tuanna08go commited on
Commit
b14c170
·
verified ·
1 Parent(s): 5cb48c5

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 sha256:16f48d99ad318bd1b3ef41de65ec66fbc8c1e22f6a6bb57d690f32101cd5e8bc
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2848993e981317b63c887f776828074dbf7d079dc69c30bf3166cb1782cc21db
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:073b9d91a384d0f2b7d8611bae0f5e84fe725e6e2d8fa5dfef6705ba1144a2c1
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df7fa8c286b784ee23d1bacafcf53c05533e6f84a2b031f4213645fc5ab621c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2b24b89fc33cbe8d8d45fd00fafb48d0af14cae75f04e9d92782a501466b631
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02fd813bb0de5aa0b8f4f8d84a341c28f5266f7eb3b168cd326af89381ab1e9
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": 0.0010958326747800432,
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": 2.7684,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8193740661325824.0,
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": 0.0016437490121700648,
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": 2.7684,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001264422317053896,
72
+ "grad_norm": 3.9624576568603516,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.8031,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001264422317053896,
79
+ "eval_loss": 0.6921516060829163,
80
+ "eval_runtime": 1561.0748,
81
+ "eval_samples_per_second": 6.399,
82
+ "eval_steps_per_second": 3.2,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001475159369896212,
87
+ "grad_norm": 4.666100978851318,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.7865,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2137252209557504e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null