Nexspear commited on
Commit
a68658e
·
verified ·
1 Parent(s): 1dfb5da

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 sha256:8a939469575153adfbfc2f3df26d10e9ee8f30b3b3fe9a6b8d08f986f514c849
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e219bccefb2f09aa09257be309892be68a4f4ffa517b4927e4c3e501258dd76b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b412ed276d0ee13ba4b6aaeb08f7f3cd1ad7ce4fc6039e3c9c5bf4af59fe3d2a
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15f02365c1195370c60eb164bcc48c9291a976bd0b76c1698b1c724f57b0db4
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:ae5c619a4da90fa409bbf7a5cbb5a9f5b01fe3852d698c17628b4c1fb740305c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5926316ccbdc15291fd4d44c743eae350fd67684d89bb86c8ec5f6337921754f
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": 0.04764173415912339,
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": 6.291,
112
  "eval_steps_per_second": 0.79,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 7.54256789372928e+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": 0.05717008099094807,
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": 6.291,
112
  "eval_steps_per_second": 0.79,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.05145307289185326,
117
+ "grad_norm": 1.093232274055481,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 2.1642,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.05717008099094807,
124
+ "grad_norm": 1.1265302896499634,
125
+ "learning_rate": 5e-05,
126
+ "loss": 2.2761,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.05717008099094807,
131
+ "eval_loss": 2.271261215209961,
132
+ "eval_runtime": 140.6344,
133
+ "eval_samples_per_second": 6.286,
134
+ "eval_steps_per_second": 0.789,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 9.051081472475136e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null