duyphu commited on
Commit
0be4ca3
·
verified ·
1 Parent(s): e945b14

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 sha256:276f3ba9ed2bf8356df73ca02bf2f16d5579c2d8940681f88bd784a8745e6095
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6de5c10c5589fb271b811dcff6ef01a379fa2ae6830c8b3a8a59430150b346d
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f9da777910d331cd67f7b8b8afbea2d9a277be783e32c3d6f42b8df78671fc5
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19b9a41cc8c81c883bba83ebb0419f2fcfec0fc60c55780939bad7536f75e60
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46b250027aa7f478a085b3fee4a82c9a03a61ed325ad8cf718942d3c12fc0926
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d592fbfabcdcf0f0d5483e62271f3e31eb1c315b6c63d18110736fd9d9e900f
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": 0.034255599472990776,
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": 1.2137,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8544453975343104.0,
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": 0.05138339920948617,
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": 1.2137,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.039525691699604744,
72
+ "grad_norm": 0.6072627902030945,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.1616,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.039525691699604744,
79
+ "eval_loss": 1.1616449356079102,
80
+ "eval_runtime": 34.7532,
81
+ "eval_samples_per_second": 9.208,
82
+ "eval_steps_per_second": 4.604,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0461133069828722,
87
+ "grad_norm": 0.6614992618560791,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0897,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2816680963014656e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null