Best000 commited on
Commit
fc592e8
·
verified ·
1 Parent(s): 4086e55

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 sha256:16055cec6747203a40d6ffd293585eff730b9025957225fcdd442e07ee25beb3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b868dc3866ac651dac49037220149d4d6ec6ee0da7ee8144193126555656b656
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7918db69cc0b2980a321f4377fc365eb35783f9840e2595368345b969fe6f806
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f101360f3f28863666af1aaa478caf9f1e1fdb7a5020fa0d5188b0b8ed162d4a
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": 0.0003146096873566232,
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": 32.483,
74
  "eval_steps_per_second": 16.242,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109738548887552.0,
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": 0.0004719145310349348,
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": 32.483,
74
  "eval_steps_per_second": 16.242,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00036704463524939374,
79
+ "grad_norm": 0.5774815678596497,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.1108,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0004194795831421643,
86
+ "grad_norm": 1.3663733005523682,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.0975,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0004719145310349348,
93
+ "grad_norm": 0.9578419923782349,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.1214,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0004719145310349348,
100
+ "eval_loss": 2.107719898223877,
101
+ "eval_runtime": 247.5052,
102
+ "eval_samples_per_second": 32.444,
103
+ "eval_steps_per_second": 16.222,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664607823331328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null