kostiantynk1205 commited on
Commit
5a38f24
·
verified ·
1 Parent(s): 5d0806d

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 sha256:10b69f16d03ad48960c5ce34cd9af7fe911b0289a04084b97d558322d59b1a40
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6db9ceed1462b84297e75e60ed484367ce787ab0f2d8d2850ce44aed6f3c874
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55dca9f568541576d1ed2d2201a492726dfd7970d07e992d6aa8d2258bfe7868
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de768c05cf0ccc2f81b6e089641ff45ad949f7772bc81facf03136b129c92c52
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f31b023efb06514ca94fe879833ac32e1c4067a5c53f09b3b9c2d73968e6d54e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17433ac3ae8a2c287fe064636b401a77ecda1e5f28c86f7c780169d14715b1a
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": 0.00018717828731867103,
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": 12.159,
74
  "eval_steps_per_second": 6.08,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3720313558794240.0,
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": 0.00028076743097800656,
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": 12.159,
74
  "eval_steps_per_second": 6.08,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00021837466853844953,
79
+ "grad_norm": 0.28629568219184875,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.3721,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00024957104975822806,
86
+ "grad_norm": 0.3808829188346863,
87
+ "learning_rate": 0.00016,
88
+ "loss": 8.4298,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00028076743097800656,
93
+ "grad_norm": 0.3027486503124237,
94
+ "learning_rate": 0.00018,
95
+ "loss": 7.6258,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00028076743097800656,
100
+ "eval_loss": 2.063856601715088,
101
+ "eval_runtime": 1109.5521,
102
+ "eval_samples_per_second": 12.164,
103
+ "eval_steps_per_second": 6.083,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5540892534374400.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null