VERSIL91 commited on
Commit
9e3451e
1 Parent(s): 824a501

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 sha256:909e7ca545f32204d495af53e27ce2fdafcc87c6b154a7f98da59d607ff7b815
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef49ba54ff5ce4182a3309c5e577f11362c3c102628bb68ab75173919ada57a
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a1573ece213080b3194bd8a276e66e5be757d1d1504774bbd28ddda8422eb29
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e158d79bce209c237fa34566ecc216646bea8cb0699a1dd4f0959e82c3339c59
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23a86de1df0f3b7aa8bee495f190d53ab032f8eff4af01fcb623df004410d1c4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5038562034e3fb7746f0f33a324281a510fea3cd63a44cb1d968e86f32f52f9
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": 0.0011268002394450509,
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": 12.803,
38
  "eval_steps_per_second": 6.402,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4511840946094080.0,
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": 0.0022536004788901018,
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": 12.803,
38
  "eval_steps_per_second": 6.402,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0016902003591675763,
43
+ "grad_norm": 3.199329137802124,
44
+ "learning_rate": 3e-05,
45
+ "loss": 14.5531,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0022536004788901018,
50
+ "grad_norm": 2.3833396434783936,
51
+ "learning_rate": 4e-05,
52
+ "loss": 13.065,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0022536004788901018,
57
+ "eval_loss": 0.8808584809303284,
58
+ "eval_runtime": 370.8435,
59
+ "eval_samples_per_second": 8.063,
60
+ "eval_steps_per_second": 4.031,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 9181992100823040.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null