dimasik87 commited on
Commit
79bbead
1 Parent(s): b504a46

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:cc5a7f03be06dc349ac4d435d35083a6b338d1f289a270f3e8513b26b86673ed
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb955fd4f4e398f76b6e44e0184d882bfc9b661d21829b0fb5b4b873ce25ab42
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71147b1455f8cf84a401825958bf6be1bde83a5648434fbb00a148dc43e9df6a
3
  size 320082106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e9336eb7264415126838ec5a6ae6eb89f2974d9a2b436ada82528ede7ea74f
3
  size 320082106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:763215bea5d1a4c574744e6c699e3f1500c51935002767db23d636da54b8f9a6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d403b274d925cebcf8d248245f3cc8fc3452b5d842d4d632f41f2cd4fc6136
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": 0.00022974861672187016,
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": 5.452,
74
  "eval_steps_per_second": 2.726,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3920749211418624.0,
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": 0.0003446229250828052,
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": 5.452,
74
  "eval_steps_per_second": 2.726,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00026804005284218184,
79
+ "grad_norm": 1.0133801698684692,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.3383,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00030633148896249356,
86
+ "grad_norm": 1.2487194538116455,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.2447,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003446229250828052,
93
+ "grad_norm": 0.8460904359817505,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.3048,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003446229250828052,
100
+ "eval_loss": 1.9420808553695679,
101
+ "eval_runtime": 1008.6015,
102
+ "eval_samples_per_second": 5.451,
103
+ "eval_steps_per_second": 2.726,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5881123817127936.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null