ClarenceDan commited on
Commit
d86bb33
·
verified ·
1 Parent(s): 569b61f

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 sha256:21a7b0d1ceb4b3a0323b7cc2d8c52412de86c3c84e4e94f5e54eeb38777049c3
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd8d04d2d3a0e95a9fe68fa504dd014c1e9ad66654165e2825f73a52bd93146
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba541ed241a063d7fff06d0a9a640b04502caf485e8dc429fcb0c0b6f62ac7bc
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8eadbf6e97a547ab6a1047c4552375c62b94018d297bf65ebc4a776ab0292b6
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b179617ae99d33e6523cf1758e9c30872c98fc73fd423c8ca3b6821828405c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da882cb07bc6ca5e8b5ed796193c84d9a124e44c14110bfba4cffb05cc470ae6
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": 0.0015085800490288515,
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": 7.141,
74
  "eval_steps_per_second": 3.573,
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": 0.0022628700735432775,
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": 7.141,
74
  "eval_steps_per_second": 3.573,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001760010057200327,
79
+ "grad_norm": 0.32019948959350586,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.0199,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002011440065371802,
86
+ "grad_norm": 0.3743453919887543,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.2238,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0022628700735432775,
93
+ "grad_norm": 0.3187636435031891,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.1751,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0022628700735432775,
100
+ "eval_loss": 0.7286435961723328,
101
+ "eval_runtime": 96.1963,
102
+ "eval_samples_per_second": 17.412,
103
+ "eval_steps_per_second": 8.711,
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