duyphu commited on
Commit
238680a
·
verified ·
1 Parent(s): 67b158c

Training in progress, step 39, 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:d4978abff3959d181a60616b9fe70b0dff6e5469e4dbc60268d5ed49e3188c42
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f0e8945c07b04b49319665b009601ef0f174f3d7e2db4c26e5d402e5bd525d
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:115d5500f52a1e3ea7ca701230719782e67dbb85bbdd9882f903e243795ec7f7
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ae67086bb49742697d253a7e435399cdd3f06e3497363a860bc77410d0c8df
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbf433e815bcfb3615ba2122a948b4904fc7b63110f4cc06d5f59bbf9003d456
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f4c5d4b86825b6500540affc20dd6a1231983e729a4827c7ce2ed5ccdb795d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0021169621593014024,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.9121,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4038739675054080.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0031754432389521038,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.9121,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.002442648645347772,
72
+ "grad_norm": 2.1868631839752197,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.8007,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.002442648645347772,
79
+ "eval_loss": 1.936930537223816,
80
+ "eval_runtime": 330.7595,
81
+ "eval_samples_per_second": 15.637,
82
+ "eval_steps_per_second": 7.818,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002849756752905734,
87
+ "grad_norm": 1.8994628190994263,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.7277,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6006856471019520.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null