chauhoang commited on
Commit
597504d
·
verified ·
1 Parent(s): 7018243

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 sha256:7b0a97ccfa72c39621a5fbbc20bb25f98ee1e332fbd96861281255b0240bf39e
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122a7b3af0e0a60bac97552ab32f84563eb31164e9a1bb9120d1b19176ef0f10
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507d25898c9bef0156384c4e8f389d97f3251b9939d927303b2cb00579667edf
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb5320aeabcdaaab9038235f6dd9e4e261b4f7be12e01909661e93b1f3bc460
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90d14217b9aab4afc34bce8881096a848de30c1e82c9da12bc5a58ed5b303046
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0d25207b91073ecb1d8a246fff2f3dfd714db66536f34092c31ccf8ef9581c
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": 0.021711899791231733,
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": 0.4975,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 859390385061888.0,
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": 0.0325678496868476,
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": 0.4975,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.025052192066805846,
72
+ "grad_norm": 0.8014892935752869,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4266,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.025052192066805846,
79
+ "eval_loss": 0.43505820631980896,
80
+ "eval_runtime": 23.9252,
81
+ "eval_samples_per_second": 21.107,
82
+ "eval_steps_per_second": 10.575,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.029227557411273485,
87
+ "grad_norm": 0.7463769912719727,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.405,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1305300490518528.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null