kooff11 commited on
Commit
7249e96
·
verified ·
1 Parent(s): 95965c7

Training in progress, step 13, 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:b941437f8f5adc30c8d8b646f5ebdca65d629aab45b5bcf80694a63db90ee74d
3
  size 247944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085639881fe3d90620a57fd76b82ac798d68e0ab5f92df280fff104a558826be
3
  size 247944
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6818586f1bff931e6761d8ea528ec61ffce61d86735b2b0855555d43d0daf2a
3
  size 263088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2365199c340c83d73c5aa4abf7e8616af7c8ac374eefb1694b7ac484558f15d2
3
  size 263088
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c26f365cac1317ac7717d8d7fed569b9ee8569217a3a63a2bff3f96ac3bc944b
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea7fba41e72a061c87b9c81e5b7981cdef279d463bf24a0c53d041fc6c485619
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9096a675bca03d3146bb2cbed300e224b12143889738fc5012a9f7cd4ddeb71f
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bb08213e9f4c7d6524d3584dcfe099212ebbacc99120d380088d5067ed1e87
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65f96fac9738bd743d88f80ce88e146114dc2ab55ff1e159bd8b01a0222db339
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339b579a534790054eb28e51de35d1a47ad1a4526ec1be6232e5e2a340410148
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": 0.927536231884058,
5
  "eval_steps": 4,
6
- "global_step": 12,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -123,6 +123,13 @@
123
  "eval_samples_per_second": 248.25,
124
  "eval_steps_per_second": 62.062,
125
  "step": 12
 
 
 
 
 
 
 
126
  }
127
  ],
128
  "logging_steps": 1,
@@ -137,12 +144,12 @@
137
  "should_evaluate": false,
138
  "should_log": false,
139
  "should_save": true,
140
- "should_training_stop": false
141
  },
142
  "attributes": {}
143
  }
144
  },
145
- "total_flos": 15974057115648.0,
146
  "train_batch_size": 2,
147
  "trial_name": null,
148
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0217391304347827,
5
  "eval_steps": 4,
6
+ "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
123
  "eval_samples_per_second": 248.25,
124
  "eval_steps_per_second": 62.062,
125
  "step": 12
126
+ },
127
+ {
128
+ "epoch": 1.0217391304347827,
129
+ "grad_norm": 32.89696502685547,
130
+ "learning_rate": 0.0,
131
+ "loss": 352.2435,
132
+ "step": 13
133
  }
134
  ],
135
  "logging_steps": 1,
 
144
  "should_evaluate": false,
145
  "should_log": false,
146
  "should_save": true,
147
+ "should_training_stop": true
148
  },
149
  "attributes": {}
150
  }
151
  },
152
+ "total_flos": 17305228541952.0,
153
  "train_batch_size": 2,
154
  "trial_name": null,
155
  "trial_params": null