VERSIL91 commited on
Commit
c475911
·
verified ·
1 Parent(s): 492b767

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 sha256:6bfe8691965ad198416ffc2a8c92822ea784c8c7a77c889dc7a1b8f8018e1255
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f91552f07a99b4c01b0e68cd3263be2da8d0a4d1d8a848df1e8d1aad6fa0044
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2efc68e3facaed3707e0ae9151c59e64e97af1bf1e733cbf97e20dcd66812469
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1dea5cbc8294d641cd14638bd21bd201af01bf653ea26538153739caa585688
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:207f66a3c887b74cd1db69c091115f5c25396878c1407db35bd2b1c6a57eecee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ad0b3c8c5cceedf5a189a90eb9b07f92d6d9af65176e2a41a16db159f342c9
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": 0.012618296529968454,
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": 12.688,
38
  "eval_steps_per_second": 6.368,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2524536360665088.0,
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": 0.025236593059936908,
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": 12.688,
38
  "eval_steps_per_second": 6.368,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.01892744479495268,
43
+ "grad_norm": 6.963824272155762,
44
+ "learning_rate": 3e-05,
45
+ "loss": 54.6442,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.025236593059936908,
50
+ "grad_norm": 7.627413749694824,
51
+ "learning_rate": 4e-05,
52
+ "loss": 55.8553,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.025236593059936908,
57
+ "eval_loss": 3.4388527870178223,
58
+ "eval_runtime": 23.945,
59
+ "eval_samples_per_second": 11.151,
60
+ "eval_steps_per_second": 5.596,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 4886199407738880.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null