kostiantynk1205 commited on
Commit
6ba99b1
·
verified ·
1 Parent(s): 7893bed

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 sha256:5173e389550d19c97205e17a23d26e7888e4bad5e689dd69ce407234f27f736c
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ddc160207ee1af6ca45186728d88636abfa8efb51d4a42ac4708b05c22bd608
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dbf36b359843c55900366e858f78350c6bbc4047522062ea0a98c6ac759a813
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a20ffcb8145697491800552415bfdd00122d234e2338bd0c402a760fe92e72a
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bffe7c2454336adf1073b700dbbf9ab38b312b4e28fdb7704aa022403a69ca2d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb04223ba875e51fcbb6b90adb429f8425ccc26eacd70e231de69e7656d74fd
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": 0.001255821254774737,
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": 26.854,
74
  "eval_steps_per_second": 13.427,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 550107063779328.0,
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": 0.0018837318821621056,
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": 26.854,
74
  "eval_steps_per_second": 13.427,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0014651247972371933,
79
+ "grad_norm": 1.389266014099121,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.3148,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0016744283396996494,
86
+ "grad_norm": 1.2340798377990723,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.2516,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0018837318821621056,
93
+ "grad_norm": 1.129597544670105,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.4434,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0018837318821621056,
100
+ "eval_loss": 2.254772424697876,
101
+ "eval_runtime": 74.9283,
102
+ "eval_samples_per_second": 26.852,
103
+ "eval_steps_per_second": 13.426,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 787653295865856.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null