duyphu commited on
Commit
1325a58
·
verified ·
1 Parent(s): 050426e

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:e4600cd174efa3ff8a9058ca256119fe312810869e303a1f213de94fc80244a5
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b0e214febac2dd07145c1af65ef25ad6732af7cc5fbd75c90912a6a0dd99b7
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01255b4251364d582ed9216576c633a888418f684b069582f4cc0ea89c5a7ba3
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6cc402c59908c2f6ffd02836a292d6e342f3ac46948a21413d95e7ba05999a2
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:016c55e82eccfcbb8148b8b86c4e028c9b46d0568f2e785086aa10cc78ee6493
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35757f99aede5aa3cc24364e0aa31a367f6b45b4bcc48a59f3f8094086b95b26
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": 0.006444416904201264,
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": 2.8972,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 93447472545792.0,
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": 0.009666625356301896,
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": 2.8972,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.007435865658693766,
72
+ "grad_norm": 0.8339029550552368,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.9029,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.007435865658693766,
79
+ "eval_loss": 2.897880792617798,
80
+ "eval_runtime": 30.1974,
81
+ "eval_samples_per_second": 56.263,
82
+ "eval_steps_per_second": 28.148,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.008675176601809394,
87
+ "grad_norm": 0.9288826584815979,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.8161,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 142314499473408.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null