ardaspear commited on
Commit
5e18a78
·
verified ·
1 Parent(s): 5b57126

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b56057395db046e69174cd102ec05a8cef5fd60c3673fc8f7a9e69ae965661
3
  size 338298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67ae6f5029c748d71484f4ed224e6ebb67a1fdafb8705f4664ad9114adebb5b
3
  size 338298
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:493c9a52a8d0978544996a306577fa3509897b69780d3df8df75651a614b9f65
3
  size 418030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6abaacf93b4a89b45980e86ad4801e9b5860e9ec1483988f571fd9fe37bac55
3
  size 418030
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:029c00b369e8e39599fcd073967debe547b02579df9318d5dd1b7d89f06fc09a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8aa19cd9ecc96793f7d95ebdf271ae9d5fba9ad8aee081a27d3558a59c4a68
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
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": 0.1836734693877551,
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,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 611.451,
132
  "eval_steps_per_second": 155.642,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 346006093824.0,
154
  "train_batch_size": 4,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.22959183673469388,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 611.451,
132
  "eval_steps_per_second": 155.642,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.1989795918367347,
137
+ "grad_norm": 0.28444114327430725,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 6.8474,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.21428571428571427,
144
+ "grad_norm": 0.28362318873405457,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 6.8428,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.22959183673469388,
151
+ "grad_norm": 0.23609378933906555,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 6.8412,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.22959183673469388,
158
+ "eval_loss": 6.8371405601501465,
159
+ "eval_runtime": 0.2731,
160
+ "eval_samples_per_second": 604.065,
161
+ "eval_steps_per_second": 153.762,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 432507617280.0,
183
  "train_batch_size": 4,
184
  "trial_name": null,
185
  "trial_params": null