trenden commited on
Commit
c1cbcfd
·
verified ·
1 Parent(s): 8fd22e8

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:dbd24fea7ffa9dcc8d1bcedff0894b60ab69849c990e142c0fe4ed3166783e04
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc707b5cbd8d250673b0dd8105294bbcd47e886dc8a20bec20f93a686d3aebf8
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4a21701923adf9ab7fbcda69ed16f0d6ad4b0a00116538c9803eb9a2d8efa6b
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2813f172bec345395f230978c8b9b9bc47589e033f88edb8bc5ac7979d815f7d
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a796dd7283cb007ac40b6a2c4efcd6c0f8ca9d4b28a916c37ef0908a54d75a34
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99a5c11c0b82fc5bdf98c308da31be04d7e528dc72c280e687a63346b44e2fc
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": 6.431230053138038e-05,
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": 54.448,
74
  "eval_steps_per_second": 27.225,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 293686676029440.0,
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": 9.646845079707057e-05,
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": 54.448,
74
  "eval_steps_per_second": 27.225,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 7.503101728661045e-05,
79
+ "grad_norm": 21.81522560119629,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.1899,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 8.574973404184052e-05,
86
+ "grad_norm": 21.471542358398438,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.5243,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 9.646845079707057e-05,
93
+ "grad_norm": 21.635026931762695,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.5233,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 9.646845079707057e-05,
100
+ "eval_loss": 2.257808208465576,
101
+ "eval_runtime": 718.0733,
102
+ "eval_samples_per_second": 54.706,
103
+ "eval_steps_per_second": 27.354,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 440530014044160.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null