dimasik2987 commited on
Commit
c657aeb
·
verified ·
1 Parent(s): fa7d829

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e2845801b99cb3685224f18642535d4f0e28bd88158c755f597fb623a25d0bf
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794296f31a07e3e269f490c5dedc8253aacbbb152ace30a4820eb7e68a889931
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94c42555967d1acf7c84b6668a91bcf71ee6d4b55eba7c1db4fd5803c3092c16
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ac9fb1fc9a6f94a636c1e7d7f004e76668e7bcca5d2ded0d715ff1c6eb0b3e
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea3c486b366b7ad1bd39abe0b3d1a0af4c6b486923a5eced42a19e659304e95
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
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": 0.6722689075630253,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 0.0003,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 7031294986813440.0,
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": 1.0168067226890756,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 0.0003,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.7058823529411765,
79
+ "grad_norm": 0.008489878848195076,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 0.0001,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.8067226890756303,
86
+ "grad_norm": 0.002849513664841652,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 0.0001,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.8067226890756303,
93
+ "eval_loss": 2.648355621204246e-05,
94
+ "eval_runtime": 1.9424,
95
+ "eval_samples_per_second": 6.693,
96
+ "eval_steps_per_second": 3.604,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.907563025210084,
101
+ "grad_norm": 0.003049885854125023,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 0.0001,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 1.0168067226890756,
108
+ "grad_norm": 0.0022303862497210503,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.0001,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1.054694248022016e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null