chauhoang commited on
Commit
5755be2
·
verified ·
1 Parent(s): e5e7555

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:d2a21049fb759a5455308daa3ac74badaf3c695758ba8d1abc32346fdcc368ff
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fd10a7e2676ea0bd4248b7a979f0e23508d4313150482c0d3211f5ce5377a0
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40445e9eb8a00fe0e852a26ff2437de71950ccb2ff41996bbc3035658df9a855
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a6debf3eedf44828e3d123bcacb605912e00dc78d8a4e14bb28259b8633cb0
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05882469d4ba520ef0e550cec0fc647162706c8d328d079d58f3c294c300c5b5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c28d8d1307642efe947fe98f6f7e242467882f7ac03aafe16fdbd065e0dc84
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": 0.03680113234253362,
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": 1.4689,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3617759837552640.0,
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": 0.055201698513800426,
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": 1.4689,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.04246284501061571,
72
+ "grad_norm": 0.5480692386627197,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.4806,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.04246284501061571,
79
+ "eval_loss": 1.4323680400848389,
80
+ "eval_runtime": 20.8381,
81
+ "eval_samples_per_second": 14.301,
82
+ "eval_steps_per_second": 7.15,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.04953998584571833,
87
+ "grad_norm": 0.4671808183193207,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.4361,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 5426639756328960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null