tripathiarpan20 commited on
Commit
324ac5d
1 Parent(s): 8e6c307

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2007068a77bc5a236a15db665931f2b9bd11e54f775d1110bcf4fa7b6ec9ebef
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897f905bc43f8cad8ab8a8bda878c54023987e9e9eca0c9eddbf7cf30fd033a0
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a2c5f636f2003d285f69c345e6271bfe4fc5858bb1fb8fb1d723d2d0a7a5553
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab778c51d13d1bae87a585b19477c4f7a3c86711fe29b007f90121f65ab89b01
3
  size 23159290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24df05627e2e86925ca37683e21f902381144a8ad40105a0738461c44ce5f2e2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32fae2f082bc2b8a4f93f074fb88d1c6113a4081d21b0babdad2ac6534f83080
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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.002932121389825539,
5
  "eval_steps": 3,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -58,6 +58,57 @@
58
  "learning_rate": 0.0001,
59
  "loss": 2.0774,
60
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  }
62
  ],
63
  "logging_steps": 1,
@@ -72,12 +123,12 @@
72
  "should_evaluate": false,
73
  "should_log": false,
74
  "should_save": true,
75
- "should_training_stop": false
76
  },
77
  "attributes": {}
78
  }
79
  },
80
- "total_flos": 967722569564160.0,
81
  "train_batch_size": 2,
82
  "trial_name": null,
83
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005864242779651078,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
58
  "learning_rate": 0.0001,
59
  "loss": 2.0774,
60
  "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0035185456677906467,
64
+ "grad_norm": 3.4223129749298096,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.3995,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0035185456677906467,
71
+ "eval_loss": 2.007136821746826,
72
+ "eval_runtime": 110.0306,
73
+ "eval_samples_per_second": 6.525,
74
+ "eval_steps_per_second": 3.263,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004104969945755754,
79
+ "grad_norm": 3.431300163269043,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9596,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004691394223720862,
86
+ "grad_norm": 2.9658634662628174,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.8995,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00527781850168597,
93
+ "grad_norm": 3.0212576389312744,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.8483,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00527781850168597,
100
+ "eval_loss": 1.6423418521881104,
101
+ "eval_runtime": 109.9227,
102
+ "eval_samples_per_second": 6.532,
103
+ "eval_steps_per_second": 3.266,
104
+ "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005864242779651078,
108
+ "grad_norm": 2.9213950634002686,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.8063,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
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": 1935445139128320.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null