ardaspear commited on
Commit
28bfda7
·
verified ·
1 Parent(s): 9bf937d

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 sha256:3aa99e7cf2c3076f5ba88203146caeafb7c3c3e471219a98518a8ae34ea3bac0
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7ee60a0a44b6439b704240a661c46ded6f259af1851918427a5e77324a18cb
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f808c01192174f4f98f7f0269a5c6044231c9e8c5247c1824b0f10192f14b6fd
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e270a0694a1d6ab0fe16f92645d076ebec60a83aa5f6ad8ea26cd719f9122b
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e6d5121af4ad8437561e7d254c21798ee487271bfae0bf79a1a5a2f43ee4420
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e26364f3cce101390527d688d4bddc18dce96177c114ab13ed952e8abea57e
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": 0.0023321711347178654,
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": 16.019,
112
  "eval_steps_per_second": 4.005,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 3.048173869203456e+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": 0.0027986053616614387,
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": 16.019,
112
  "eval_steps_per_second": 4.005,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.002518744825495295,
117
+ "grad_norm": 3.0833184719085693,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 1.0283,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.0027986053616614387,
124
+ "grad_norm": 2.3142240047454834,
125
+ "learning_rate": 5e-05,
126
+ "loss": 0.8235,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.0027986053616614387,
131
+ "eval_loss": 0.9399139285087585,
132
+ "eval_runtime": 1126.7479,
133
+ "eval_samples_per_second": 16.024,
134
+ "eval_steps_per_second": 4.006,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 3.661363364757504e+16,
156
  "train_batch_size": 4,
157
  "trial_name": null,
158
  "trial_params": null