chauhoang commited on
Commit
f3ff60b
·
verified ·
1 Parent(s): 8308208

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:ee46dadeac1670ee2171ed2cd7c35b07a0b3308beb8018956641d3ba75bbee03
3
  size 16794864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdfd1349872b4f2a5dbdacb089876a77cee0c916b0724bfa0b0cc44204f6f8bf
3
  size 16794864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7c410d22cdf775b649879ce01b8284c6d98f84fdd30cecb39337cc97c5f43f1
3
  size 8671162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef95acde7d09e83a0a3a0e96a3b672edb58396a2ba24f551243e12c6ca0dc8e3
3
  size 8671162
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b706875855f2be5f34e8de6609fc6e1b16fd875f08c9910f48619db8c936bf46
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": 0.0008665150265370227,
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": 9.1971,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 583355275935744.0,
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": 0.001299772539805534,
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": 9.1971,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0009998250306196416,
72
+ "grad_norm": 7.114785671234131,
73
+ "learning_rate": 5e-05,
74
+ "loss": 9.0419,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0009998250306196416,
79
+ "eval_loss": 2.2561514377593994,
80
+ "eval_runtime": 188.0369,
81
+ "eval_samples_per_second": 67.189,
82
+ "eval_steps_per_second": 33.594,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001166462535722915,
87
+ "grad_norm": 7.222141265869141,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 8.5684,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 875032913903616.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null