lesso08 commited on
Commit
0f2e957
·
verified ·
1 Parent(s): 2a5464a

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 sha256:6a9e53de7a82a91e3c6b66245cc5f123d5e785f6824aaba46725be4fec3222fb
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba9f9677d465da8f7ccc0581dc0f1ef32bb1ad41a21739bff389d133646ea5f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d2a826f6d7003cb0f503b76e9ea086a296725988969044bb41fb8d30a171dd0
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5085875928dad94906111ef1d72d02a3e28966d7b27a8831852da8acd92cee42
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dae627a7d2298122bff578106eebf3a91e3c4a65f4b6f1686a626ab036cc9c37
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17602379fd7311d0f276d1ebf45e775c93bcab84ae4bf6e66fb3d0fb451e92a1
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": 0.00644468313641246,
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": 14.541,
74
  "eval_steps_per_second": 7.271,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 977249545224192.0,
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": 0.00966702470461869,
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": 14.541,
74
  "eval_steps_per_second": 7.271,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.007518796992481203,
79
+ "grad_norm": 5.69166374206543,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.0578,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.008592910848549946,
86
+ "grad_norm": 3.523707628250122,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.2101,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00966702470461869,
93
+ "grad_norm": 3.2407777309417725,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.2568,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00966702470461869,
100
+ "eval_loss": 1.5488775968551636,
101
+ "eval_runtime": 26.9709,
102
+ "eval_samples_per_second": 14.534,
103
+ "eval_steps_per_second": 7.267,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1465874317836288.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null