chauhoang commited on
Commit
6846487
·
verified ·
1 Parent(s): 1b94a68

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:d5f17fa874a5de838861d15ae158a8b83d7079106f6c087926bf120de290261f
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607c8b1ad69802f81519ffbd22329ca1726bc5506bac7dc4d5c5d833396c5084
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de9626fff525ddfbf048282a33eca7a60e7b0acb104b386d1086aa42ca9267a1
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7762d3bcbb292709f10bb01eb9cbd7dcbbeecba1737c78c7217e13e26360c37a
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
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": 0.03363518758085381,
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": 10.3788,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 672407224320.0,
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": 0.050452781371280724,
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": 10.3788,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03880983182406209,
72
+ "grad_norm": 0.010108263231813908,
73
+ "learning_rate": 5e-05,
74
+ "loss": 10.3786,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03880983182406209,
79
+ "eval_loss": 10.37945556640625,
80
+ "eval_runtime": 2.3114,
81
+ "eval_samples_per_second": 141.038,
82
+ "eval_steps_per_second": 70.519,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.045278137128072445,
87
+ "grad_norm": 0.009184284135699272,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 10.3809,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1008610836480.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null