duyphu commited on
Commit
40083d7
·
verified ·
1 Parent(s): 15676dc

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 sha256:6341075ce9f542c41e6fdf0790e59918346224d90350bc2fcc18fbca5b61854d
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c6034b33d2c004348fdfa291076bb6da556faebb2036f22edd582f50bebee4
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b516a2c87cc42f087e77203aad4b4a4c563d5c49c8345f909ab0b751a5c2f415
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1afca020a835e7efe6b318a7cb88ba59995e32de72f36f19ee06700f4a37fe
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5e843a3007417b54718c9360bff0f4c72b8e2a4e589e479eb4a6b3b7a981de
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07826b0a1715771cf8401779e148b2e054e92f43284fa32f35d7a2caedc00d70
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": 0.004396533502430776,
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": 0.4523,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2956822944153600.0,
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": 0.006594800253646164,
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": 0.4523,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0050729232720355105,
72
+ "grad_norm": 0.3301470875740051,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4762,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0050729232720355105,
79
+ "eval_loss": 0.5101726651191711,
80
+ "eval_runtime": 143.6995,
81
+ "eval_samples_per_second": 17.328,
82
+ "eval_steps_per_second": 8.664,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005918410484041429,
87
+ "grad_norm": 0.3366134762763977,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.469,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4417841340088320.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null