laquythang commited on
Commit
97f2855
·
verified ·
1 Parent(s): b78a6f8

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 sha256:6e2c397deb44df01378f829673b1d39811b2bab7da5b1f93a8c0fdf89ba56692
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7579d90b93a7bf51b56f2700504ef4d975735d5f17536db9e0e72be2201a9e6e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f9840b2a015100ec78f495eb4fd160fecaeb15d1e922fa918017e033adfdab8
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da481e59697d50c515aca86263aec294fb1e29da0f77cd0915196c5cff016185
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67a48c31b23b285064d8c759df108ca3cb56a00af4942d42a98416ef2b782d16
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8148319d5b32ce40422cb32202a6b3d6e4bf1804e2904023f6e6a85d1866e8
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": 0.0034757422157856628,
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": 7.63,
74
  "eval_steps_per_second": 3.82,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109738548887552.0,
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": 0.0052136133236784935,
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": 7.63,
74
  "eval_steps_per_second": 3.82,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004055032585083273,
79
+ "grad_norm": 1.317775011062622,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.9932,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004634322954380883,
86
+ "grad_norm": 1.117720365524292,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.3084,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0052136133236784935,
93
+ "grad_norm": 1.2141731977462769,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.8136,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0052136133236784935,
100
+ "eval_loss": 2.5741186141967773,
101
+ "eval_runtime": 95.2372,
102
+ "eval_samples_per_second": 7.634,
103
+ "eval_steps_per_second": 3.822,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664607823331328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null