nadejdatarabukina commited on
Commit
8549cad
·
verified ·
1 Parent(s): f33eb67

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99c3b2136e5c8710d8878fb094af6fa626e227921bc634d41a723f747bd44b4f
3
  size 9864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f8e1ed4984690180aa15ea1905b74f5f8b0501f95db93b1229808ff9894618
3
  size 9864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f4138918dcbd01a20b7db0b4bfff1fb183406dc9eff9871820edd31ad2e01e
3
  size 27002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34b021f7c34e33bc4fb2204925cafd276d6ff36bc8113fc1189df0f004eb33e
3
  size 27002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d349eefde442d7ff305100770c74fc0736a5e9bdf35f2b86c961ef818a410804
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e71cead5a7fcc376909c83446602574c8bdf1bd2d38d471d24ab6cfd202c92
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
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": 0.0011228385358185494,
5
  "eval_steps": 7,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 0.00018,
45
  "loss": 46.0,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 408934907904.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0022456770716370988,
5
  "eval_steps": 7,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 0.00018,
45
  "loss": 46.0,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.001347406242982259,
50
+ "grad_norm": 1.6248943211394362e-05,
51
+ "learning_rate": 0.0001913545457642601,
52
+ "loss": 46.0,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.001571973950145969,
57
+ "eval_loss": 11.5,
58
+ "eval_runtime": 39.6547,
59
+ "eval_samples_per_second": 94.566,
60
+ "eval_steps_per_second": 47.283,
61
+ "step": 14
62
+ },
63
+ {
64
+ "epoch": 0.0016842578037278239,
65
+ "grad_norm": 1.0620135071803816e-05,
66
+ "learning_rate": 0.00015000000000000001,
67
+ "loss": 46.0,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.0020211093644733886,
72
+ "grad_norm": 1.4074231330596376e-05,
73
+ "learning_rate": 8.954715367323468e-05,
74
+ "loss": 46.0,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 807895793664.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null