trenden commited on
Commit
5f64ab6
·
verified ·
1 Parent(s): 2e431fc

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:b68a3a42736c2a23c6262a1ea1656864efb894e5ea216d8f4838a8b8554793d6
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e624f52826e6f6bee1049708969f25068af4e8c2b5fb49dc975ed1b30f286be7
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83f6d4eb83ad5a6829c2d8a36a708bf2161cb96ce3faf87d9ffa4b684a091ff6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55076d87977afa17a54a96bec3e4101ab8dc57594f6eb8f23d44ecf2aecb9da
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d68d2a8ec68d97e9f6781386cdc5d11673589bf128caf93d024b660045d53f99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c794a47edc9435384cbc7bbda79d6455642ccecbb17e631e8dfd483567816013
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": 0.0021629416005767843,
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": 15.839,
74
  "eval_steps_per_second": 7.926,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1954499090448384.0,
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": 0.0032444124008651765,
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": 15.839,
74
  "eval_steps_per_second": 7.926,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0025234318673395817,
79
+ "grad_norm": 0.3815302848815918,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.9936,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002883922134102379,
86
+ "grad_norm": 0.4225100874900818,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.8196,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0032444124008651765,
93
+ "grad_norm": 0.41114550828933716,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.8682,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0032444124008651765,
100
+ "eval_loss": 0.8888127207756042,
101
+ "eval_runtime": 73.8329,
102
+ "eval_samples_per_second": 15.833,
103
+ "eval_steps_per_second": 7.923,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2931748635672576.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null