mamung commited on
Commit
2cc822a
·
verified ·
1 Parent(s): e0360a5

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:ec7cb6ff4d15c20c96385f4ac695ef9a639159a25a609775358906e14d278463
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e5a25e4ad9cac9d4df95470708deabb9789035a2d5bac9f6f7be515828b4e9
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86dab714d27f0887c5815327b4a49f743fd5f5539c77d1e35bfb57ff565ec841
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbb2f02618b2a40553b0dbf0c78612e7975a417e5ec77feacf49503c1bfe420
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22d0e0f373f425efa292dac5abf951f67103d9d788fea236fa7b5ab0e5d83fa6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ad7439565a5462d968f8d3364199f027aa6f68d9890049e5a20a8e24781131
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
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": 0.6028257456828885,
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": 2.76,
132
  "eval_steps_per_second": 1.38,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 1.8932777192993587e+17,
154
  "train_batch_size": 2,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7535321821036107,
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": 2.76,
132
  "eval_steps_per_second": 1.38,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.6530612244897959,
137
+ "grad_norm": 9.960721969604492,
138
+ "learning_rate": 0.00017343225094356855,
139
+ "loss": 3.1298,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.7032967032967034,
144
+ "grad_norm": 8.25685977935791,
145
+ "learning_rate": 0.00016494480483301836,
146
+ "loss": 2.9661,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.7535321821036107,
151
+ "grad_norm": 9.187298774719238,
152
+ "learning_rate": 0.00015555702330196023,
153
+ "loss": 2.7679,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.7535321821036107,
158
+ "eval_loss": 0.073814257979393,
159
+ "eval_runtime": 73.168,
160
+ "eval_samples_per_second": 2.761,
161
+ "eval_steps_per_second": 1.38,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 2.3665971491241984e+17,
183
  "train_batch_size": 2,
184
  "trial_name": null,
185
  "trial_params": null