duyphu commited on
Commit
6a6ad74
·
verified ·
1 Parent(s): 6e046a7

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 sha256:7a16e1c85c334fc7eada6b24ff37be32e2525b190ded3df237d851388d56011f
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0407431add305c44a9c034f733a910207225c308ced08c249fb0b020b8d92fa5
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:656a791ad7bc5b47caf10ca8b9723d8ffde109e7723b75b7c6e0b82de6a39a88
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1158deeb82825dc9134ec81b873391a0de1dcf5738314d7d0cd60d264dcb3a81
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04fd270e669bc9caccdd1fc28fe53bb7f40c11badb883404c1759d887caa66cd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4e3a63ff432f0070f016a4fba7d15b41ae3139da5c92fc0c7a44016f2d48d3
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": 0.014793741109530583,
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": 2.0976,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 240403042271232.0,
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": 0.022190611664295874,
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": 2.0976,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.017069701280227598,
72
+ "grad_norm": 1.3707565069198608,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.16,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.017069701280227598,
79
+ "eval_loss": 2.133972644805908,
80
+ "eval_runtime": 24.4512,
81
+ "eval_samples_per_second": 30.264,
82
+ "eval_steps_per_second": 15.132,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.01991465149359886,
87
+ "grad_norm": 1.2129231691360474,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.9256,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 362830517501952.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null