VERSIL91 commited on
Commit
5e30222
·
verified ·
1 Parent(s): 9b436db

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:772226d69a22b2159347220a25546958aed44715b44349767e3db4ad036ea6cb
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0284a91322faffc8fe737fb8701a94eed4830e6a7ca4596674c900f9e9f7cbd9
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d078a5a13572f53d6f4cd6255362edd174793b8c28428038afdeaacb8cbe2a9b
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3e5f7d14055f37c1d3ee928fb9e5f5031de04015901a92c9c420c4212bf63b
3
  size 43122580
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:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
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:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.028193832599118944,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 20.894,
38
  "eval_steps_per_second": 10.447,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1479651398516736.0,
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": 0.05638766519823789,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 20.894,
38
  "eval_steps_per_second": 10.447,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.04229074889867841,
43
+ "grad_norm": 26.700958251953125,
44
+ "learning_rate": 3e-05,
45
+ "loss": 9.6083,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.05638766519823789,
50
+ "grad_norm": 28.18412208557129,
51
+ "learning_rate": 4e-05,
52
+ "loss": 8.8679,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.05638766519823789,
57
+ "eval_loss": 7.889341831207275,
58
+ "eval_runtime": 5.789,
59
+ "eval_samples_per_second": 20.729,
60
+ "eval_steps_per_second": 10.364,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2959302797033472.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null