chauhoang commited on
Commit
510c5fa
·
verified ·
1 Parent(s): b57f3f7

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 sha256:1a6f5d8ec2ca702c32d620ea31212ee0326bdc44c046fd619e5498980871cebd
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074f817a1e06980d836b2f190dddb37bc0e10d0447ad0e1cd2056bd24b5f59b4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27c6affb93d194ea64862b17836b2eab222d7b87c6f72a8e1cd5d7d41ef09a5a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a73b14c9ce4eac6c56598549ebb6542ccf57c86643069aa54bae53cc26f0979
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a47fca3639d80e70dbf3c3184796f71da8605d334ca66b7e8450dbc7a8e3c251
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:346a86e33c4fc9bb13ea2c6d8957c569c6b0f0d7f2f487067bbdfae3040ed41d
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": 0.001198819623755072,
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": 0.0012,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4819847447838720.0,
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": 0.0017982294356326078,
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": 0.0012,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001383253412025083,
72
+ "grad_norm": 0.003302945988252759,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.7641,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001383253412025083,
79
+ "eval_loss": 0.20368286967277527,
80
+ "eval_runtime": 647.9929,
81
+ "eval_samples_per_second": 14.093,
82
+ "eval_steps_per_second": 7.046,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0016137956473625968,
87
+ "grad_norm": 0.02023138664662838,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.5793,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7317404761718784.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null