evgmaslov commited on
Commit
ffa30cf
1 Parent(s): 9454f18

Training in progress, step 2180, checkpoint

Browse files
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1294308d8bf6ba6841b15363db149eaa5825bcd538cf2b88a510fc7962145886
3
  size 67201802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd97621adbb9d248201089b74bd82480b6a1b7c05969600d0c780b0e56f0e427
3
  size 67201802
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98cb974d5d0ef0d7e1ac4e112ff901422a5698aacd83631999f7e03673918b92
3
  size 134433530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324d95ec2e4ba1f65e1906345dfb25a0970825a54076a009070f6a75438349e6
3
  size 134433530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a95847de8f71aeb0560485081d7ae3dbacd353743448787a10a2de32c045ab16
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ddb8ab23ecbb1f22fbc7249a1f4a132a2b1d244bfaa9c3dc084220f0917f81
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98862280ab449bf7d27896304f7ad4f092621710fc5ed1dc8e457ff1507b5b3c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6bbb3a2656972a7730072c5a553566a2af8d064180891226c18307cb101e1d7
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.8524497747421265,
3
  "best_model_checkpoint": "/content/results/checkpoint-2080",
4
- "epoch": 0.5148986889153755,
5
  "eval_steps": 20,
6
- "global_step": 2160,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1627,13 +1627,28 @@
1627
  "eval_samples_per_second": 0.311,
1628
  "eval_steps_per_second": 0.311,
1629
  "step": 2160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1630
  }
1631
  ],
1632
  "logging_steps": 20,
1633
  "max_steps": 4195,
1634
  "num_train_epochs": 1,
1635
  "save_steps": 20,
1636
- "total_flos": 8.002564606886707e+16,
1637
  "trial_name": null,
1638
  "trial_params": null
1639
  }
 
1
  {
2
  "best_metric": 0.8524497747421265,
3
  "best_model_checkpoint": "/content/results/checkpoint-2080",
4
+ "epoch": 0.5196662693682956,
5
  "eval_steps": 20,
6
+ "global_step": 2180,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1627
  "eval_samples_per_second": 0.311,
1628
  "eval_steps_per_second": 0.311,
1629
  "step": 2160
1630
+ },
1631
+ {
1632
+ "epoch": 0.52,
1633
+ "learning_rate": 0.0001476923076923077,
1634
+ "loss": 0.4314,
1635
+ "step": 2180
1636
+ },
1637
+ {
1638
+ "epoch": 0.52,
1639
+ "eval_jit_compilation_time": 2.8318,
1640
+ "eval_loss": 0.8527898788452148,
1641
+ "eval_runtime": 16.1058,
1642
+ "eval_samples_per_second": 0.31,
1643
+ "eval_steps_per_second": 0.31,
1644
+ "step": 2180
1645
  }
1646
  ],
1647
  "logging_steps": 20,
1648
  "max_steps": 4195,
1649
  "num_train_epochs": 1,
1650
  "save_steps": 20,
1651
+ "total_flos": 8.083361658322944e+16,
1652
  "trial_name": null,
1653
  "trial_params": null
1654
  }