ccore commited on
Commit
cdd3998
·
verified ·
1 Parent(s): 5e015d5

Training in progress, epoch 16, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10c788a3231500becd0e9a6adaea3cc99b5c460910f00c856dd75fb13a6c610b
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a655b3cb72ef6ba6b5cbc73f816532338dc1f376f009d16f2a9ed3dbd95eab
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a24dd36fd82efe9d6d32a045e4511183d5b4a5a8db10e4b322a9b7c2b8e4c7d
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1c918220923f3918ce8d9918f66ac71488d628cfc8554cda87b7e02df339c1
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:824f71db9f1256709fc08ef93182ab782a12b918c06c53930c51cb2d50c70df1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a07b953a6a45e05300151d5b920eb873d97649a826f6e931e77b1a9a37fda0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a7151eaee3e7a4e65d1924a3b0e9e091841f505cff806dfce44af7b59f8fee2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337ace8f5d4144b7f6a2379c830420f5f5bcb0d99f8f89360b299a3ae265b8ec
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.323224663734436,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-330",
4
- "epoch": 15.0,
5
  "eval_steps": 500,
6
- "global_step": 330,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -127,6 +127,14 @@
127
  "eval_samples_per_second": 36.933,
128
  "eval_steps_per_second": 9.233,
129
  "step": 330
 
 
 
 
 
 
 
 
130
  }
131
  ],
132
  "logging_steps": 500,
@@ -146,7 +154,7 @@
146
  "attributes": {}
147
  }
148
  },
149
- "total_flos": 1.064130172416e+16,
150
  "train_batch_size": 16,
151
  "trial_name": null,
152
  "trial_params": null
 
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,
 
127
  "eval_samples_per_second": 36.933,
128
  "eval_steps_per_second": 9.233,
129
  "step": 330
130
+ },
131
+ {
132
+ "epoch": 16.0,
133
+ "eval_loss": 1.3214843273162842,
134
+ "eval_runtime": 8.1269,
135
+ "eval_samples_per_second": 36.914,
136
+ "eval_steps_per_second": 9.229,
137
+ "step": 352
138
  }
139
  ],
140
  "logging_steps": 500,
 
154
  "attributes": {}
155
  }
156
  },
157
+ "total_flos": 1.1350721839104e+16,
158
  "train_batch_size": 16,
159
  "trial_name": null,
160
  "trial_params": null