duyphu commited on
Commit
2bbe71b
·
verified ·
1 Parent(s): f5878f7

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 sha256:8dc7627f6d81b7323fed2ac66376f5a7c340a72c1266f9f857b904c6de699984
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb0a489e550a277a2cdf24a31186a08d844159d52be874114c9514ae63cc945
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:838e2a79403a3a4048d01ac4409cd9920978df6b486c04e4b46f7ea84d79a8e9
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5e911361919dc0e5ec48d5b9044264452c0a4772a271620f0abc58e0fda340
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f926762ceb843f047dd528118613a61d4c267c001c9630420aab81a53778c78c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f095f52b97b7bccb542e54340cb700c4842060cb5eae55d2f7ac1450ce3c2c
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": 0.006938421509106678,
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": 1.3088,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 940035520069632.0,
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": 0.010407632263660017,
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": 1.3088,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.008005870972046168,
72
+ "grad_norm": 0.3198167383670807,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.3884,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.008005870972046168,
79
+ "eval_loss": 1.3172019720077515,
80
+ "eval_runtime": 51.3541,
81
+ "eval_samples_per_second": 30.728,
82
+ "eval_steps_per_second": 15.364,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.009340182800720529,
87
+ "grad_norm": 0.271278440952301,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.2783,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1374881883095040.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null