duyphu commited on
Commit
71bda68
·
verified ·
1 Parent(s): b4ac316

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 sha256:72235e3dd090cfa4df0b89efb2ac081bb9173513e361f96d1add317189559a95
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1e4611949e554c60fcd860e4fd9c7c068796296524e249f2ef992c43da02dc
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:458ffc0a86e2ba96ba3fc6f9e8a888e2ab3395ddd13833601882b0613507d44b
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb2f53486fc4727a368d007466100a8707a90c99406a6aaf28693a5cb64791c
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63916ab7d5be6d7bb777fc4e5bd29eea52b9737122f154edbb3373deb10a9583
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fdd776f586a88ff6833460d9955d2123f07a9cb127865e4dd00045102cfeb8
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": 0.2694300518134715,
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": 3.0248,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 89160891236352.0,
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": 0.40414507772020725,
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": 3.0248,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.31088082901554404,
72
+ "grad_norm": 0.9830533266067505,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.9533,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.31088082901554404,
79
+ "eval_loss": 2.9466686248779297,
80
+ "eval_runtime": 0.8016,
81
+ "eval_samples_per_second": 51.146,
82
+ "eval_steps_per_second": 26.197,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.3626943005181347,
87
+ "grad_norm": 1.1721653938293457,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.8659,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 133741336854528.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null