tuanna08go commited on
Commit
fcbf535
·
verified ·
1 Parent(s): b718bf7

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 sha256:676fd43c354a0e831385592b382c62a32785105824ac1710755c592765026cd0
3
  size 28348936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e11a69b59d112f675cc8e79307c08cb4b6e0a5e4f00b273373f1f06f9e82481
3
  size 28348936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf5f7452ed2cf904193b959eeff61a2f8dfd3381446cfd6ba6ac0d51a717fc5d
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba69dfea596ee4c34cda6a9896d5511c6380c400dee68e5494610b130f6d81d
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7220bcdf1e0071d3c9063219d77a75a745c869bbcb752b7ee1ddf041c34a52c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5df2a32540efe04518b932accc88bc4b406e31a8c93842f8edf84477d8a6d3
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": 0.0005044478721030626,
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": 0.4433,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1168285932453888.0,
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": 0.0007566718081545939,
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": 0.4433,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005820552370419952,
72
+ "grad_norm": 3.079180955886841,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.281,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005820552370419952,
79
+ "eval_loss": 0.3025643229484558,
80
+ "eval_runtime": 761.3039,
81
+ "eval_samples_per_second": 28.506,
82
+ "eval_steps_per_second": 14.253,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0006790644432156612,
87
+ "grad_norm": 0.7384060025215149,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2969,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1776768188940288.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null