lesso commited on
Commit
9922460
1 Parent(s): 2a667eb

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:b6a2c4a5302057ae4bf5ebde0e11e45540f94682117bd98ab4a74f4464b2c67d
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3558277e560a59b9badeb6bac2729bade34c78b8b20452984d4887b54497dbb4
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc334085c8ce887a496861d7033a48b8bbcb1129f48e78c7c567869cc09bccf2
3
  size 160172858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc8054f5f2102f9bf053d9fe6c4659c0c0ba6ab9b32c5e930f053d851021ce4
3
  size 160172858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38c6291480501dedfdd188a2dde82d0e9dc6215c3786cd8b8b61e96d2ad44a53
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3483100185f9bb64a1baea7d0678dd8819a763e19d4dc3947a4c495c2a757eec
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": 0.00032123353678124,
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": 10.736,
45
  "eval_steps_per_second": 10.736,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 936521553149952.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00064246707356248,
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": 10.736,
45
  "eval_steps_per_second": 10.736,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0004283113823749866,
50
+ "grad_norm": 0.5536651015281677,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.1659,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0005353892279687332,
57
+ "grad_norm": 0.4006960093975067,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.0878,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00064246707356248,
64
+ "grad_norm": 0.34919866919517517,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.0365,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00064246707356248,
71
+ "eval_loss": 1.0633049011230469,
72
+ "eval_runtime": 184.7088,
73
+ "eval_samples_per_second": 10.649,
74
+ "eval_steps_per_second": 10.649,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1669451464310784.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null