kostiantynk-out commited on
Commit
db7040f
·
verified ·
1 Parent(s): dec5f2a

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ccf7e6a3b6cb2acf5fcf36251e2fa2b5b12773d32417494947e081b4f2ab223
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e18367faeec495a4692d71c9b797eaff09a487d043c0b170d6e5705d485781
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9533083114befb1f6f27d3c55bd7b8f916b304b79aa831fb3fa8b0a15d49211
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ade605dec930b52f8ee8773fa88cdb63ac7918025de1c3d5191d3d207207ff9
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86c0e10a935030c84e25d102a1924a6d4ce44217fe68fd04a8a01ab30e4f14c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f06f736c0f41cb7607b86e5979ce3b08b7e211689aa13e876aea3af1577ddd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0012795905310300703,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 19.356,
45
  "eval_steps_per_second": 9.678,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 550772026638336.0,
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": 0.0025591810620601407,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 19.356,
45
  "eval_steps_per_second": 9.678,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0017061207080400938,
50
+ "grad_norm": 0.7213350534439087,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.6767,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0021326508850501172,
57
+ "grad_norm": 0.7695198059082031,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.7562,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0025591810620601407,
64
+ "grad_norm": 0.9236007928848267,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.9805,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0025591810620601407,
71
+ "eval_loss": 0.4349501132965088,
72
+ "eval_runtime": 51.0295,
73
+ "eval_samples_per_second": 19.361,
74
+ "eval_steps_per_second": 9.681,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1101544053276672.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null