duyphu commited on
Commit
41539e1
·
verified ·
1 Parent(s): bec5168

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:b880a184c4b04bc678e53bbf358924422452dc97f75d7ae32a75c79e9015a003
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d649518b65eb08e03e6ecfa67dc712037ce5ee916f9a9202e7eea5c9a048e8
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1afbb236dd0b36fd18bb377c5d63f3411c33a7c8cd753c0207fd10be18f3c0ad
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d629d4a9cedc0dad3239eb2436299517415cd59cf380a7d04d32a19a037974a4
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
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": 0.09515096065873742,
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": 0.7451,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4284339600752640.0,
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": 0.14272644098810613,
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": 0.7451,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.10978956999085086,
72
+ "grad_norm": 1.2351694107055664,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6899,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.10978956999085086,
79
+ "eval_loss": 0.6869314908981323,
80
+ "eval_runtime": 7.1682,
81
+ "eval_samples_per_second": 16.043,
82
+ "eval_steps_per_second": 8.091,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.1280878316559927,
87
+ "grad_norm": 1.4144127368927002,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6356,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6426509401128960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null