philip-hightech commited on
Commit
cd0cdef
·
verified ·
1 Parent(s): c37d26f

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:299a174b79961ed36b1867e001be8bbd23453435d08eb43eb67e78d44f89a3a4
3
  size 1579352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b0dc56f82e3b7732652d3960d4d648be44834b7aad33dabaac9be474b91a0e
3
  size 1579352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:334c9ed3243fe9241d44ba5e6b07b75bc7cc1be00ab01c29869bbfa9f2a95a62
3
  size 857338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a5acc77b711730c0e3d1400d67a975e0901680ed05dc52ff1ab8407f17d93b
3
  size 857338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:990a21d9696b6c96e808ec0a76f11b513ce3c62eca65d1528221b851c32b677f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f53083d6bf416fa674a4d7654c4dc44772d047f9fd45a1c2d70bd5cf789eb73
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.003420102603078092,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 234.86,
103
  "eval_steps_per_second": 117.43,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 9967478243328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0038001140034201026,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 234.86,
103
  "eval_steps_per_second": 117.43,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0038001140034201026,
108
+ "grad_norm": 714.2702026367188,
109
+ "learning_rate": 0.0002,
110
+ "loss": 88.4231,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 11074975825920.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null