lesso commited on
Commit
a3d8c86
1 Parent(s): 9e22952

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 sha256:87eceed1967c8bd0c320fd6eba1bedc93a96a7a1ed9418e240f2920ab4c1d79c
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0cabf4f9b6ec23d6472dd3c101d1a4aa391e8cee9a4c8eed591842007a3792
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da0833dc932af47b53a1622f93720f7bfa8ebb586a7771cbabf0773b0c06f5cb
3
  size 250679090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f3f6ee433466a3d17e7ceae02e407cd469bef2c2574d02ec91ccbd083f25d0
3
  size 250679090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c68ffab4b21297e45ed3ee7d7dea552f1b0499ba35355fdd480197c38f72ce
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d350fb63629b5bbbb1b6067754fd294bad8dde900daee7588c8d726fa5fb4835
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
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": 8.350294869787589e-05,
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": 9.864,
74
  "eval_steps_per_second": 9.864,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1903974521241600.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00012525442304681385,
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": 9.864,
74
  "eval_steps_per_second": 9.864,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 9.742010681418854e-05,
79
+ "grad_norm": 2.4749975204467773,
80
+ "learning_rate": 0.0001,
81
+ "loss": 3.6626,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0001113372649305012,
86
+ "grad_norm": 3.602562427520752,
87
+ "learning_rate": 0.00012,
88
+ "loss": 5.4928,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00012525442304681385,
93
+ "grad_norm": 4.245274066925049,
94
+ "learning_rate": 0.00014,
95
+ "loss": 3.3841,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00012525442304681385,
100
+ "eval_loss": 5.604666233062744,
101
+ "eval_runtime": 1537.609,
102
+ "eval_samples_per_second": 9.839,
103
+ "eval_steps_per_second": 9.839,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2855961781862400.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null