duyphu commited on
Commit
1303d84
·
verified ·
1 Parent(s): 5919ac2

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45005d4eabc4ac1e42ae5466de8d716f924829f032ae67026d77cb7503e6b1df
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0bdb2897cc792030df32c597e670c569b90c482f9abfdfd0fea1558320f5c6
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6aa3c1e635da1e59f0528734f98fb753451cccd2cdc2aafe61a3c7dab787548
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aebc69b886d4b2259c16f07c1347474912cd04429ccbce906b1160f3b69d0b48
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:958c0967f3b07c04b45b3e51df344f8d1721871460b2425689cc05ce4f3bb33f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4153372e5441b0ea2e6a8c0a0ff12401521178273f30862f0b9f4725190679f0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.001323710972800285,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.3904,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 231499225890816.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0019855664592004275,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.3904,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0015273588147695597,
72
+ "grad_norm": 2.2464773654937744,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.2897,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0015273588147695597,
79
+ "eval_loss": 2.3795933723449707,
80
+ "eval_runtime": 274.5051,
81
+ "eval_samples_per_second": 30.131,
82
+ "eval_steps_per_second": 15.067,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001781918617231153,
87
+ "grad_norm": 2.3766283988952637,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.1278,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 347248838836224.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null