ClarenceDan commited on
Commit
95ce2cc
·
verified ·
1 Parent(s): 707124b

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:eed24b477fdf71608bbabb4783597c243d9214ed09504f9c40db1f89a398ad10
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a2638e940b817544111d193e0450055f82faf887fadd675a1f346db71043c9
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00bb604adff075916652553e6f756b485ce26d9245ee91577e1adacf02c29ca2
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d277fc44029378a2f0d6c174c5bbd556887b43ca1148ea1f404fafbeabb8cc3c
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:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
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": 0.0016955139526669022,
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": 17.56,
74
  "eval_steps_per_second": 8.78,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2103206159056896.0,
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": 0.002543270929000353,
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": 17.56,
74
  "eval_steps_per_second": 8.78,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001978099611444719,
79
+ "grad_norm": 6.197779655456543,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.307,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0022606852702225363,
86
+ "grad_norm": 6.19174861907959,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.7262,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002543270929000353,
93
+ "grad_norm": 5.924742698669434,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.5307,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002543270929000353,
100
+ "eval_loss": 0.4889945685863495,
101
+ "eval_runtime": 84.8789,
102
+ "eval_samples_per_second": 17.554,
103
+ "eval_steps_per_second": 8.777,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3154809238585344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null