VERSIL91 commited on
Commit
cbdb983
·
verified ·
1 Parent(s): 0f6ee5c

Training in progress, step 6, 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:bd25c3c74f63fc6f0c14de7cfc96d620765987550d9de4619b27aad3a38dbe95
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d983fb77b7fe853a56397d420b018a96a1883d74f6de8c327035acfa6fd38c
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f383915b43aced62dc1129dfb3f2408a912c0b9f7f88a955bb9ff434cbfc7a8a
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1146031d96072a620b4bc0926116eab7917994af6c0f15779513ad896790f63
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c30b90cacd6043668a9fceb65b4815e3ca7a9635af8292b75bda3517456e3b3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
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": 0.6530612244897959,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,28 @@
59
  "eval_samples_per_second": 38.508,
60
  "eval_steps_per_second": 21.004,
61
  "step": 4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -78,7 +100,7 @@
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 2636516677386240.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9795918367346939,
5
  "eval_steps": 2,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 38.508,
60
  "eval_steps_per_second": 21.004,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.8163265306122449,
65
+ "grad_norm": 1.609917402267456,
66
+ "learning_rate": 5e-05,
67
+ "loss": 1.1747,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.9795918367346939,
72
+ "grad_norm": 1.8385484218597412,
73
+ "learning_rate": 6e-05,
74
+ "loss": 1.1581,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.9795918367346939,
79
+ "eval_loss": 2.186253309249878,
80
+ "eval_runtime": 0.2832,
81
+ "eval_samples_per_second": 38.836,
82
+ "eval_steps_per_second": 21.183,
83
+ "step": 6
84
  }
85
  ],
86
  "logging_steps": 1,
 
100
  "attributes": {}
101
  }
102
  },
103
+ "total_flos": 3995970589163520.0,
104
  "train_batch_size": 2,
105
  "trial_name": null,
106
  "trial_params": null