leixa commited on
Commit
e5e0437
·
verified ·
1 Parent(s): e271090

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 sha256:07a5ecdbadb2ab0137331404ef1b0130d66db190c9fe69082fe7925914108596
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c6fdf9e9a232560719e77c0c853c18367a999fc044cad32df887624f6a9a9a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41bf36d7c7e6de97d0f9325142f7902caac6d2e195ac1f93cf75eb653bbd26bc
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17890b88aa14a3db23091d24326669770116cb671714801e6ca546e9c8e5694e
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1096e2380034f689d985b908db3f1a7e2fe156b4c4b33a315a0fff11943e1414
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4a3a1b96fec2a6e106190db5936dd024d3e04da279c604cce6fe98d30aa355
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": 0.2012072434607646,
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": 6.332,
112
  "eval_steps_per_second": 0.818,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 7.467142214791987e+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": 0.2414486921529175,
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": 6.332,
112
  "eval_steps_per_second": 0.818,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.21730382293762576,
117
+ "grad_norm": 0.07795149087905884,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 0.0092,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.2414486921529175,
124
+ "grad_norm": 0.0602896623313427,
125
+ "learning_rate": 5e-05,
126
+ "loss": 0.009,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.2414486921529175,
131
+ "eval_loss": 0.008096303790807724,
132
+ "eval_runtime": 33.0663,
133
+ "eval_samples_per_second": 6.321,
134
+ "eval_steps_per_second": 0.817,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 8.975655793537843e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null