duyphu commited on
Commit
c877dc5
·
verified ·
1 Parent(s): c292f20

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:a8f72bb98da71de6ed9d33eff582c9975f7111040e782c585361aaec028ad472
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ff63f8a8436c44ba862a6e257e1061f307bd88d8cee6479318c8957cc6369a
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad42813e0c2e5c60f68462649ecf32f7fd6217169d2aecbe3a6c67355dfa2d3c
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6355d60235a2d3b8b12b81b03c7308bd9c186aac1fab2ee7e1501697c7b3cc
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5e58f6d1cdeebe1d7aa57259944c3c801316bbcd010a1ab4fe7f9d624ecf2bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca68f3c7f5320b8c12bfaa341eeb9926d2957be2b572aa4906c3b06ad3b29e
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": 0.0006049571585627614,
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": 2.2767,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4366730746920960.0,
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": 0.0009074357378441421,
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": 2.2767,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0006980274906493401,
72
+ "grad_norm": 3.392641544342041,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.5175,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0006980274906493401,
79
+ "eval_loss": 2.222399950027466,
80
+ "eval_runtime": 1102.8097,
81
+ "eval_samples_per_second": 16.41,
82
+ "eval_steps_per_second": 8.205,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0008143654057575635,
87
+ "grad_norm": 3.994202136993408,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.5334,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6632487266549760.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null