chauhoang commited on
Commit
33cbd75
·
verified ·
1 Parent(s): 739bd06

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 sha256:0c529450b6b38e0cee15e5c16a9477919e1146327431559a7f6cb617dccee247
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e908281e0960ff9a2d4a0fe8a2638ab0291a1b88a7dc53fe8a5b62c9361d0e69
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d10898a608cfaffa1bf58cc291da1b1c008a419413621b20950e0448d0ffcef6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa0e8fece85be74cc186ec2a59c62640ac2f728c149c8fc2d4a2461ba9df47f
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e5490d94bb03531bf8be5cc1bbbbb8917faf84a2ab32417656d21a48c1d381f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66846a1a2d466cde2705e723dbdb0fd132aefa0f6eb3cd191f3c155efb669d2a
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": 0.010290916287354047,
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": 1.017,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 6613736009760768.0,
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": 0.015436374431031071,
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": 1.017,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.011874134177716208,
72
+ "grad_norm": 0.5955860614776611,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.9265,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.011874134177716208,
79
+ "eval_loss": 0.9131612777709961,
80
+ "eval_runtime": 88.6617,
81
+ "eval_samples_per_second": 12.001,
82
+ "eval_steps_per_second": 6.0,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.013853156540668909,
87
+ "grad_norm": 0.6309583187103271,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8876,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 9694668933562368.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null