duyphu commited on
Commit
de85e05
·
verified ·
1 Parent(s): 44e3a17

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 sha256:3bc9850308d17106843bd00f406fc21810abd1e5cad894893a4b00b7dbe1fc69
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f58410d96441928b8e84e5a035dd9daab11804184e66e72f4a9943f6f7543b9
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9de03504bc28b265e80f7b3ff8e9ea668b18cc527b33bfa2733b6a290676f067
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521fb488372582689b64a4c4f59d3ebdeba63473ff33c9bc9ddfd307ad145452
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25ec60ffe2fb5edbd0cfbdda0f17282b968644048575059d74da5532e8c1dcd
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": 0.0038172141677371993,
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": 2.7701,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 329441206075392.0,
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": 0.005725821251605799,
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": 2.7701,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004404477885850615,
72
+ "grad_norm": 1.5364112854003906,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.9963,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004404477885850615,
79
+ "eval_loss": 2.9349489212036133,
80
+ "eval_runtime": 103.4049,
81
+ "eval_samples_per_second": 27.736,
82
+ "eval_steps_per_second": 13.868,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005138557533492384,
87
+ "grad_norm": 1.593353033065796,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 3.1426,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 489709900922880.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null