tuanna08go commited on
Commit
335e581
·
verified ·
1 Parent(s): 920bf5c

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 sha256:4eb04fb2c802a2ba73f457ae433401165e29845f8ef4790c4c2051abd5ff9c69
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6160a9688e5518a6a9c93f5ed67c94ecddf4fc974117e29e79f6a05fa9c5f1c
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:223a9567f839887bcfbe034060807cf8ab5c671237ad674547cc543a4f6f71a3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02b4e4538ebcbb52c0f8a295f4ba67d04229a33ac992e0d7592c3b3a3302057
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bacace43e547c94b41abff4056126eb4e9b430747001acf89e0e67ee0e4b31ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41545c83c667446944388978812bb06593d44bfffd5dfc346f997e48601eff99
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": 0.05450733752620545,
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": 1.2521,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9247821240729600.0,
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": 0.08176100628930817,
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": 1.2521,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.06289308176100629,
72
+ "grad_norm": 0.4165772795677185,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.4209,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.06289308176100629,
79
+ "eval_loss": 1.3841878175735474,
80
+ "eval_runtime": 35.7038,
81
+ "eval_samples_per_second": 5.63,
82
+ "eval_steps_per_second": 2.829,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.07337526205450734,
87
+ "grad_norm": 0.4540785253047943,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.4054,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.38717318610944e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null