philip-hightech commited on
Commit
97b5a04
·
verified ·
1 Parent(s): bce8fc7

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:dd07dd78b4b3df1671a88ed8bc86467cd58f7f0ddf93f39ca52434c5faf84b07
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a30bcbf703174536a3e9d02ab580d7a8d76b11f4c8f3416ecdc24586f7591b
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7255aa0c5f6a8eb55f8011ec9819309282e44156609911ff0c295372a7a4a206
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6955eebf1a7454c08231027f677ba7b139d35da73d985515e570f1b20d4f61ed
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a13307056da4bbb211ad48ade25632cd037a6f559d3df7d1e4eebdbef92276c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a695df56b08ab5db2e2c7c62b578c49fc2667a8ac1c0e4e80bbd214eabb94e4b
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": 0.0010727215840522057,
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": 22.754,
74
  "eval_steps_per_second": 11.377,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1226868850163712.0,
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": 0.0016090823760783086,
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": 22.754,
74
  "eval_steps_per_second": 11.377,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0012515085147275734,
79
+ "grad_norm": 4.511407375335693,
80
+ "learning_rate": 0.00014,
81
+ "loss": 9.2954,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0014302954454029411,
86
+ "grad_norm": 4.854757308959961,
87
+ "learning_rate": 0.00016,
88
+ "loss": 9.1112,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0016090823760783086,
93
+ "grad_norm": 4.769744873046875,
94
+ "learning_rate": 0.00018,
95
+ "loss": 9.6523,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0016090823760783086,
100
+ "eval_loss": 2.458629846572876,
101
+ "eval_runtime": 103.4755,
102
+ "eval_samples_per_second": 22.769,
103
+ "eval_steps_per_second": 11.384,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2015570253840384.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null