ClarenceDan commited on
Commit
c494011
·
verified ·
1 Parent(s): 4da6f81

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 sha256:9a31ab2858e9d66a89cab9c5c25b7e5be905d871ae484e8d815297e1f3f629d4
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12333fd57f2f21090aca8b249467fa97c1937b804c5deaff197a3ca89bf3c167
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9306beb12e15235296e43ade21ec2baeb35eae9f2a6d37b0710ef585af9a2444
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206c08064e77b6fd4711b3629983506999a7c2b690874afb1bc85c9ac345d6e2
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ef8df3090ba6573a77d2f727ab3a7630e0e74ae94ec69d6fec04916402509d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2888a62db6bbbdd9fb6379059149f22a64e1c46675f5da47d0742f8805f53809
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": 0.0008895478131949593,
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": 53.076,
74
  "eval_steps_per_second": 26.538,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 95716026089472.0,
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": 0.0013343217197924388,
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": 53.076,
74
  "eval_steps_per_second": 26.538,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0010378057820607859,
79
+ "grad_norm": 0.6381222009658813,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.3513,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0011860637509266123,
86
+ "grad_norm": 0.6122051477432251,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.4294,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013343217197924388,
93
+ "grad_norm": 0.6916836500167847,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2368,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013343217197924388,
100
+ "eval_loss": 1.305905818939209,
101
+ "eval_runtime": 54.3713,
102
+ "eval_samples_per_second": 52.233,
103
+ "eval_steps_per_second": 26.117,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 140235107991552.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null