jssky commited on
Commit
eb8316b
1 Parent(s): 24537dc

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 sha256:94ca75717225e61dd3af5629b3352d0322ab3460ec5d3f7bd924fa8c15aabf96
3
  size 2264640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894ebf3126ef1afa2ad7f0a1c28c4e7c6927d9dfd2726e92bdb3c0e719b6de79
3
  size 2264640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:941a42bd85e2ebebbfbf80f54f02238860c6b98d4eb9c4698a8aa137a95b18eb
3
  size 1183674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dbed04c1738469a08f9db8002360bf85604704c60493a7729041f6a34721d85
3
  size 1183674
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d24a3b0e78134936662f0d4d52c5e330a1992c2511f7644b73ba6dacbcf6b6b9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5081bbbd97460339927b75a3b99f728398902a94fba87e277472912c152eb515
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
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": 0.02572347266881029,
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": 101.517,
74
  "eval_steps_per_second": 101.517,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 25963731615744.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03858520900321544,
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": 101.517,
74
  "eval_steps_per_second": 101.517,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.030010718113612004,
79
+ "grad_norm": 17.39157485961914,
80
+ "learning_rate": 4e-05,
81
+ "loss": 17.1975,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.03429796355841372,
86
+ "grad_norm": 18.5988826751709,
87
+ "learning_rate": 6e-05,
88
+ "loss": 16.2112,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.03858520900321544,
93
+ "grad_norm": 19.167139053344727,
94
+ "learning_rate": 8e-05,
95
+ "loss": 17.2223,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.03858520900321544,
100
+ "eval_loss": 16.201391220092773,
101
+ "eval_runtime": 0.4652,
102
+ "eval_samples_per_second": 107.473,
103
+ "eval_steps_per_second": 107.473,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 38945597423616.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null