leixa commited on
Commit
bc4b965
·
verified ·
1 Parent(s): 97bd9b3

Training in progress, step 35, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12e2366369ce8c38390addfa1542f39cc3aa413336ca1cd4d966ea681d7493ea
3
  size 891333320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4298347e53b50b963e6385890dcabe4edde31d906704cc992b0abb9ed8177ea2
3
  size 891333320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d13ca264618193c40dcaea4f30c4de6d69a2b8d01a73e7ec6274118ad1ab617
3
  size 452984596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937ee64104bb31c25302b0a37a27db6a98a23913096db45f1222044e16294e96
3
  size 452984596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fef463697b7f776aa8026ba9772a69cf45f54f0e647e6ce67df794c4a72deb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b10f01b3f2188618a5207c5ef3388e5a6e70139983e0aa8cb08ec9240d34a5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
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": 0.04333694474539545,
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,
@@ -133,6 +133,21 @@
133
  "eval_samples_per_second": 2.568,
134
  "eval_steps_per_second": 0.322,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 1.65373588537344e+17,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05055976886962803,
5
  "eval_steps": 5,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 2.568,
134
  "eval_steps_per_second": 0.322,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.047670639219934995,
139
+ "grad_norm": 0.025675935670733452,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 0.0004,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.05055976886962803,
146
+ "eval_loss": 0.018978465348482132,
147
+ "eval_runtime": 454.2548,
148
+ "eval_samples_per_second": 2.567,
149
+ "eval_steps_per_second": 0.321,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 1.92935853293568e+17,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null