tuanna08go commited on
Commit
e1bc937
·
verified ·
1 Parent(s): d59aee5

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:a8d4646abd9deaabf947784d14c2a509cd03609478ec8a5c21e6acac526e9944
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec266f79f6d24d26e525a728eecdb9f8227a708607026bd0cd6093d38be3005
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764b67931b25f8610024d8757ac09509891ea6f7166bba7adc0096acaa55e6d8
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d5d495a04ebfbfeaed430625dca647bce67b8d2c27be8c2201b3026d7d56586
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec542b26c32a374ce73f946e51924ebdfeffaac8414b3ea2a0214b7121e428a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f73a7f94cc8d884e27d6e5e3c1a8c08d2b909c93f19f6d763ca72e74ecec766
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": 0.0011305085114246582,
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": 1.2247,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4518701621575680.0,
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": 0.0016957627671369871,
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": 1.2247,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0013044328977976825,
72
+ "grad_norm": 0.8174328207969666,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.2074,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0013044328977976825,
79
+ "eval_loss": 1.2257455587387085,
80
+ "eval_runtime": 782.5361,
81
+ "eval_samples_per_second": 12.375,
82
+ "eval_steps_per_second": 6.188,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0015218383807639629,
87
+ "grad_norm": 0.7449996471405029,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.2185,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6695894221062144.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null