tuanna08go commited on
Commit
db0f0df
·
verified ·
1 Parent(s): 8282fc7

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:e811ef899c91fd17d8fed036764c71aa36a158dc35e3b0e4e8a82616f09f0196
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bb8df2fdb0e04a8f8703a934bb03b07b6f0d0cf91a7b7d61fbc1b30329ba72
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d285241eea8a0e84a5759f26866a64f7653ee90983bcb81fe7dc080e59cf5789
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681ed008e251ac20e83778071c528d85dc8ed8ce8e2d2a4cbb5090f64aa80517
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a660fe1685e8a6b7a3af3fc232b2540a63f4d3847dc6daad940db92f4e5b7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbba3e37f3da5eebd20241eda5b6317a6fa8037aef8c40511f6d82de78527891
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": 0.004458161865569273,
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": 14.603,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 228094271029248.0,
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": 0.006687242798353909,
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": 14.603,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0051440329218107,
72
+ "grad_norm": 75.8990478515625,
73
+ "learning_rate": 5e-05,
74
+ "loss": 14.0956,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0051440329218107,
79
+ "eval_loss": 3.7265784740448,
80
+ "eval_runtime": 43.433,
81
+ "eval_samples_per_second": 56.547,
82
+ "eval_steps_per_second": 28.273,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.006001371742112483,
87
+ "grad_norm": 66.21800994873047,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 15.0597,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 342141406543872.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null