lesso02 commited on
Commit
545c57d
1 Parent(s): b2739d6

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64ecb17853e45e69bb8875ed21ded472a9727881f9e0d05de3c9e9ac813eee29
3
  size 22573704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ca589bf3b9907c272e54dc23ae2abaadd6fb9bf9115546413e690c0a854ef7
3
  size 22573704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c75ace2c3360791dd2c68d043ef3b4052bd633c09740eb37d236ba5f1d7b2678
3
  size 11710970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f45f3451dac302f62435612c9f982265f413125caea8d5d394a9f8fc8e1c97
3
  size 11710970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aa98b654a6ad98d9998c44f95a9ec59c7edf25202ad9a4080fb894c3b37d6e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e430790c418395df8ca73708b8c4c3a500f2ad56804e8db2527f4c5b2ee2f2c1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 8.880074592626579e-05,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 34.083,
74
  "eval_steps_per_second": 17.041,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 144327309262848.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00013320111888939868,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 34.083,
74
  "eval_steps_per_second": 17.041,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00010360087024731008,
79
+ "grad_norm": 4.990078926086426,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.4076,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00011840099456835437,
86
+ "grad_norm": 7.9193572998046875,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.4641,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00013320111888939868,
93
+ "grad_norm": 8.150678634643555,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.7354,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00013320111888939868,
100
+ "eval_loss": 5.326913356781006,
101
+ "eval_runtime": 842.0517,
102
+ "eval_samples_per_second": 33.787,
103
+ "eval_steps_per_second": 16.893,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 216490963894272.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null