ardaspear commited on
Commit
6c65ae4
·
verified ·
1 Parent(s): 4f1f2e6

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:d9e1fc52df00af6f86bf334d17420bdc509fe71996afa01336eacfd633c3a683
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a932a0faac4b641bf72ce63748ddde2dd62fcaf2789e90f0d14249273ee7e352
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e99c8d5762ea8dc4877e91ceeb01f13fd3f27d53a22eb3e0a0533bf0fe2f459
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28fe608ae6053ba54c94c3375caaf9cf2499321d53b93bfafae7f3423f342e6
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1af2d1ad71d0a525efd297d63ece1800652033d73e1aabfc1096f4a3269303a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016983c686e3f6559a80f761a5aee2d676a2ab199aac6efd1774aeda9637b12d
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": 0.017686072218128224,
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": 134.442,
134
  "eval_steps_per_second": 16.846,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 33053736960000.0,
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": 0.020633750921149593,
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": 134.442,
134
  "eval_steps_per_second": 16.846,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.019454679439941048,
139
+ "grad_norm": 0.3371483385562897,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 11.8769,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.020633750921149593,
146
+ "eval_loss": 11.87283706665039,
147
+ "eval_runtime": 21.1617,
148
+ "eval_samples_per_second": 135.008,
149
+ "eval_steps_per_second": 16.917,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 38562693120000.0,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null