tuanna08go commited on
Commit
0f16933
·
verified ·
1 Parent(s): 88779a2

Training in progress, step 43, 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:f8eb64e5fc64af89e7d7a6ad7d5fdca548320f515e30052a9b2aa49df90ffb14
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf0455ea5a5762682196071a060512fbeb751b04745d6bde03526d630b67d7e
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:912b2665b93b7b768963683576465e91964b826aef0f8fd420760998594de18f
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a31ed8c19e3d166f9e750ea890325e15db289c92d12807b38e79decc62674d6c
3
  size 162868
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75da50fc05ac3af40091fffa29af9b1286ecdf2a5575cc1b1bf98209587348f1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be4cd18c296a9c4f4aec802b0ccf4dc1e31a133c508fa148dc28c18263b82d5f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b55da3539bea7b2a5ee7e90ae234ebb83f0bcf3370372577761e8ba6d802b8f2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4596f05f2825020af546e9fe75445728cf0ec904fa7301c7875d2ed533ffa193
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": 0.7787610619469026,
5
  "eval_steps": 9,
6
- "global_step": 33,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,21 @@
60
  "learning_rate": 2.282162249993895e-05,
61
  "loss": 176.7675,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +89,12 @@
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": 10184910962688.0,
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": 1.0147492625368733,
5
  "eval_steps": 9,
6
+ "global_step": 43,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "learning_rate": 2.282162249993895e-05,
61
  "loss": 176.7675,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.8495575221238938,
66
+ "eval_loss": 11.008992195129395,
67
+ "eval_runtime": 0.9276,
68
+ "eval_samples_per_second": 308.313,
69
+ "eval_steps_per_second": 38.809,
70
+ "step": 36
71
+ },
72
+ {
73
+ "epoch": 0.943952802359882,
74
+ "grad_norm": 19.834644317626953,
75
+ "learning_rate": 1.3152288061110518e-06,
76
+ "loss": 176.2137,
77
+ "step": 40
78
  }
79
  ],
80
  "logging_steps": 10,
 
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
+ "should_training_stop": true
93
  },
94
  "attributes": {}
95
  }
96
  },
97
+ "total_flos": 13264014016512.0,
98
  "train_batch_size": 8,
99
  "trial_name": null,
100
  "trial_params": null