kostiantynk commited on
Commit
36eb937
·
verified ·
1 Parent(s): 1adc700

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 sha256:4a228bd6c36e474ba1e9b7c9691f08dd6391788bdfd4239fca255a781a92c884
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eda0f437de8a90fd9762b2eab11b88207453357b899a1e1cab239335d906b75
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c940f2a2805d660972220fe987df081e4dd88123c9e7ae6e3933d4028b90fc
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d889b95afbf0006e1560974f82128d4403f98287cab97aa7a87a36720cb685a7
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
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": 0.20168067226890757,
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": 27.804,
74
  "eval_steps_per_second": 14.971,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1051602475548672.0,
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": 0.3025210084033613,
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": 27.804,
74
  "eval_steps_per_second": 14.971,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.23529411764705882,
79
+ "grad_norm": 0.4345746636390686,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.006,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.2689075630252101,
86
+ "grad_norm": 0.1058090478181839,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.0015,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.3025210084033613,
93
+ "grad_norm": 0.04596443846821785,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.001,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.3025210084033613,
100
+ "eval_loss": 0.00030156096909195185,
101
+ "eval_runtime": 0.4556,
102
+ "eval_samples_per_second": 28.534,
103
+ "eval_steps_per_second": 15.365,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1577403713323008.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null