Nexspear commited on
Commit
64276a8
·
verified ·
1 Parent(s): 6fe4ec7

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:224f2c94168f793bb457181dd0eed62e3b853f868330b09a4559ddfd765609dc
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140a2636639ca9c8f0036920c9a255be8e644fd8aacc802fd23aeb0d030f3566
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1a357421a56e38d8f83c3be8a21e09ff3a277292a6b2f4d6bcc35b63f337d56
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0c44da032b843bcabc2cd766664b0c1b0fda66d017aa5f41fa0357ad54bb12
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:692d9c50fe52a548aadff33300ef671f90f09a4fe52b8d8acd02eb05c9a1aed8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5fe797653ca95db8ea412f0cdf40228caecd07053fbe64f67ff0864160dff7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
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": 0.008595495960116899,
5
  "eval_steps": 5,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -111,6 +111,28 @@
111
  "eval_samples_per_second": 28.492,
112
  "eval_steps_per_second": 3.565,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 1.01269389705216e+16,
134
  "train_batch_size": 8,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.010314595152140279,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
111
  "eval_samples_per_second": 28.492,
112
  "eval_steps_per_second": 3.565,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.009283135636926251,
117
+ "grad_norm": 2.28306245803833,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 0.6412,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.010314595152140279,
124
+ "grad_norm": 2.4008116722106934,
125
+ "learning_rate": 5e-05,
126
+ "loss": 0.6312,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.010314595152140279,
131
+ "eval_loss": 0.6085503101348877,
132
+ "eval_runtime": 171.9315,
133
+ "eval_samples_per_second": 28.494,
134
+ "eval_steps_per_second": 3.565,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 1.215232676462592e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null