ccore commited on
Commit
a204d9e
·
verified ·
1 Parent(s): 92521e9

Training in progress, epoch 17, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92a655b3cb72ef6ba6b5cbc73f816532338dc1f376f009d16f2a9ed3dbd95eab
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2ac1e7e990aff3af0a15d1835576aa2aebb5b9ee90647359719d3fd0134b8d
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac1c918220923f3918ce8d9918f66ac71488d628cfc8554cda87b7e02df339c1
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c963f45c1bd5ae5ff9658232185d3b067942933ba18628c76240dda57365c1
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a07b953a6a45e05300151d5b920eb873d97649a826f6e931e77b1a9a37fda0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25a1346ff38ded6949f1c63ea9bed0f00deec534050210f1999680410c965b05
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:337ace8f5d4144b7f6a2379c830420f5f5bcb0d99f8f89360b299a3ae265b8ec
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ac85153b9d8c1365faf7f0479f8e838f8c32f294048b97d718e681ea322699
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3214843273162842,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-352",
4
- "epoch": 16.0,
5
  "eval_steps": 500,
6
- "global_step": 352,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -135,6 +135,14 @@
135
  "eval_samples_per_second": 36.914,
136
  "eval_steps_per_second": 9.229,
137
  "step": 352
 
 
 
 
 
 
 
 
138
  }
139
  ],
140
  "logging_steps": 500,
@@ -154,7 +162,7 @@
154
  "attributes": {}
155
  }
156
  },
157
- "total_flos": 1.1350721839104e+16,
158
  "train_batch_size": 16,
159
  "trial_name": null,
160
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.31853449344635,
3
+ "best_model_checkpoint": "./opt_trained/checkpoint-374",
4
+ "epoch": 17.0,
5
  "eval_steps": 500,
6
+ "global_step": 374,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
135
  "eval_samples_per_second": 36.914,
136
  "eval_steps_per_second": 9.229,
137
  "step": 352
138
+ },
139
+ {
140
+ "epoch": 17.0,
141
+ "eval_loss": 1.31853449344635,
142
+ "eval_runtime": 8.1214,
143
+ "eval_samples_per_second": 36.939,
144
+ "eval_steps_per_second": 9.235,
145
+ "step": 374
146
  }
147
  ],
148
  "logging_steps": 500,
 
162
  "attributes": {}
163
  }
164
  },
165
+ "total_flos": 1.2060141954048e+16,
166
  "train_batch_size": 16,
167
  "trial_name": null,
168
  "trial_params": null