great0001 commited on
Commit
ba6b4b9
·
verified ·
1 Parent(s): c807ecb

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 sha256:73203bcf1e177527e0ee5a678f9ff6166b3739a72d0b010f239467e02835adcd
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97dc62be0411b6a2ba03ee083281737ad3c3f59663a15ebd797df4b1aabf5ebb
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5df6dacfe4c916ec9c8eeb2f6a1fade862a66e6821c15b38b03952f41cacd52
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d942fbdcd097c29274f17e1809b8887be590097ebf02d017377b1ba98e8bed
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb409ae620b5bbdfeea121938a3b3d9d9f10021e589f8d860427406bb0f91fc
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": 0.004790419161676647,
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": 25.476,
74
  "eval_steps_per_second": 12.738,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1267309624688640.0,
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": 0.00718562874251497,
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": 25.476,
74
  "eval_steps_per_second": 12.738,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.005588822355289421,
79
+ "grad_norm": 3.140864133834839,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.073,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006387225548902195,
86
+ "grad_norm": 7.965623378753662,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.2922,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00718562874251497,
93
+ "grad_norm": 5.314204216003418,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.7362,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00718562874251497,
100
+ "eval_loss": 3.3656184673309326,
101
+ "eval_runtime": 20.677,
102
+ "eval_samples_per_second": 25.536,
103
+ "eval_steps_per_second": 12.768,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1900964437032960.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null