tuanna08go commited on
Commit
c0c3c17
·
verified ·
1 Parent(s): 9a0f2c3

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:e59be6317254a6818aa32cdb9deef19ab6e0881afa52185f420290e6e6818eb9
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e77c0bb2523be6758cf5133cfc8d4fb44f5e54c6283fbb0c57f499cdec1dc89a
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd51e17e4d601f66c2b6ab56480bb8d66819a8491bc9de4714f9147c556ca0b
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2161970f2a9abd64ece7aa83f7647e49dcda16232f354eea44ae946152cb5f2e
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14277333675efd53eaa048f8199fb760b13b54df07dfe24e92514b78a644cfe6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da0f7e6c4f7543e83506c0648750f953520ef6c61f99774a8942be4e7831d9ec
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.2653061224489796,
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,
@@ -60,6 +60,36 @@
60
  "eval_samples_per_second": 27.401,
61
  "eval_steps_per_second": 3.432,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +104,12 @@
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": 3.927251910603571e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3401360544217687,
5
  "eval_steps": 10,
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": 27.401,
61
  "eval_steps_per_second": 3.432,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.272108843537415,
66
+ "grad_norm": 2.5240602493286133,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 1.447,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.272108843537415,
73
+ "eval_loss": 1.3286805152893066,
74
+ "eval_runtime": 36.3788,
75
+ "eval_samples_per_second": 27.214,
76
+ "eval_steps_per_second": 3.409,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.3401360544217687,
81
+ "grad_norm": 2.9974277019500732,
82
+ "learning_rate": 0.0,
83
+ "loss": 1.2756,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.3401360544217687,
88
+ "eval_loss": 1.2556947469711304,
89
+ "eval_runtime": 36.4335,
90
+ "eval_samples_per_second": 27.173,
91
+ "eval_steps_per_second": 3.403,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 5.02662300696576e+16,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null