flytech commited on
Commit
0d34379
·
1 Parent(s): c1b8f25

Training in progress, step 600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b8eb123499e8392ba5ad821bb9da8fbcdf4df19d8e1c76b9870fe463ae04b36
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca8f20510733b4d16dd7297194631c192e39f8530581b5af76a793ac04e324f
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31fbc12714c21256e870a21356ebcef472e473aa422f6db9b9bd12331cc5519f
3
  size 126034975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44bd1c169b13957c006697fd590a7f0d5ec2307759e4b514b0b37b9fd2b34b72
3
  size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13ea66d8c66a5650930e65e8658c9e457131927f39417fd12c5000d0638f1d41
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:995d3a0dcc194d6d7316c3e62a9316c8f6a4ff574e8e486c51d021cc9b08807c
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 6.097560975609756,
5
  "eval_steps": 100,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -72,13 +72,26 @@
72
  "eval_samples_per_second": 8.523,
73
  "eval_steps_per_second": 0.154,
74
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
76
  ],
77
  "logging_steps": 100,
78
  "max_steps": 656,
79
  "num_train_epochs": 8,
80
  "save_steps": 100,
81
- "total_flos": 6.442331252195328e+17,
82
  "trial_name": null,
83
  "trial_params": null
84
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.317073170731708,
5
  "eval_steps": 100,
6
+ "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
72
  "eval_samples_per_second": 8.523,
73
  "eval_steps_per_second": 0.154,
74
  "step": 500
75
+ },
76
+ {
77
+ "epoch": 7.32,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.0281,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 7.32,
84
+ "eval_runtime": 32.3958,
85
+ "eval_samples_per_second": 8.52,
86
+ "eval_steps_per_second": 0.154,
87
+ "step": 600
88
  }
89
  ],
90
  "logging_steps": 100,
91
  "max_steps": 656,
92
  "num_train_epochs": 8,
93
  "save_steps": 100,
94
+ "total_flos": 7.731362690236416e+17,
95
  "trial_name": null,
96
  "trial_params": null
97
  }