Nexspear commited on
Commit
c4d584a
·
verified ·
1 Parent(s): 2f0be12

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 sha256:2f71d81a39abc391eebce46adc7515ae0b09d902f940f4183c06eb5e8dae076a
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e6ae29e1beda2d98937a2c2bdfcbe855cdaed6d575bb6ef4a8810daea3d441
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8005599fc82c0385b4240ca9e8c0c349710ccac8bced7e852ee2751d209091df
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2075a26f248adfe8404c3f4984ec8eb634473c693deca725eedf47cc1341d610
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:e0e6a9f77e80f64fd6145e88fb40919fa4f2e93cb194f5ef257b88329eea0ac7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824176984ad55e63482533637c9562406be551a7b54ccfb6e37dd38741558da7
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": 0.03073140749846343,
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": 12.711,
112
  "eval_steps_per_second": 1.595,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 3.959848144207872e+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": 0.03687768899815612,
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": 12.711,
112
  "eval_steps_per_second": 1.595,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.03318992009834051,
117
+ "grad_norm": 1.7881927490234375,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 0.5399,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.03687768899815612,
124
+ "grad_norm": 1.5611547231674194,
125
+ "learning_rate": 5e-05,
126
+ "loss": 0.5698,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.03687768899815612,
131
+ "eval_loss": 0.5137801170349121,
132
+ "eval_runtime": 107.8291,
133
+ "eval_samples_per_second": 12.715,
134
+ "eval_steps_per_second": 1.595,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 4.7141049335808e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null