phungkhaccuong commited on
Commit
8b5e469
·
verified ·
1 Parent(s): 5f1b9ba

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 sha256:539f5b24a0383e891eee68846fd16a340037a81942670d211cce332a5f50d58e
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f8ce199b6cd7f2a90cebfc1bc4d7d13b3533d231201a7ba670ee99d6574223
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a30eeb27c16b4e8abbff65be0fb0f72178b1636bd3b8be437bdfc0e907c3fd99
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3f9b8a9607a5e94e2d321e2de3a6ff0f73a34145cdca58271f7793f1629d0c
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3792359ce259c97b79ba2cc86cec68868e3a782d6f4b8b840af98211ae50b86
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cacaf8ca7dccda8c7558dd4f048e47ecbfd6553f222b04583f4b378449c85d41
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": 0.03612365404654394,
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": 1.2685,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4530853719834624.0,
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": 0.05418548106981591,
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": 1.2685,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.04168113928447378,
72
+ "grad_norm": 1.7187610864639282,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0837,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.04168113928447378,
79
+ "eval_loss": 1.0210185050964355,
80
+ "eval_runtime": 34.0398,
81
+ "eval_samples_per_second": 8.901,
82
+ "eval_steps_per_second": 4.465,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.048627995831886074,
87
+ "grad_norm": 2.0270674228668213,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6796280579751936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null