jssky commited on
Commit
594e8f8
·
verified ·
1 Parent(s): 66af5e3

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 sha256:068892dd9bba4d58d765c9c6bd3493ae3b0982d40a0f01c851b669ff586c90bf
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296c77ace204d16bc303da4af803bd77d3865523c8e73a875386f9f1bf6b012f
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:502fda1757d0dac83d62ef4e3e682339cfd1d486c5eceb63a29eb82731c53943
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd11974664ae9797c1c038fb65216f2022d8d0b0abd57e05885ecb60d2e34b93
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc31493e63ecd538ed9797ce7f0b1f45e546239d1056d5181e4cff524b5c4118
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7567ae8a1ec33e28c23869de794452faaab4545ecafbc1b4920ceae179c9547
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.00014165476373165865,
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": 16.997,
74
  "eval_steps_per_second": 16.997,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 216286290247680.0,
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": 0.00021248214559748798,
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": 16.997,
74
  "eval_steps_per_second": 16.997,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00016526389102026844,
79
+ "grad_norm": 4.292576789855957,
80
+ "learning_rate": 0.00012,
81
+ "loss": 2.4561,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00018887301830887822,
86
+ "grad_norm": 5.075192928314209,
87
+ "learning_rate": 0.00014,
88
+ "loss": 2.4012,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00021248214559748798,
93
+ "grad_norm": 4.3318610191345215,
94
+ "learning_rate": 0.00016,
95
+ "loss": 1.9781,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00021248214559748798,
100
+ "eval_loss": 2.1713130474090576,
101
+ "eval_runtime": 524.5919,
102
+ "eval_samples_per_second": 17.0,
103
+ "eval_steps_per_second": 17.0,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 324429435371520.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null