VERSIL91 commited on
Commit
26e550e
·
verified ·
1 Parent(s): 48e1283

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 sha256:7cd5613ef0051165929245077acf89b14796ac9fbe816c182a91b13c9ef53438
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38530996b9bb00146ed58abe1ea6d84a1a777227da752e170f910431734c4495
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88333c467c4da6d4513cc121aed294bef79ccab2038801a8a7545aae62947ad1
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dcd40dfa9273356c61ae596df8c7cf2bfa70597fe77d16620ffd4f87f4b7999
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b550eddb1fd0b6c7745761b04141bf71e2f5f8aef394e37d964f7d28953bcf3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9f821a5545c75b1cfa1a06b1823d7b35dba42e6f8dc963e0faf49c548c574b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
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": 0.5748502994011976,
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": 20.102,
74
  "eval_steps_per_second": 10.051,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2203088106553344.0,
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": 0.8622754491017964,
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": 20.102,
74
  "eval_steps_per_second": 10.051,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.6706586826347305,
79
+ "grad_norm": 19.34385871887207,
80
+ "learning_rate": 7e-05,
81
+ "loss": 7.1555,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.7664670658682635,
86
+ "grad_norm": 19.580270767211914,
87
+ "learning_rate": 8e-05,
88
+ "loss": 6.3322,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.8622754491017964,
93
+ "grad_norm": 19.722665786743164,
94
+ "learning_rate": 9e-05,
95
+ "loss": 5.4843,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.8622754491017964,
100
+ "eval_loss": 0.16169598698616028,
101
+ "eval_runtime": 0.9032,
102
+ "eval_samples_per_second": 19.929,
103
+ "eval_steps_per_second": 9.964,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3304632159830016.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null