quannh197 commited on
Commit
b5f50b1
·
verified ·
1 Parent(s): fdd5ea0

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 sha256:05b98ea2c21cd68f231ef1f7fee32f96624b18ea3485ba6e89f10791042fdd3b
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c0d59ad22334c537bd78df673936460200f2c082599f55957e4f38991ad96f
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c77d657c3af60961915dd8b13bd7edc9bcd7d44939c3463c0e89845ce2d2b34b
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:effa6a719fed108f15bf28be03fe9c9d495c522f76a4ecf68fce254483d2ea6f
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
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": 0.002551834130781499,
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": 74.165,
74
  "eval_steps_per_second": 37.082,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 153475186950144.0,
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": 0.003827751196172249,
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": 74.165,
74
  "eval_steps_per_second": 37.082,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0029771398192450825,
79
+ "grad_norm": 0.8422204852104187,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8683,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0034024455077086655,
86
+ "grad_norm": 0.7477498650550842,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.5238,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003827751196172249,
93
+ "grad_norm": 0.7416492104530334,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.6067,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003827751196172249,
100
+ "eval_loss": 1.580859661102295,
101
+ "eval_runtime": 13.3094,
102
+ "eval_samples_per_second": 74.384,
103
+ "eval_steps_per_second": 37.192,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 230212780425216.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null