havinash-ai commited on
Commit
83657f8
·
verified ·
1 Parent(s): e787574

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 sha256:7588715a8cbe17d1a2cf9e4ec8a2ce2664217c18ef10e01e8b03c313e710d685
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878c1483e1b4c0498a747cf6149c521cf0910f06f63206819664f119172bcfd0
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c52b440974e3bae5272bc5e7f7d4cfc1819579c7647bf44a7684f48664e38a8f
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa0c01f7ae85bcd837a55e5c93318d12cbff1a466f78236a80b994963645d54
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7e7bd56506ee5c450c2c30722a3224706f3d1e8fe3e9d338dacefa3ac043697
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e653c589a93d454c1d7738619accbc8d17154d42f167ee133dbebedba21de71a
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": 0.01898272085665612,
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": 56.91,
61
  "eval_steps_per_second": 28.488,
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": 1912205494714368.0,
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": 0.02433682161109759,
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": 56.91,
61
  "eval_steps_per_second": 28.488,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.019469457288878073,
66
+ "grad_norm": 0.4495070278644562,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.3451,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.02433682161109759,
73
+ "grad_norm": 0.503346860408783,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.2631,
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": 2467969653276672.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null