ClarenceDan commited on
Commit
edf97ad
·
verified ·
1 Parent(s): 09fe77b

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 sha256:3b741bf2b8d491ca3cdbef51fac5416ea7f22a4b392d99272cb3ebe93eea570f
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83cd0e580df99b6a06a4c0d830aa2bc61ee4fc23746edabc8ec21954242ada4
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef543c988ff2fe1684a686b8f4b6a1826a8558fa1cdadb9a5ebb44cd7752b22d
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd61821931ddb4b801f7c851207330a0c8076810885a62c789c61932a62edc2
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0d93e3061b64759aa620549b741bccbbc12c7c91b59abbbc924cb2070bc4aaa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24da4f1c8fccc422960ec1e67f6ca5995c6e5471bfec8ff1a27d6db43853ec9e
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": 0.00011096059511865849,
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": 20.331,
74
  "eval_steps_per_second": 10.165,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 186607730688000.0,
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": 0.00016644089267798772,
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": 20.331,
74
  "eval_steps_per_second": 10.165,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0001294540276384349,
79
+ "grad_norm": 3.669551134109497,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.7205,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0001479474601582113,
86
+ "grad_norm": 3.312818765640259,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.0611,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00016644089267798772,
93
+ "grad_norm": 3.7113163471221924,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.0469,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00016644089267798772,
100
+ "eval_loss": 1.647411823272705,
101
+ "eval_runtime": 1108.4452,
102
+ "eval_samples_per_second": 20.54,
103
+ "eval_steps_per_second": 10.27,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 283643750645760.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null