dimasik2987 commited on
Commit
00860b7
1 Parent(s): c3b2006

Training in progress, step 9, 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:ccc589b2ed469d8a16232a491c057d453a94adf4cd274e82f0b342e01d824ff2
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa518ce0175b110a07fda9ead090047f69fb61f680a68292c3b14162175d497e
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a871ec41e604afb96042dea37a84812778c4c7a8a56a252ab39de0dfed853d4f
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:209afbef6c9df20a2ac532c038dd75d1b6b46acbeefc06ec36d2d2789b196e9b
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fd06e640d4dc34cb78b41e592a516f89687f6f43b09f38b29ad5a3384483f5b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a8e0a151dd98e594ef8e043b5fe855d94534ed6384f4867496734a3beedb85
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.00030533185756268844,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 6.85,
74
  "eval_steps_per_second": 3.425,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2293309699522560.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00045799778634403267,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 6.85,
74
  "eval_steps_per_second": 3.425,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00035622050048980317,
79
+ "grad_norm": 6.340505123138428,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.6984,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00040710914341691794,
86
+ "grad_norm": 5.083515644073486,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.2718,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00045799778634403267,
93
+ "grad_norm": 3.3060462474823,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.8094,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00045799778634403267,
100
+ "eval_loss": 2.9464833736419678,
101
+ "eval_runtime": 1207.6921,
102
+ "eval_samples_per_second": 6.852,
103
+ "eval_steps_per_second": 3.426,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3439964549283840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null