kostiantynk1205 commited on
Commit
3985832
·
verified ·
1 Parent(s): e328954

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 sha256:92d52e37c41e950a2743a96a9524f6f43f4c157f4b753d783af6dec67177ab2f
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cabeca0b0399bfd11924ba1d321688b3bc764fd3061d92ae0642b8cb0dd5fa
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e06435aaef2ab84b113a7005f2de02947913961c321da5e980c9ff3b9f131c0
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43149fa3c90f76c64be5b898f59723753fdd62d14781303eec32557ea83c247
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fd7a2290f77a4159b388fe0269382f9ae2e2474e3f0daa565228958f5b5fb62
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c134cc708ce9d81193583fcacdd32f3e4fe0ff99e63b47726e2fd3625affde6
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": 0.02608695652173913,
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": 29.104,
74
  "eval_steps_per_second": 14.702,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1183052105515008.0,
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": 0.0391304347826087,
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": 29.104,
74
  "eval_steps_per_second": 14.702,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.030434782608695653,
79
+ "grad_norm": 15.488730430603027,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.1101,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.034782608695652174,
86
+ "grad_norm": 18.726163864135742,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.114,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0391304347826087,
93
+ "grad_norm": 26.18992042541504,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.8161,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0391304347826087,
100
+ "eval_loss": 0.7243495583534241,
101
+ "eval_runtime": 3.3166,
102
+ "eval_samples_per_second": 29.246,
103
+ "eval_steps_per_second": 14.774,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1752669785948160.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null