k4black commited on
Commit
2c49107
·
1 Parent(s): e765e19

Training in progress, step 1500

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c318274b9e69ca15d787840901e5bad0f748e669ca6a376cbb8ff2ba58b87440
3
  size 484015877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ad9ec05bbeaeea6847c8e5f34048897f15864d2e6417f92fe0384bcbe38a37
3
  size 484015877
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e2dfdee4d7e75e8661622e097ff1e10ee5c8afc9aae20e5f930126f250e2c6e
3
  size 242014297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dc530845fe5a0bb9f5e1d6d74bc0636c41628b3927424ca3ceb56e67cc3ed6
3
  size 242014297
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaef02ab8b67579aa70c9ab6ff61fabf7587a5da367ec704bf81333ce8386341
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdeb9ad2ec0b208042e20d040a22710fabc05e2dd9799b2ad24d60acdb7ae1f4
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6be6f394af4e26beaac13be32587b2f57676614cd6ad9f656259a62b2b7708fa
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4afba0142ee523929b01f1d1ea569b3d2c52550df725ed2ab1f846d29ecaac4
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b9097c2fa6fe7e76f005295cc0f44ad72751203fbe52b0e2a8b21cbe743411
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8c3a989c90e8906959eca2e634a75ff7806fbfde38d988307faba643b8a69f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.5382577445488361,
3
- "best_model_checkpoint": "results/checkpoint-500",
4
- "epoch": 0.2,
5
- "global_step": 1000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -46,11 +46,31 @@
46
  "eval_samples_per_second": 36.063,
47
  "eval_steps_per_second": 1.803,
48
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  }
50
  ],
51
  "max_steps": 15000,
52
  "num_train_epochs": 3,
53
- "total_flos": 2563405440614400.0,
54
  "trial_name": null,
55
  "trial_params": null
56
  }
 
1
  {
2
+ "best_metric": 0.5385440798738839,
3
+ "best_model_checkpoint": "results/checkpoint-1500",
4
+ "epoch": 0.3,
5
+ "global_step": 1500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
46
  "eval_samples_per_second": 36.063,
47
  "eval_steps_per_second": 1.803,
48
  "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.3,
52
+ "learning_rate": 9.477192982456141e-05,
53
+ "loss": 0.8139,
54
+ "step": 1500
55
+ },
56
+ {
57
+ "epoch": 0.3,
58
+ "eval_bleu": 0.11562105292517781,
59
+ "eval_exact_match": 0.1425,
60
+ "eval_loss": 0.8843896389007568,
61
+ "eval_rouge1": 0.5385440798738839,
62
+ "eval_rouge2": 0.3630877932160531,
63
+ "eval_rougeL": 0.520238931080043,
64
+ "eval_rougeLsum": 0.5274836357515698,
65
+ "eval_runtime": 55.2097,
66
+ "eval_samples_per_second": 36.226,
67
+ "eval_steps_per_second": 1.811,
68
+ "step": 1500
69
  }
70
  ],
71
  "max_steps": 15000,
72
  "num_train_epochs": 3,
73
+ "total_flos": 3850447817932800.0,
74
  "trial_name": null,
75
  "trial_params": null
76
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e2dfdee4d7e75e8661622e097ff1e10ee5c8afc9aae20e5f930126f250e2c6e
3
  size 242014297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dc530845fe5a0bb9f5e1d6d74bc0636c41628b3927424ca3ceb56e67cc3ed6
3
  size 242014297