duyphu commited on
Commit
8cac699
·
verified ·
1 Parent(s): 3712b68

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 sha256:62ce243e116b25d46f8c0fa58df12baf1e6fe957ae0ffa58654697e169c0c6fc
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4f5780da7479df03b31780ffd660f4126d9a41af235bd2c373ef8ab037d45c
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3d2197aeace4bbf0d8f7601669c9610adb99b3d43cefc55affbece58ead5e13
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:919f7ec4c8c6e4d64e621460085a022d36082060758c1422f5c2f4080c424f74
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:501bbc95a07fee90fa37abc1c02060dd46fa0ea348b19f80d5547d4a0bb8d1d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daadbc8a0eb5eb3627f0a4012f1711d3d7a034e1da76dffaa7cff7352b14d0f
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": 0.013967230727907601,
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": 0.493,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4543869219766272.0,
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": 0.020950846091861403,
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": 0.493,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.016116035455278,
72
+ "grad_norm": 0.3808046877384186,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4076,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.016116035455278,
79
+ "eval_loss": 0.10152747482061386,
80
+ "eval_runtime": 80.2919,
81
+ "eval_samples_per_second": 9.764,
82
+ "eval_steps_per_second": 4.882,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.018802041364491002,
87
+ "grad_norm": 0.31879931688308716,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.3137,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6861701498535936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null