filipesantoscv11 commited on
Commit
b4d0dc4
·
verified ·
1 Parent(s): 4d76a3c

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6df3835ebb8a410086e40775839dcd215ef004799cfb91fcd99f06ed300090ac
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6eebfa927dd597f5b2467576d1b4e5a74f50d01f39872c16db123c54f82a8c
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38245d61c131b5b4e0018bb823c3efc96347ef8db6e4c3ed808188891564ba21
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cfd3b1a88f228dbdc969d3524399bd91b3255e54a58768bc7812dfde69253d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
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": 0.0004776974980593539,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 24.69,
53
  "eval_steps_per_second": 12.346,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +108,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 1126656871759872.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009553949961187078,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 24.69,
53
  "eval_steps_per_second": 12.346,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.0005732369976712247,
58
+ "grad_norm": NaN,
59
+ "learning_rate": 9.755282581475769e-05,
60
+ "loss": 0.0,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.0007165462470890309,
65
+ "grad_norm": NaN,
66
+ "learning_rate": 8.535533905932738e-05,
67
+ "loss": 0.0,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.0007165462470890309,
72
+ "eval_loss": NaN,
73
+ "eval_runtime": 356.4576,
74
+ "eval_samples_per_second": 24.729,
75
+ "eval_steps_per_second": 12.366,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.000859855496506837,
80
+ "grad_norm": NaN,
81
+ "learning_rate": 6.545084971874738e-05,
82
+ "loss": 0.0,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.0009553949961187078,
87
+ "eval_loss": NaN,
88
+ "eval_runtime": 357.768,
89
+ "eval_samples_per_second": 24.639,
90
+ "eval_steps_per_second": 12.321,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 2367612266741760.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null