duyphu commited on
Commit
46c139e
·
verified ·
1 Parent(s): 9c4ec8e

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:ad8a188b243f35ca51ed253395e81f4ef61bb32e4bbd9a15cf3ff852d0a287a5
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ecbce72d3f6a26bdd43a7604972d94d4ec8f12a93e5cc059fc56628fa594974
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:152b0ce1d0d6eb2ece2f2969ca449eb990394cd83b8acecd0663a62ab8c9de4b
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0696615033b7aba4e959bbf7081f1b4f00c92b16e9577ba43a156a4b7d2c2076
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19b63fdfce2e5954f245268db134b14093d0754375512bc7aefe8fce3fdc2100
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0c2adc975262f2df4c486df9e442410842d91213e05f1917c8f382c736c6cd
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": 0.006291591046581972,
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": 5.4739,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1007681745715200.0,
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": 0.009437386569872959,
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": 5.4739,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.007259528130671506,
72
+ "grad_norm": 3.2383882999420166,
73
+ "learning_rate": 5e-05,
74
+ "loss": 6.1798,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.007259528130671506,
79
+ "eval_loss": 1.5152812004089355,
80
+ "eval_runtime": 65.6178,
81
+ "eval_samples_per_second": 26.517,
82
+ "eval_steps_per_second": 13.259,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.008469449485783424,
87
+ "grad_norm": 3.7061190605163574,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.9487,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1492861845504000.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null