ClarenceDan commited on
Commit
f8122b4
·
verified ·
1 Parent(s): 08cb1f3

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:ea582f83a7b503f0af3c2317ca4731403da75bd9d4a81daadbc87f95a12d9e59
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64a8f10aeddd8db4e420d1aa6c4f88d4d1a2903d7fbd337a132af8aac3084cd
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e340326d2975e84ca0380806fc09a39b4a8223cd5b32897f6ba5557f26a729b
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbf71e6d36097b002ff0303edbd91d5fdf3cef07e6c903c0b5393f0068faf94
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6db5623a7dfbae47cc2c2f2d1105e6fdf1531d36ed29f450b50b1071453ceafb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dba9286d84416e7d5a19cf385fa24463f4be8dc1077de4409bcaaeb85f0000c
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": 0.0031809145129224653,
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": 11.996,
74
  "eval_steps_per_second": 6.006,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3462976744980480.0,
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": 0.004771371769383698,
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": 11.996,
74
  "eval_steps_per_second": 6.006,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0037110669317428763,
79
+ "grad_norm": 0.9897186160087585,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.5271,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004241219350563287,
86
+ "grad_norm": 1.0747867822647095,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.5138,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004771371769383698,
93
+ "grad_norm": 0.6603133678436279,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2162,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004771371769383698,
100
+ "eval_loss": 1.1624972820281982,
101
+ "eval_runtime": 66.2338,
102
+ "eval_samples_per_second": 12.003,
103
+ "eval_steps_per_second": 6.009,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5029561462947840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null