kostiantynk-out commited on
Commit
9a50f25
·
verified ·
1 Parent(s): 3d3914b

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 sha256:64e18367faeec495a4692d71c9b797eaff09a487d043c0b170d6e5705d485781
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3496245ecf1ab3a3931949f72f6e157b4a43f632ed870c552635fbc42d556ba4
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ade605dec930b52f8ee8773fa88cdb63ac7918025de1c3d5191d3d207207ff9
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595aef4e05a7aa7fd73c54182dabe822287ab0a6ec90916a3346c1a23c2b24f0
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45f06f736c0f41cb7607b86e5979ce3b08b7e211689aa13e876aea3af1577ddd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2f457240119946c5c74a24a6a6392ae345c6b57b3f3e328f050df386eee12e
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": 0.0025591810620601407,
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": 19.361,
74
  "eval_steps_per_second": 9.681,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1101544053276672.0,
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": 0.003838771593090211,
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": 19.361,
74
  "eval_steps_per_second": 9.681,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002985711239070164,
79
+ "grad_norm": 0.7685030102729797,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9835,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0034122414160801876,
86
+ "grad_norm": 0.780146062374115,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7891,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003838771593090211,
93
+ "grad_norm": 0.7326439619064331,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7685,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003838771593090211,
100
+ "eval_loss": 0.3959052264690399,
101
+ "eval_runtime": 51.0716,
102
+ "eval_samples_per_second": 19.345,
103
+ "eval_steps_per_second": 9.673,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1652316079915008.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null