trenden commited on
Commit
380817c
·
verified ·
1 Parent(s): f2524e9

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 sha256:136d15febd6079ad93341418e815e287b111315fb0dfa1cffd90b9bb702952ae
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15e99d1d415227f6fad95b012dc0e631338af61326eeacd544c3610e5f30c56
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e25c56443f6d5b91ceca75564bb41e357a5f67d5bd5af17b0aba9cc4bcd57215
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c2752ae503edea2b1c53144c9d91d221025c7ad37d94ebed41a10a3fd66630
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": 0.0007449714427613609,
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": 33.128,
74
  "eval_steps_per_second": 16.564,
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": 0.0011174571641420412,
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": 33.128,
74
  "eval_steps_per_second": 16.564,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0008691333498882542,
79
+ "grad_norm": 1.308701753616333,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.5555,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0009932952570151478,
86
+ "grad_norm": 1.7601176500320435,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.4406,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0011174571641420412,
93
+ "grad_norm": 1.5814690589904785,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.4161,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0011174571641420412,
100
+ "eval_loss": 1.2501493692398071,
101
+ "eval_runtime": 102.2988,
102
+ "eval_samples_per_second": 33.158,
103
+ "eval_steps_per_second": 16.579,
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