great0001 commited on
Commit
7855e57
·
verified ·
1 Parent(s): 9569705

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 sha256:261ee571feb7bf78b54c49d4f8fd89bf300b99bf93bb39f823dd78702982356c
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7cf5ec08cbd420410bf6f8890e1b4e2ae82091309dbf2d4eec99c6b2476b35
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b496f6491072087d8596b8bd51d8270cbb5072d6b9c8a6df50948a6c77477464
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c286621a81cf8fdb92acc0a2668cc07e27561c05504975b0925c124dca96bc12
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e980ac91dfd10bdb6e3091ce3c0f4bddff3a1862ab5ef480db9ef26d4707dae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:287ecd53a1d24297ce2f39c80b9d4d5380a3ef651a2a854cd0e76d3d6c05c66d
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": 0.004189944134078212,
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": 39.257,
74
  "eval_steps_per_second": 19.661,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 575136407224320.0,
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": 0.006284916201117319,
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": 39.257,
74
  "eval_steps_per_second": 19.661,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004888268156424581,
79
+ "grad_norm": 0.7674152851104736,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.3201,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00558659217877095,
86
+ "grad_norm": 0.8000145554542542,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.2271,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006284916201117319,
93
+ "grad_norm": 0.9004802703857422,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.0464,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006284916201117319,
100
+ "eval_loss": 2.3105177879333496,
101
+ "eval_runtime": 15.381,
102
+ "eval_samples_per_second": 39.204,
103
+ "eval_steps_per_second": 19.635,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 856586138419200.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null