duyphu commited on
Commit
b82b68d
·
verified ·
1 Parent(s): 3c05218

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 sha256:0a6dacd18351efc0ce0ee8d61da0755d63fd5e468bf9dcd5c8e87dd92d211050
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0b0788bbc24e6ffd3d7772d181fd76baf3125f66d3243ca7d9487047a627d3
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50db2c681c1867d6d959aa06062a4a36aad7fe7926d4605a1d84e2eaf45381a
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f898f8145515c0014185f3b63452c18bc4156d0b19e9bf78dc01f18e4e2eada
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c0d77bcd56d96825c5ef028b2dd99ac2e61994d3c453c8d2883da32a92047be
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84a5cf2454179937316496e4212e2e56502a7858df2afe7855b38d36059da33
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": 0.0036889897843359817,
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": 0.6668,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 697581994770432.0,
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": 0.005533484676503973,
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": 0.6668,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004256526674233825,
72
+ "grad_norm": 0.8009120225906372,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.6256,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004256526674233825,
79
+ "eval_loss": 0.6064170002937317,
80
+ "eval_runtime": 86.325,
81
+ "eval_samples_per_second": 34.382,
82
+ "eval_steps_per_second": 17.191,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.004965947786606129,
87
+ "grad_norm": 0.7089608311653137,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6629,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1028332078497792.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null