duyphu commited on
Commit
f1968e1
·
verified ·
1 Parent(s): 5ad57e3

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 sha256:26c3303e1101263037bae97bf7fed2a7e749826d01931f99be6e9eb0d4fbc334
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aec6dccb1a9d8225dad96b8de50ea4bbbeb2aa4000558b8992e6f3d37cbf199
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab7ea7178c0c589a40fb4a8e2da32f34d5c2c20905fc64a16f67f6daa9a05aca
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5b89faf29cb3cf926a19ed6a4f665f5ed464e1a26928c4afb6749753545238
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66d743f7d7f1e483fc21966690f23e79e8c531a6f00323f193d4a604fb0e9d14
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5c24709107a16c4a366ef695fabf1bcf47b8db012ccbceb7d99c5d75c4b350
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": 0.046889089269612265,
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": 4.0398,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4644580267917312.0,
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": 0.0703336339044184,
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": 4.0398,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.05410279531109107,
72
+ "grad_norm": 5.880407333374023,
73
+ "learning_rate": 5e-05,
74
+ "loss": 4.0062,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.05410279531109107,
79
+ "eval_loss": 0.9842478036880493,
80
+ "eval_runtime": 15.7977,
81
+ "eval_samples_per_second": 14.812,
82
+ "eval_steps_per_second": 7.406,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.06311992786293959,
87
+ "grad_norm": 6.333781719207764,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.9598,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6966870401875968.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null