auxyus commited on
Commit
474da9e
·
verified ·
1 Parent(s): 9972a1e

Training in progress, step 36, 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:d3e180431901e1ce634b774363f43e832c57d1af94eb43193c1d3326e1046d5e
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db84560640f91efc56e844bdea8afc675bd95bceca3d42f9d5f0bb4ec2cdacf9
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c745f53dba14c5841ad408ba7f0df2f35e551bf11db41194c987ce4622d2c46
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4909eccaab426430b3fe8c5f4a3b4d1a4f547347c178f7cf549085791a7703fd
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0157d26a6c9880b1ce48a0bee6735b6a2e075272af9c2ec140c34f306deed1f1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875cc80f5d170fa1121c26562fc04de720d828ce782c9d29bd2e7b6e67614c5a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
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": 0.01517706576728499,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 18.204,
103
  "eval_steps_per_second": 2.278,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1.4107703437688832e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02023608768971332,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 18.204,
103
  "eval_steps_per_second": 2.278,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.016863406408094434,
108
+ "grad_norm": 0.1481175273656845,
109
+ "learning_rate": 8.83022221559489e-05,
110
+ "loss": 0.7242,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.01854974704890388,
115
+ "grad_norm": 0.14273004233837128,
116
+ "learning_rate": 8.473291852294987e-05,
117
+ "loss": 0.697,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.02023608768971332,
122
+ "grad_norm": 0.1542915254831314,
123
+ "learning_rate": 8.07830737662829e-05,
124
+ "loss": 0.7494,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.02023608768971332,
129
+ "eval_loss": 0.7546795606613159,
130
+ "eval_runtime": 164.7817,
131
+ "eval_samples_per_second": 18.188,
132
+ "eval_steps_per_second": 2.276,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 1.8810271250251776e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null