ClarenceDan commited on
Commit
4d3d8b0
·
verified ·
1 Parent(s): c91ae79

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 sha256:99d5d6c9ab9aacee2962332909cae3c39709385d7b9db00bd29d51db03b57d69
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d2324d24b3af01ec2ec4f77fd05f1dedb723c3125f40e8612114ad672d7fa6
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd4c7b5d191e542f9cca00a70d9522775d91879d37efa394eb962598402d919f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a0881a15f28cb881ba9905aac0e0957f5b04fa15ded7c127fa4fe95589df1f
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40f36e39537ec3fe538f54513e23a84b95ec42e39b76848a0228344c913c6840
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baabc1d53a3fa3b56c5b315a5ebae68edc35387897d274365ec617d5e7bc22a9
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": 0.007430340557275541,
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": 22.689,
74
  "eval_steps_per_second": 11.344,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109738548887552.0,
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": 0.011145510835913313,
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": 22.689,
74
  "eval_steps_per_second": 11.344,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0086687306501548,
79
+ "grad_norm": 2.634336471557617,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.009907120743034056,
86
+ "grad_norm": 2.586655855178833,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.3643,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.011145510835913313,
93
+ "grad_norm": 2.1898770332336426,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.3185,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.011145510835913313,
100
+ "eval_loss": 1.5426946878433228,
101
+ "eval_runtime": 15.028,
102
+ "eval_samples_per_second": 22.625,
103
+ "eval_steps_per_second": 11.312,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664607823331328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null