oldiday commited on
Commit
b847afc
·
verified ·
1 Parent(s): e785b4c

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 sha256:7ee2d2b8a87f8169ad8787e8282394eb0bb1ab9f31d961faea0729a1b54e1507
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e064a5d5d8aad1cb95c1b3520bd70d9302e1f36c9f93e3dfdae85d6f2e340f7a
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b02e08fdafd32d46be484cc7bf21f9bf090f03ce7d97e0677712fbe95b573b8e
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3174032e752723bbbca33f9601321b2b08cdbf096ac72cb23e87b56dd4066d1
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10350b5619e7d96fb7f3bffab3732b8b921da553987e25ecf13af945b954a09e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49324b9e90e4a3300216fe09ec318d103f16e5de8c543c825c0b873b9acee835
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
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": 0.7164179104477612,
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": 15.079,
132
  "eval_steps_per_second": 1.951,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 4.704899053702349e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8955223880597015,
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": 15.079,
132
  "eval_steps_per_second": 1.951,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.7761194029850746,
137
+ "grad_norm": 0.5589205026626587,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 1.0332,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.835820895522388,
144
+ "grad_norm": 0.5794256329536438,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 1.0239,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.8955223880597015,
151
+ "grad_norm": 0.5618190169334412,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 0.9851,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.8955223880597015,
158
+ "eval_loss": 1.0372254848480225,
159
+ "eval_runtime": 5.6453,
160
+ "eval_samples_per_second": 15.057,
161
+ "eval_steps_per_second": 1.949,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 5.881123817127936e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null