leixa commited on
Commit
6bc67f4
·
verified ·
1 Parent(s): c5c489c

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 sha256:116891ae0ef4cfa6f919d2744ec5a1f25dac6cb37192283e4d375cdece627943
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba25ce0dda301f5b9245ffcd5e552cc74da84ce6b004f7e45385833a47405276
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:333e95c1fc799ccfd6b4ea02c8a0d11c2c127db01d49687161fec5e08472f5fb
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a4886fdba993fda8c37a853f6301d74e673e1ea3338429da8afe2ade262efe
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5d410b3554f51a9e330e4afd32a4b9dfb61483b755d339ad915a14e3add09dd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae23c720e43827fac7ec9738d78285292b2b49a0ea5579feabe2dcfc07f544e5
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": 0.021367521367521368,
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": 6.538,
112
  "eval_steps_per_second": 0.819,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 6.4401180721152e+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": 0.02564102564102564,
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": 6.538,
112
  "eval_steps_per_second": 0.819,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.023076923076923078,
117
+ "grad_norm": 1.8316013813018799,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 2.4214,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.02564102564102564,
124
+ "grad_norm": 1.9308996200561523,
125
+ "learning_rate": 5e-05,
126
+ "loss": 2.4971,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.02564102564102564,
131
+ "eval_loss": 0.5809954404830933,
132
+ "eval_runtime": 301.5058,
133
+ "eval_samples_per_second": 6.537,
134
+ "eval_steps_per_second": 0.819,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 7.72814168653824e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null