dimasik87 commited on
Commit
f871984
1 Parent(s): 5b25626

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 sha256:3a865ca33a5e47f374a75c9fc60ef8d9da1d025e4f273e40678515edd30452bf
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0f1d90b8438b34f67d7bb6fcfb3f7221595e5eb83685defb206a8a8e0218b5
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aed2516b11a99d1cc878870c216bedfced197dbb8bf0472d4bf847f32d092ef
3
  size 320082106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618cf330b9bfc9f150e25ae1066c55bfb796bd8e05e89a884b0c513b013691cc
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": 0.00016038706745612744,
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": 5.446,
74
  "eval_steps_per_second": 2.723,
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": 0.0002405806011841912,
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": 5.446,
74
  "eval_steps_per_second": 2.723,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00018711824536548203,
79
+ "grad_norm": 0.5095219016075134,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.4361,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0002138494232748366,
86
+ "grad_norm": 0.5460357666015625,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.6091,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0002405806011841912,
93
+ "grad_norm": 0.5249965190887451,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.3963,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0002405806011841912,
100
+ "eval_loss": 0.6169511675834656,
101
+ "eval_runtime": 1446.3469,
102
+ "eval_samples_per_second": 5.445,
103
+ "eval_steps_per_second": 2.723,
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