dimasik87 commited on
Commit
6be0932
1 Parent(s): 2efd391

Training in progress, step 9, 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:fa2052aea8d730d6f641daa0283942bbad1566d514d1b0d1d736e2bb25844005
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609f4dfd93814675300d007f012fe43bc9d9a93ce4ddfb892000347a6cb22aea
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60a8142277391c4b72c8427b7445d296effd0ba75847ff57ed83396d655ecd98
3
  size 25986148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a352ed648367902bbbf893519c5aec4c49a743ca2e0ffac5d0b0d9cb50e89fe0
3
  size 25986148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cb24b3f3f4c4a67fab43264a5041d5eddbe696e430c47d0bfd9e5f90902b3a0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da371ed384dd48ba3f51b4afee7d61db3dfdb18617828b0330774642ccc5f0e8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.005375139977603583,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 4.271,
74
  "eval_steps_per_second": 2.135,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1235242526441472.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008062709966405375,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 4.271,
74
  "eval_steps_per_second": 2.135,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006270996640537514,
79
+ "grad_norm": 0.5025619268417358,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.0538,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.007166853303471445,
86
+ "grad_norm": 0.41523295640945435,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.0953,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.008062709966405375,
93
+ "grad_norm": 0.40565767884254456,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.8898,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.008062709966405375,
100
+ "eval_loss": 1.0463182926177979,
101
+ "eval_runtime": 79.1602,
102
+ "eval_samples_per_second": 5.937,
103
+ "eval_steps_per_second": 2.969,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1852863789662208.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null