nathanialhunt commited on
Commit
5856621
·
verified ·
1 Parent(s): 3c375ad

Training in progress, step 6, 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:a19358b5df6c73943b2d1065f2ba043dc81c55d6a95f11784d6fd54b4862f332
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:093c15f2fded96bff0e61da05e2c51d06d69f0e739da21a1fd32ba1c4321340c
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3069a4207d84ccfad03680fffe1fe5e4fb7b3ad1cff24f6c3572b765e37eafaa
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3d5df975d3fbc07815abcc1e685622664fd8b7499af7e6ab1d766e5435b843
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.014018691588785047,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 31.631,
45
  "eval_steps_per_second": 15.989,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 554869274443776.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.028037383177570093,
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,
 
44
  "eval_samples_per_second": 31.631,
45
  "eval_steps_per_second": 15.989,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.018691588785046728,
50
+ "grad_norm": 1.6331862211227417,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.2682,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.02336448598130841,
57
+ "grad_norm": 1.4806976318359375,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.9887,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.028037383177570093,
64
+ "grad_norm": 1.6370915174484253,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.0355,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.028037383177570093,
71
+ "eval_loss": 1.9479806423187256,
72
+ "eval_runtime": 2.8938,
73
+ "eval_samples_per_second": 31.446,
74
+ "eval_steps_per_second": 15.896,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1109738548887552.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null