trenden commited on
Commit
c38165a
1 Parent(s): bccbbd9

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 sha256:0b6c161634ef9071ce31fafc2f817dec8c4a627280fff737b86ddffe13cd651f
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcfed13a8edcad7532cd8db706eca80911a14b65c8bf8f22831a53d7acdd756b
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e78323e4f60a35fabce53f4ef2fbf296fd58158a7cf5e7761217fb2c5dfe94c
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f034cda3e43922e3b1f5eea6ab2fcb05809e661f01c201415288b288df48ae92
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8533ac5c809e23e45fa3502773ae0eeaf07bc3c38c0faa86616fda6bd7fa0465
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84d16d72b7e6ff5d6769d55df31c36b252d605a20a4c4c276e5840c32f666b1
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": 0.1276595744680851,
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": 62.46,
74
  "eval_steps_per_second": 31.23,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 144327309262848.0,
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": 0.19148936170212766,
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": 62.46,
74
  "eval_steps_per_second": 31.23,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.14893617021276595,
79
+ "grad_norm": 3.397935628890991,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.021,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.1702127659574468,
86
+ "grad_norm": 2.54946231842041,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.4491,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.19148936170212766,
93
+ "grad_norm": 2.3854799270629883,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.4781,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.19148936170212766,
100
+ "eval_loss": 3.475511074066162,
101
+ "eval_runtime": 0.3117,
102
+ "eval_samples_per_second": 64.163,
103
+ "eval_steps_per_second": 32.082,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 216490963894272.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null