Nexspear commited on
Commit
49be4c1
·
verified ·
1 Parent(s): 2e282d8

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:be9d2efb9e317fc6772e56f800552745bbfa573be0e138980248abdf7ea0344d
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8179eb4d79f7aa393f411e50e5c3a1ff84073d8c32d1a3f521a92b60690000c2
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f63d6b848cf583a4f54b6c39c1c464c5378f12e7d597e5e1eaa34406776367f
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e743c6e642d4272a6e7f54ee181f1edc1fd7730bed0b4b788cce05061d667e
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:584f9af47faa33f58e366891684daa24bbcfd0788a48868de15ac3d036b8b6b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224afa5218127cd3f7e7e6941d3c3023031e6b092cee08118cf53f23377cd02b
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": 0.011756407241946862,
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": 49.289,
112
  "eval_steps_per_second": 6.165,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 5332869631180800.0,
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": 0.014107688690336233,
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": 49.289,
112
  "eval_steps_per_second": 6.165,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.01269691982130261,
117
+ "grad_norm": 0.4752669930458069,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 1.2031,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.014107688690336233,
124
+ "grad_norm": 0.48559480905532837,
125
+ "learning_rate": 5e-05,
126
+ "loss": 1.1301,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.014107688690336233,
131
+ "eval_loss": 1.1357909440994263,
132
+ "eval_runtime": 72.6566,
133
+ "eval_samples_per_second": 49.3,
134
+ "eval_steps_per_second": 6.166,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 6399443557416960.0,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null