ClarenceDan commited on
Commit
4e24b7d
·
verified ·
1 Parent(s): 4c2316c

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 sha256:58f16b70d5c7ea66f5bcf93feb1af9bcb07f4092e71922f8a07ab16b615c422d
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f284e79943d9fafdc9aa3d48aecec2467a03db9d759280afc17eca31d9349f4
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1120b9579c643a9ffcec130356e2691b013a0442bab57947464d952a0cb557da
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec565ad1e6247f5d04d38828fa3f9b7c6f623c80a5e0223a7d325764141c1cb
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b463883609ea29a433544401e2cca59a163be1d6a17f6d6e25dc877b7bef91b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44dffdb8b477c32cdfd4aa16dff9c4b527b396c65d3d182308d4425298615b6
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": 0.001014584654407102,
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": 32.816,
74
  "eval_steps_per_second": 16.408,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 102393888374784.0,
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": 0.0015218769816106531,
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": 32.816,
74
  "eval_steps_per_second": 16.408,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0011836820968082857,
79
+ "grad_norm": 0.44897976517677307,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.7276,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0013527795392094695,
86
+ "grad_norm": 0.41854241490364075,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.6267,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0015218769816106531,
93
+ "grad_norm": 0.45529505610466003,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.7532,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0015218769816106531,
100
+ "eval_loss": 0.6932230591773987,
101
+ "eval_runtime": 73.2665,
102
+ "eval_samples_per_second": 33.985,
103
+ "eval_steps_per_second": 16.993,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 155816786657280.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null