philip-hightech commited on
Commit
a0167a8
·
verified ·
1 Parent(s): 289f0d2

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 sha256:9a90c211a75c1c32aa1e0c850254bab843b9b95a8dd979d269db603a0f3846a4
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cbabe8386f9201a4be92675e8588a7d4e2f7b02c93fc147ade3ba231160ed4
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec4a9e7da294ff01b71a79018d81db1b96386361b4632c1e43d17cfcc64c4b7
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a2420ff4b42f7c31321744f661a0a233f32b4cdf4df00633be62e3fea09c27
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": 0.0013099006658661718,
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": 15.631,
74
  "eval_steps_per_second": 7.819,
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": 0.001964850998799258,
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": 15.631,
74
  "eval_steps_per_second": 7.819,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0015282174435105338,
79
+ "grad_norm": 0.5309928059577942,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.4052,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0017465342211548957,
86
+ "grad_norm": 0.4780644178390503,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.3675,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.001964850998799258,
93
+ "grad_norm": 0.5216543078422546,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.389,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.001964850998799258,
100
+ "eval_loss": 0.8844879269599915,
101
+ "eval_runtime": 123.4319,
102
+ "eval_samples_per_second": 15.628,
103
+ "eval_steps_per_second": 7.818,
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