duyphu commited on
Commit
e43c62e
·
verified ·
1 Parent(s): fee4655

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:d55327680b98f5a4b0054bd0e646f560e6e41ed6f63e025fdce0ef43e6f0111e
3
  size 327040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3c2a4b3043758db87aea66ab315fa2cbc313165bb80462915bc105c60af228
3
  size 327040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d5a8845bd61516516ca018d9320a3afe8d721c4172e9af29f2367f5c10db25e
3
  size 739258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d72e3443f6773246671b21cfde17e1159a1de68d5073dbfe8c386d124d2a2c
3
  size 739258
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38c414079b785cf8d1fad8f33cd71845cb15909579b0bc15b941b713fcaa6e99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
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": 0.023391812865497075,
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": 11.9293,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3254054289408.0,
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": 0.03508771929824561,
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": 11.9293,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02699055330634278,
72
+ "grad_norm": 0.4041164219379425,
73
+ "learning_rate": 5e-05,
74
+ "loss": 11.9306,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02699055330634278,
79
+ "eval_loss": 11.9298677444458,
80
+ "eval_runtime": 11.3831,
81
+ "eval_samples_per_second": 41.114,
82
+ "eval_steps_per_second": 20.557,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03148897885739991,
87
+ "grad_norm": 0.46610507369041443,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 11.9284,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4881081434112.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null