tuanna08go commited on
Commit
f3dac42
·
verified ·
1 Parent(s): ab15b90

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 sha256:530704ccd2cbef86006f154f3b2c4d208bc1fa76c971907a2cfda734ec05e709
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a622fed5730a4e62f53d426fafae7ecfe4c004649ae9d3bd0da3169acc30fe
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f85d8ee916c525513f80bf71554ca7fcc98d7d0cc4d9f92472dfac261ea41803
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743624874f034c6a37244a29ed592a12f406e90627161ad78c9c41f0dc286dea
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8b13df26bddb3c70b41dbe531e063a6e553c93965d731263f3f8cc687e7afb6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a69897655d6335f40565e13c6d562938736cf3824c45eb132524b68b5b2ee5
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": 0.03908305148440436,
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": 1.5414,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2545284525588480.0,
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": 0.058624577226606536,
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": 1.5414,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.04509582863585118,
72
+ "grad_norm": 1.018785834312439,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.4741,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.04509582863585118,
79
+ "eval_loss": 1.432031273841858,
80
+ "eval_runtime": 22.2918,
81
+ "eval_samples_per_second": 12.606,
82
+ "eval_steps_per_second": 6.325,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.05261180007515971,
87
+ "grad_norm": 1.1833542585372925,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.4144,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3817926788382720.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null