nat-hunt commited on
Commit
a9a3105
·
verified ·
1 Parent(s): 7b9577f

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:ffa202c9b35fda6e24a97350231be6362ec1a53854be2b419af5dc9da929e38f
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037236ac126dda937889ef046e34e3e73f44bc06567a6455c68295e8a566d7a6
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fadcd8ca96c4dfa4fff5db83681a4993c05a530af58fe5fed3398094a3a09a62
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17c962153968e731ae57e3d799beadeaf2a26d967e156d2a2bf62cacfdacaaf
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fee39bc01ddf78a38b847a29934f584af8ce3a64a3a53517107690a8bce55e4c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5ecbbf7b92c5892f8c669e6ba889de91fbf39e1c597bb83cbf4822a1109422
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": 0.009811937857726901,
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": 20.962,
45
  "eval_steps_per_second": 10.562,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 615718085197824.0,
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": 0.019623875715453803,
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": 20.962,
45
  "eval_steps_per_second": 10.562,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.013082583810302535,
50
+ "grad_norm": 2.4495112895965576,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.4988,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.016353229762878167,
57
+ "grad_norm": 3.515925645828247,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.0154,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.019623875715453803,
64
+ "grad_norm": 2.7797224521636963,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.7438,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.019623875715453803,
71
+ "eval_loss": 2.6141974925994873,
72
+ "eval_runtime": 6.3756,
73
+ "eval_samples_per_second": 20.233,
74
+ "eval_steps_per_second": 10.195,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1231436170395648.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null