tuanna08go commited on
Commit
d30c05d
·
verified ·
1 Parent(s): e9ffba9

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 sha256:4c279622a5143129a7d62ce8962ab4b809ad2d12929180d1caea3b7d645fbdfe
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae53f5561a22819b9fd470830d7d640c9be9431e44bbaacf1613c834a672e61
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f898a01c2ced8c622f984cb497ec397dbe243a4664c6405d9eb8b2c8cec22fd3
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfd2e56b0344c5282584822191ed4024e28497a32fe2e8528505641cbc55f72
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab88c76e1a200c7f5fc1bfd392b2b60a4878104da3f6a35d2813aaaa7c1e3d68
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71e7d5985870b6965f25a8a7214a793a5c935f0b038f27ab6a11f462f8b5f40
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": 0.002070393374741201,
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": 1.4656,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4244442879885312.0,
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": 0.003105590062111801,
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": 1.4656,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0023889154323936935,
72
+ "grad_norm": 6.8505659103393555,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.8193,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0023889154323936935,
79
+ "eval_loss": 0.36222878098487854,
80
+ "eval_runtime": 449.6465,
81
+ "eval_samples_per_second": 11.76,
82
+ "eval_steps_per_second": 5.88,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002787068004459309,
87
+ "grad_norm": 5.405407905578613,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.3195,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6366664319827968.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null