devvanshhh commited on
Commit
d6b1068
1 Parent(s): 314c219

Training in progress, epoch 2, 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:df0614e6ae0c4cca08ec46a3a0eca5c114c29487c73131333ee0ac8747dbc354
3
  size 37789864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cf38f014772cfcdeec2c5faa136d146b02002f02921ba47785fcf6257b5b91
3
  size 37789864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c375252e989676c82361bf75c9e05f8625ab364d94f54619de39642b83371a55
3
  size 2621690
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a418fe7b8f7343475866a7c922ff5e2054db620b0181b374466ca0a6de439ff0
3
  size 2621690
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3206cfea353705871f16d46e55ccf93893b489d46b83fd7ba2c4d45d71b93a7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6d24b9d254e55dd502f46ee3a75731bdd6708d3ea9ed7943f073b2f1ffd723e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30c8d100410f3813df39e9f84e8d440fdc3cad2e6c15e5ee2bb73e18d8c8af53
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5471e537684dae9b1e0fdb6332e8f4ceb0c244b24aed115cdfcefd75bee9cbed
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": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 328,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -20,13 +20,32 @@
20
  "eval_samples_per_second": 1.852,
21
  "eval_steps_per_second": 0.236,
22
  "step": 328
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "logging_steps": 500,
26
  "max_steps": 3936,
27
  "num_train_epochs": 12,
28
  "save_steps": 500,
29
- "total_flos": 2458142180573184.0,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 656,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
20
  "eval_samples_per_second": 1.852,
21
  "eval_steps_per_second": 0.236,
22
  "step": 328
23
+ },
24
+ {
25
+ "epoch": 1.52,
26
+ "learning_rate": 1.8394004282655248e-05,
27
+ "loss": 18.3143,
28
+ "step": 500
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_gen_len": 8.896907216494846,
33
+ "eval_loss": 0.9259825944900513,
34
+ "eval_rouge1": 31.5806,
35
+ "eval_rouge2": 27.0287,
36
+ "eval_rougeL": 29.6916,
37
+ "eval_rougeLsum": 30.0327,
38
+ "eval_runtime": 155.4292,
39
+ "eval_samples_per_second": 1.872,
40
+ "eval_steps_per_second": 0.238,
41
+ "step": 656
42
  }
43
  ],
44
  "logging_steps": 500,
45
  "max_steps": 3936,
46
  "num_train_epochs": 12,
47
  "save_steps": 500,
48
+ "total_flos": 4916284361146368.0,
49
  "trial_name": null,
50
  "trial_params": null
51
  }