tuanna08go commited on
Commit
99fa357
·
verified ·
1 Parent(s): fe1b248

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:d6b803c46a19a7d6d161fdaca065c16fb3570285c05d72f7359c2b0cef4e185a
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f80bd690bc795873881cc7d6fbbfb5d0a39aeffd95276d0c64b484fdd1c405
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9ed7b08b52e85267318a417f479d249bd0384e9f9e2b0b9ce87c741d89c74fc
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04879fe79286b7dabbb85f58b958ea459dd3b8ba332ce0d3d8621594e2107405
3
  size 162868
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:913a7368968d4008e86629febfbb08ed71c049260fa617734b65bfe139c8dfd8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b7f58f46be17989edce51431a5206319271ef30c1df04cc9f420e21f1886cd
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": 0.0031994093398141884,
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": 44.3418,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 330334470144.0,
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": 0.004799114009721282,
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": 44.3418,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0036916261613240634,
72
+ "grad_norm": 1.1006004810333252,
73
+ "learning_rate": 5e-05,
74
+ "loss": 44.3088,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0036916261613240634,
79
+ "eval_loss": 11.075800895690918,
80
+ "eval_runtime": 20.0623,
81
+ "eval_samples_per_second": 170.568,
82
+ "eval_steps_per_second": 85.284,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.004306897188211407,
87
+ "grad_norm": 1.3228192329406738,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 44.2922,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 482240102400.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null