pedrosperber760 commited on
Commit
8c384d2
·
verified ·
1 Parent(s): a9ac09f

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 sha256:9c8082d05112c87bff18a06d89ae71f7ec8f1f8f5d3d50a12b5a6f31da4b4ba5
3
  size 619632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4a43ac8091611c1cc53514ea9ec33e40f430d7183a44ea6d8d21d3ea737dfb
3
  size 619632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea51a0b2f1b147765212a0c129875b40034c0f21b63b72c171e6b36fcb2a3ffd
3
  size 1324026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9bfbfa34ddb1d304aadabeeb65701d22db5895820bc2237c19822b2ac5dabc
3
  size 1324026
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba51572f4be7b333f9d714c27401cf70ead5183b8f6bf9320618c25d4360c826
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e82a545308bfc3ba013924b6db78f99518b732725545f075a75afa654078ba6
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": 0.002761795166858458,
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": 14.951,
74
  "eval_steps_per_second": 7.484,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 6093665206272.0,
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": 0.004142692750287687,
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": 14.951,
74
  "eval_steps_per_second": 7.484,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.003222094361334868,
79
+ "grad_norm": 0.4935219883918762,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.9358,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.003682393555811277,
86
+ "grad_norm": 0.6514948606491089,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.9266,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004142692750287687,
93
+ "grad_norm": 0.6624245643615723,
94
+ "learning_rate": 0.00018,
95
+ "loss": 11.9153,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004142692750287687,
100
+ "eval_loss": 11.91427993774414,
101
+ "eval_runtime": 61.1185,
102
+ "eval_samples_per_second": 14.971,
103
+ "eval_steps_per_second": 7.494,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 9140497809408.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null