great0001 commited on
Commit
847b250
·
verified ·
1 Parent(s): ca5e0c2

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aa3919eaf1adc00159e9a31210553b43d4265854bbedf2a85ad41efb28a33c4
3
  size 1204200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca3becb465ad5391344e973449dbdf07d0aefe20fabcce5258273d79c826750
3
  size 1204200
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e573bcc5a2853b6e25fee2290f631a80ef0343fc13f0b309d9b4401fe5d4b8df
3
  size 2492922
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc3658b93d64917d3bd75f9e68e64b0966a6da36e3ba591d691689c1733bb5c
3
  size 2492922
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:385963a176ffc48bf03192b4ae6c481b93294392672176225e3eb124121ad082
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca802d2339a34005ba8507fc49e31d471dfb2e7af1671cb2f0ca11334b29142a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.027967013266403728,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 75.412,
61
  "eval_steps_per_second": 37.706,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 5058510520320.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.035855145213338116,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 75.412,
61
  "eval_steps_per_second": 37.706,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.02868411617067049,
66
+ "grad_norm": 0.726130485534668,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 11.8774,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.035855145213338116,
73
+ "grad_norm": 0.3824235200881958,
74
+ "learning_rate": 0.0,
75
+ "loss": 11.881,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 6494474797056.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null