ClarenceDan commited on
Commit
38962d1
·
verified ·
1 Parent(s): 8dc9475

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:d6b58c81e2727b72bbbd149a49523b1c4c0ba3cab1a1c0c8a503c9b8e8ebbc4f
3
  size 28351000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7108c12ecb0bea707b20e316fe4c5e0f34340c9f6a117beaad1fcde594900c08
3
  size 28351000
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31a4c65a96781bee46f461cc239d806ae58b933209b6916ee0be7ca14b9bdaf4
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317a41fe06905c18f6addc82f99f210d00d45100708b0d4333be8f6f12cf5582
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b427ffc959c32848145c63eda0c046811dcfd2f74c4735bac423974e4d718de0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0860148a5490b599e99944483a9c384219ff285d2e241ac00d74f0d5a768e3
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": 0.00016735001255125095,
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": 49.889,
74
  "eval_steps_per_second": 24.946,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 351049630089216.0,
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": 0.0002510250188268764,
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": 49.889,
74
  "eval_steps_per_second": 24.946,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00019524168130979276,
79
+ "grad_norm": 2.1591832637786865,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.7041,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0002231333500683346,
86
+ "grad_norm": 2.9507343769073486,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.1911,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002510250188268764,
93
+ "grad_norm": 3.269846200942993,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.7977,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002510250188268764,
100
+ "eval_loss": 1.2447813749313354,
101
+ "eval_runtime": 257.3929,
102
+ "eval_samples_per_second": 58.654,
103
+ "eval_steps_per_second": 29.329,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 515370733535232.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null