duyphu commited on
Commit
3262678
·
verified ·
1 Parent(s): 529317e

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 sha256:25d8a4c93956776006d87daf08b68b79be60c2b3609686ecd3ec544f0a020ecb
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b154abd3441833c7443da1f77ff6860e90ef8fad231b76f33eb124bda6aed7c4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39dfb541cf2166547d6770165b306518b56e8c70ea2139cceace3210fc7a6a8c
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638caa18771c095c4cc960fe980cbb31b5c144bcc3f4c3af4043d69bf271686f
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:f478ca0849c70741c0206e13530f0c493597d4e8cd07e0e6c9e51ab8378b2300
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89be65360c462d9c4812bfee4e603b36894408ac274af51796d35fb242819f3e
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": 0.0005075275114071688,
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": 1.6065,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5271258107215872.0,
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": 0.0007612912671107532,
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": 1.6065,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005856086670082717,
72
+ "grad_norm": 1.466151237487793,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6043,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005856086670082717,
79
+ "eval_loss": 1.621889352798462,
80
+ "eval_runtime": 1583.6005,
81
+ "eval_samples_per_second": 13.621,
82
+ "eval_steps_per_second": 6.81,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0006832101115096503,
87
+ "grad_norm": 1.3835320472717285,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.5097,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7999365373231104.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null