lesso02 commited on
Commit
49e220b
1 Parent(s): 43f0114

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:f6d720a608c5e53080a8325eca6e3a801091a412083a6756e13d4984c102bc70
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd930926d4b53c0f3cc88a0f47484fcf6ea4e738add79dd4e4349564420a32d
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d88a93debff029f855385dc7dc0b0b94413c9f396957e196d9d6334a74296e
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3291c5a6d95ccbcdd769d8239706f3e9ff859038c05a2fdab2be8d746e12ec
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fa5a9e7fe9b733f4d7378c2f4295e39738bd784ce49157561d991d047aeb2c0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7aff96afc5f824b7ed5aecc135005bf3f081ddcf459ff2ffbdc421f0310581
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": 0.01818181818181818,
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": 20.069,
74
  "eval_steps_per_second": 10.107,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 492029198991360.0,
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": 0.02727272727272727,
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": 20.069,
74
  "eval_steps_per_second": 10.107,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.021212121212121213,
79
+ "grad_norm": 2.3415682315826416,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.6022,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.024242424242424242,
86
+ "grad_norm": 2.3357975482940674,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.6437,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.02727272727272727,
93
+ "grad_norm": 2.6000447273254395,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.3052,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.02727272727272727,
100
+ "eval_loss": 1.2580008506774902,
101
+ "eval_runtime": 6.9222,
102
+ "eval_samples_per_second": 20.08,
103
+ "eval_steps_per_second": 10.112,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 738043798487040.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null