grad_norm": 1.0154387950897217,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.1619,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00012829456431967797,
86
+ "grad_norm": 1.0590178966522217,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.2332,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00014433138485963774,
93
+ "grad_norm": 1.2695728540420532,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.5335,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00014433138485963774,
100
+ "eval_loss": 5.314380645751953,
101
+ "eval_runtime": 206.5011,
102
+ "eval_samples_per_second": 127.147,
103
+ "eval_steps_per_second": 63.574,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 30863385427968.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null