daniel40 commited on
Commit
5ed2bf3
·
verified ·
1 Parent(s): fcbcbe5

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 sha256:28aab121721ec9edae3b34bdfa48b22e43d5a532a731250ee6afcbbd59883db7
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60708d228dd5571f0798bdcd03526d237ac1179d38ee1173cf0d209cf638da6
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50fbb8068bcb09895ba9f67924431cab5d6af7afde4dc90b41725c6a8927a23d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38130dd7668badb1c4bae8c760e26d0957a0923b93c609fda50d5f4f9b6a5066
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:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
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": 0.0013206405106476642,
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": 32.176,
74
  "eval_steps_per_second": 16.096,
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": 0.0019809607659714962,
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": 32.176,
74
  "eval_steps_per_second": 16.096,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0015407472624222747,
79
+ "grad_norm": 1.5483531951904297,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.552,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0017608540141968855,
86
+ "grad_norm": 1.6075634956359863,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.4392,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0019809607659714962,
93
+ "grad_norm": 1.6612417697906494,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.4921,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0019809607659714962,
100
+ "eval_loss": 0.451882004737854,
101
+ "eval_runtime": 59.5127,
102
+ "eval_samples_per_second": 32.144,
103
+ "eval_steps_per_second": 16.081,
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