duyphu commited on
Commit
8ca9c36
·
verified ·
1 Parent(s): 8ebbfbe

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 sha256:81f0cf86ce50f6786f1c55af0478d03ed3319bbebf2af398ff054c8961848143
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195bf9d81f051b86b75272ecf1c1959686558995094cdb78b55eb7508f770326
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58b388eb7d6d2a0ef75d85c6cd3209e51a70890b32551245908d88361c2a77f
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2ab33f906e69acdb920c591de3d56714dc590e5c690fed6de7aea9a2ca0120
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dfde186a246679aff5ac812ee1b48959224a51864d34e011b4ef4c38ee651cc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d267add0f57facc2bcd1f0495b322eae339f52c0bf72ab67697d1854f1fd656
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": 0.000806996034856021,
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": 1.1063,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7940152554946560.0,
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": 0.0012104940522840316,
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": 1.1063,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0009311492709877166,
72
+ "grad_norm": 1.7839757204055786,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.799,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0009311492709877166,
79
+ "eval_loss": 0.6185202598571777,
80
+ "eval_runtime": 1357.0146,
81
+ "eval_samples_per_second": 9.997,
82
+ "eval_steps_per_second": 4.998,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0010863408161523361,
87
+ "grad_norm": 1.172727346420288,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.4837,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.1971306928996352e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null