ardaspear commited on
Commit
9e90212
·
verified ·
1 Parent(s): a992b26

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:b49222358c631c4efd5f6a67247e0afafaeb43f20659e563aed41c3cbc50037d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:005e80a0da39dc5a9402a1c6eae4c4259ff55441b8c8e0f354d2bedb6e1a4150
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35f048fd69e27e14c22b14407a413bd9583e33183fcb9bec3670c09f9d86ef70
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb940ebf47f948dde819a227650a19932f8170cea411fe83bc640234ac5b89b3
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:847e6adafbce1ce406fa778b8b6d2b9c0edf688a485355f7d2d7c87ce66c4fa0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4bc0fbdde4f390cae1da26df59eb2c832095420c66886351f99a6e9b7aa264e
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": 0.014158289678606824,
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": 12.498,
112
  "eval_steps_per_second": 3.127,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 3.77128394686464e+16,
134
  "train_batch_size": 4,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01698994761432819,
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": 12.498,
112
  "eval_steps_per_second": 3.127,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.01529095285289537,
117
+ "grad_norm": 4.833578109741211,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 4.1645,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.01698994761432819,
124
+ "grad_norm": 3.4795303344726562,
125
+ "learning_rate": 5e-05,
126
+ "loss": 4.1821,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.01698994761432819,
131
+ "eval_loss": 4.064857006072998,
132
+ "eval_runtime": 237.9521,
133
+ "eval_samples_per_second": 12.498,
134
+ "eval_steps_per_second": 3.127,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 4.525540736237568e+16,
156
  "train_batch_size": 4,
157
  "trial_name": null,
158
  "trial_params": null