Aivesa commited on
Commit
7fe7a39
·
verified ·
1 Parent(s): 9d2f674

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:df0dfb52799bb5302892ddba0fc67d617fb333d0d9fec872cb68044048d3d478
3
  size 28351000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932627367d1ee3d40425e5f608c31b45f77ad2d8266f2136fa6ca68131658b3e
3
  size 28351000
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ab44d8c6fe593fb663a1f886885540533a3cf7205ef17345b474c4f29652fb7
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054291d9f7528140562323b56ea1759b20e059de05304fbdb40f1924798dbf65
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9496d8ed5195cd973b66d4c34811d290189626269b2a31dc82c82d975038725b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd0c719b07becd12707f516b5805a0c5e7f44255f91a52de0c74a2609cd57ec
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": 0.0005157408402277856,
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": 31.268,
66
  "eval_steps_per_second": 15.637,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 179259385577472.0,
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": 0.0007736112603416783,
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": 31.268,
66
  "eval_steps_per_second": 15.637,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0006016976469324165,
71
+ "grad_norm": 17.67934226989746,
72
+ "learning_rate": 0.00014,
73
+ "loss": 14.5922,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0006876544536370474,
78
+ "grad_norm": 21.108476638793945,
79
+ "learning_rate": 0.00016,
80
+ "loss": 14.2659,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.0007736112603416783,
85
+ "grad_norm": 17.110633850097656,
86
+ "learning_rate": 0.00018,
87
+ "loss": 11.7024,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.0007736112603416783,
92
+ "eval_loss": 2.6825897693634033,
93
+ "eval_runtime": 148.9963,
94
+ "eval_samples_per_second": 32.88,
95
+ "eval_steps_per_second": 16.443,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 268889078366208.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null