baby-dev commited on
Commit
42659b0
·
verified ·
1 Parent(s): 2954f62

Training in progress, epoch 2, 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:af136286df6ff5905af165343cf57f5a831518e937bb6fc0471b78269e350229
3
  size 48552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e9e6cfd491339a63f64471a7a81cda3f53d2d51980e1b00307bca9bb403b17
3
  size 48552
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be91a147d44e75d2fcfd702628b092ecfc4ce8e1dd0ac3f0bd83e38b571d6119
3
  size 107046
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52d2ede02987bc8297c1be2a75b0d97e64a5099ea3b24849d0d3eca58d5dc89
3
  size 107046
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b97e51ea9f5d34aebc6d066d7c2fb7a20dbec78f27d117049f04bf79c02536c3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac03d4c1e9618de3b84437676fe2619fcfaff76bcfcfab780d49e69aaca826ea
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a277d82c7576fb11769cdddd31bacd8b5bc730226a0e626981ae85a7a41efa44
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6e8ea84c6ecd44137e4a21b32f529d3562b8f29f7c3085359bd396071d4c55
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": 1.9958071278825997,
5
  "eval_steps": 500,
6
- "global_step": 238,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -100,6 +100,14 @@
100
  "eval_samples_per_second": 241.592,
101
  "eval_steps_per_second": 62.192,
102
  "step": 238
 
 
 
 
 
 
 
 
103
  }
104
  ],
105
  "logging_steps": 20,
@@ -114,12 +122,12 @@
114
  "should_evaluate": false,
115
  "should_log": false,
116
  "should_save": true,
117
- "should_training_stop": false
118
  },
119
  "attributes": {}
120
  }
121
  },
122
- "total_flos": 268360826880.0,
123
  "train_batch_size": 4,
124
  "trial_name": null,
125
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.0041928721174003,
5
  "eval_steps": 500,
6
+ "global_step": 239,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
100
  "eval_samples_per_second": 241.592,
101
  "eval_steps_per_second": 62.192,
102
  "step": 238
103
+ },
104
+ {
105
+ "epoch": 2.0041928721174003,
106
+ "eval_loss": 11.917852401733398,
107
+ "eval_runtime": 0.4182,
108
+ "eval_samples_per_second": 241.517,
109
+ "eval_steps_per_second": 62.173,
110
+ "step": 239
111
  }
112
  ],
113
  "logging_steps": 20,
 
122
  "should_evaluate": false,
123
  "should_log": false,
124
  "should_save": true,
125
+ "should_training_stop": true
126
  },
127
  "attributes": {}
128
  }
129
  },
130
+ "total_flos": 269012385792.0,
131
  "train_batch_size": 4,
132
  "trial_name": null,
133
  "trial_params": null