VERSIL91 commited on
Commit
d966073
·
verified ·
1 Parent(s): 9789b10

Training in progress, step 3, 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:e6aebd4ac8155a3d2fa753876329316987b8e2fe46c4e5c8bbc1aacd4d87f1ff
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe66648aa3ab628bb1cc772d8dbc9300d3e7ec8548fc5ebea1410dcd53d43159
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d133b197bd903db999bdd2f3bc73e952f611af56dd7f30980eb5e3e6f8880c08
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c051f1e9ae5b9ffa9695b63f5f736eaa7260bde58298ad73b5184893db7cf3c3
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de467893e672a801a7f1cdb08392e9d44e3a212844f5c512ebfc1cfea50e9b1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
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": 0.7441860465116279,
5
  "eval_steps": 1,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,21 @@
37
  "eval_samples_per_second": 13.366,
38
  "eval_steps_per_second": 8.019,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -51,12 +66,12 @@
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
- "should_training_stop": false
55
  },
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1641914893860864.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.255813953488372,
5
  "eval_steps": 1,
6
+ "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 13.366,
38
  "eval_steps_per_second": 8.019,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 1.255813953488372,
43
+ "grad_norm": 34.39786911010742,
44
+ "learning_rate": 3e-05,
45
+ "loss": 15.866,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 1.255813953488372,
50
+ "eval_loss": 8.760246276855469,
51
+ "eval_runtime": 0.3773,
52
+ "eval_samples_per_second": 13.253,
53
+ "eval_steps_per_second": 7.952,
54
+ "step": 3
55
  }
56
  ],
57
  "logging_steps": 1,
 
66
  "should_evaluate": false,
67
  "should_log": false,
68
  "should_save": true,
69
+ "should_training_stop": true
70
  },
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 2462872340791296.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null