VERSIL91 commited on
Commit
f781d4c
·
verified ·
1 Parent(s): 0c549b9

Training in progress, step 5, 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:ed1a872d194ee024f9137488a93d9841fecaab78c39ec1d3b61255ff567c07b2
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d643b60f1635bb44e17c3ce6e59f1f47adb4f3f8e194ca17623567d30ee0e97
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1267ecdcc97e176b99333a1852a7d6f095259d5280dbd66184b0da67fdf0a8d2
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63afcccacafaa161152f04353cc3a007c156024758ac63d66f83847da9a6e445
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec3e8d1151e495ffa96386ee76aba3a8b7f1d47f34b3ad5155db54f403701f08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33908394b59fe7a7ebaedb8be68ef4df972a1fe5650cf558cfa0d7fa8625c2e6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
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": 0.3004694835680751,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 27.132,
60
  "eval_steps_per_second": 14.156,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 5435787785011200.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3755868544600939,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 27.132,
60
  "eval_steps_per_second": 14.156,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.3755868544600939,
65
+ "grad_norm": 23.5028076171875,
66
+ "learning_rate": 5e-05,
67
+ "loss": 1188.2882,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 6794734731264000.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null