tuanna08go commited on
Commit
de28c04
·
verified ·
1 Parent(s): b09d6f4

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d154a4e4671a5a1afa8d92f9d04e70a9b7236d91fae3c6d82c1f67ec040069e
3
  size 327040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46665c3d7b603151a1dbae2e136f15eddd86011706a2538f5df0e981328c3bd3
3
  size 327040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9558d7cec1b36092f44630fb2070a037ec8ba68bccb43655a0056d48eb7151c2
3
  size 739258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8224c2b7ebce7cafd8ce5584af677f08495c0232254b1889e74ccb4c3769abea
3
  size 739258
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38c414079b785cf8d1fad8f33cd71845cb15909579b0bc15b941b713fcaa6e99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.04100946372239748,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 11.9268,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6132640776192.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.061514195583596214,
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,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 11.9268,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0473186119873817,
72
+ "grad_norm": 0.18544097244739532,
73
+ "learning_rate": 5e-05,
74
+ "loss": 11.9257,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0473186119873817,
79
+ "eval_loss": 11.924522399902344,
80
+ "eval_runtime": 26.5922,
81
+ "eval_samples_per_second": 10.041,
82
+ "eval_steps_per_second": 5.039,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.055205047318611984,
87
+ "grad_norm": 0.21347272396087646,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 11.9219,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9292828114944.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null