lesso07 commited on
Commit
23734b2
·
verified ·
1 Parent(s): 1480e1d

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 sha256:6782198f26d7090c75ba067cf7a49276545a977660e7e4b002ebf39bf866c4d8
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db0f776b832980717dcde4b2cf2285695f43df74ac3e060af292a848546440b
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2717f48d2203de257427a8e67c82770c2e438c954b3c679e2267c7b873adc02d
3
  size 501028338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aaa5ea5e2948c05370ac038b229fad209e85e6cc84a33ca5eed8b547e6e180c
3
  size 501028338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dce83d5e7082d084aabbacccd92be956bcfaead09c5a0116c6978f26e20a645
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2955feef4f9f87c7ea2767455f885b0fea6093be542aa0bcc52b71742fc870
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.006739679865206402,
5
  "eval_steps": 2,
6
- "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -103,6 +103,28 @@
103
  "eval_samples_per_second": 5.722,
104
  "eval_steps_per_second": 2.861,
105
  "step": 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  }
107
  ],
108
  "logging_steps": 1,
@@ -117,12 +139,12 @@
117
  "should_evaluate": false,
118
  "should_log": false,
119
  "should_save": true,
120
- "should_training_stop": false
121
  },
122
  "attributes": {}
123
  }
124
  },
125
- "total_flos": 5078231757619200.0,
126
  "train_batch_size": 2,
127
  "trial_name": null,
128
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008424599831508003,
5
  "eval_steps": 2,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
103
  "eval_samples_per_second": 5.722,
104
  "eval_steps_per_second": 2.861,
105
  "step": 8
106
+ },
107
+ {
108
+ "epoch": 0.007582139848357203,
109
+ "grad_norm": 19.95369529724121,
110
+ "learning_rate": 0.00018,
111
+ "loss": 5.6036,
112
+ "step": 9
113
+ },
114
+ {
115
+ "epoch": 0.008424599831508003,
116
+ "grad_norm": 17.343950271606445,
117
+ "learning_rate": 0.0002,
118
+ "loss": 3.5369,
119
+ "step": 10
120
+ },
121
+ {
122
+ "epoch": 0.008424599831508003,
123
+ "eval_loss": 0.4855375289916992,
124
+ "eval_runtime": 86.9048,
125
+ "eval_samples_per_second": 5.753,
126
+ "eval_steps_per_second": 2.877,
127
+ "step": 10
128
  }
129
  ],
130
  "logging_steps": 1,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 6347789697024000.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null