mamung commited on
Commit
7896a1e
·
verified ·
1 Parent(s): 9fb77b5

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 sha256:3205c2df9b5e8deefa7d97877695b23ae46023441a608c8e7f1a53043310783b
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e70bc7cc560ee3c734b69eebfd8c0301b33fda3faea7d90dfdb423a98a2536
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cbe7ffddcf84f6ea38928d7db3aa94267c99ef2965a9d35658be2e8246a0358
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8bdbab918f40ef85fba48b3593ee9566972172642efeb8921908331816e7a3
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:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b665a2618254d0693455029a117143eb612684fd8f287fa7207d501afc785521
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": 0.4243093922651934,
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": 5.92,
132
  "eval_steps_per_second": 2.96,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 1.8932962735580774e+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": 0.5303867403314917,
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": 5.92,
132
  "eval_steps_per_second": 2.96,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.45966850828729283,
137
+ "grad_norm": 24.18491554260254,
138
+ "learning_rate": 0.0001300741882076764,
139
+ "loss": 56.7812,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.4950276243093923,
144
+ "grad_norm": 29.25063133239746,
145
+ "learning_rate": 0.00012370860362476374,
146
+ "loss": 59.2692,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.5303867403314917,
151
+ "grad_norm": 26.837539672851562,
152
+ "learning_rate": 0.00011666776747647015,
153
+ "loss": 57.7333,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.5303867403314917,
158
+ "eval_loss": 1.8067072629928589,
159
+ "eval_runtime": 48.2991,
160
+ "eval_samples_per_second": 5.921,
161
+ "eval_steps_per_second": 2.961,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 2.3666203419475968e+17,
183
  "train_batch_size": 2,
184
  "trial_name": null,
185
  "trial_params": null