chauhoang commited on
Commit
b33a142
·
verified ·
1 Parent(s): 6c34465

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fe2d36739a3dd2ce2004b8d20451f5a33ee9a5e21041875120c2e2c86e09e18
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a0bbdaee8741456e6019d41435d2497031b447c90ae2e35cc5920e475341be
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d3d8c56b09cbb5485306316a487d82e46d0b71778ff26ee70bad6939f7097f4
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479a1059cf803b95f394a914cd1f25cee34ac0286bada3b2b9a0ba41b6e8c288
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb92806e57e387dc4287cb8248c41b4894921324de83cad277fe9afa6586b2d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185f5a451f9abc72729e973512be4f639b0b150a8950a48ddb47a15c2cc0c531
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.07498197548666186,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.4597,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4947584363790336.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.11247296322999278,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.4597,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.08651766402307137,
72
+ "grad_norm": 1.4230085611343384,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.4664,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.08651766402307137,
79
+ "eval_loss": 2.389425277709961,
80
+ "eval_runtime": 10.1849,
81
+ "eval_samples_per_second": 14.335,
82
+ "eval_steps_per_second": 7.167,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.10093727469358327,
87
+ "grad_norm": 0.7601160407066345,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.4343,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7536974311194624.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null