philip-hightech commited on
Commit
530da07
·
verified ·
1 Parent(s): ecbeb47

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 sha256:345db7e0abf2f9deedfd8a03f45154f0c0c6b626f968b4c9a5ddcdeab096e7d9
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7346119a6f22b1894501de348a33044b4ea469b6d1fb323a5b01588526c37ce
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d88998c53ebee99977eec272f51f60de6f6246b56e61b42bcebcc3f9b00922
3
  size 197158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09205f5ec7622183d25e1ec9a09879cefbed77b611974286dec7f3bc24c64973
3
  size 197158
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0142a686d2f42ce8f779f95a994c62a8be5e12e27afd368335d9d4d2472185ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c4203910a67ecfc4f0278cc9fadd261f3008669f9aace0335be357a28472bc
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": 0.06643952299829642,
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": 269.164,
61
  "eval_steps_per_second": 134.582,
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": 11750768640.0,
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": 0.08517887563884156,
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": 269.164,
61
  "eval_steps_per_second": 134.582,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.06814310051107325,
66
+ "grad_norm": 0.11548151820898056,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 11.9165,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.08517887563884156,
73
+ "grad_norm": 0.13397084176540375,
74
+ "learning_rate": 0.0,
75
+ "loss": 11.9171,
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": 15065088000.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null