robiulawaldev commited on
Commit
766df26
·
verified ·
1 Parent(s): b3fb9da

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d218066f9bf65d7e1fba85a442d83bdfa8b4ac1329e457dedb63f524eb74d1a
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32355dbfd3e2c2345faa1001f5ee83671417e30566f34a06a213f2b359014612
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ed5483f3386b57204f911e8f5fc0b1f04058467ad3b34aaf303f358d70c66d
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff996997f31f5062fdea86e8182a5ed2f40b3ad3a9d78384c850b353e96ad70
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e718a7530d4a43c65f6a32c4ec06806234526b2416ad18edaa4e2a72b6d99ae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937d976e009d1f4a517a8a7ac3c6389dc1bcd18394441b268110e7c7ea2402da
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
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": 0.07242339832869081,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 17.792,
61
  "eval_steps_per_second": 8.896,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 6330376330936320.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.09285051067780872,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 17.792,
61
  "eval_steps_per_second": 8.896,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.07428040854224698,
66
+ "grad_norm": 0.7836920619010925,
67
+ "learning_rate": 0.0002,
68
+ "loss": 4.5091,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.09285051067780872,
73
+ "grad_norm": 0.6817160248756409,
74
+ "learning_rate": 0.0002,
75
+ "loss": 4.7222,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 8127386386169856.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null