chauhoang commited on
Commit
e8c4998
·
verified ·
1 Parent(s): 977e617

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:def2f98a9fa49c5944552556fe507bd5a6f55f19c2d0cd54bc9be957d7214ff4
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d999dd4148687ca52dc136e9ffa5fe7dcf8f64ba15b666393a0aa825fdfe996f
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b171f01d876e54df8782cbcc3a64a4627fa0544d5b8a42080aa2c853a5b2e483
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a39bb09a478e5946a479ea1f0c8a7159de7fe5a435b4a7b9341d29317af410d
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a37c1648d3f3cc4b038615e5a05edcf7fc13e1f76bda94223bbbe825e65d819b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e4872822d2d93a87125714a96799dd0dc0b91855c62fd49037073db7b6a96b
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": 0.004781389361408671,
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": 0.6475,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3567211692687360.0,
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": 0.007172084042113006,
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": 0.6475,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.005516987724702312,
72
+ "grad_norm": 0.556086540222168,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4812,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.005516987724702312,
79
+ "eval_loss": 0.4218650162220001,
80
+ "eval_runtime": 135.24,
81
+ "eval_samples_per_second": 16.933,
82
+ "eval_steps_per_second": 8.466,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.006436485678819365,
87
+ "grad_norm": 0.5369921326637268,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.403,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 5412321188904960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null