chauhoang commited on
Commit
e4f1b4c
·
verified ·
1 Parent(s): a5142ea

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2311051796551763e53965c396ede90ce042521d96ba7fe8881b996dd6d6073a
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbbf525601ab6f26a7b0fee4a827a3ad0e06e5bcc297ae985acc451eb5269eda
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49dc72cddbd1ab76180fac0c1c4ba8f256e58c364370b57791d7ba2adc486981
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382bf4009912a43f14e68a965a8d14931c9b03e41e204895296a0d39613e83e9
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:551c6190aa7460da0f5f87f766f1e262863111d15319ee98d5b09ac189feeb2f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a9101315bed33e0f3a0fc84fd93cd1f88e425b915b76ec585cd3942cf27abe
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.08378088077336197,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.3319,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 997588715175936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10741138560687433,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.3319,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.08592910848549946,
94
+ "grad_norm": 9.571033477783203,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.9569,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.08592910848549946,
101
+ "eval_loss": 1.3932305574417114,
102
+ "eval_runtime": 6.2087,
103
+ "eval_samples_per_second": 31.569,
104
+ "eval_steps_per_second": 15.784,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0966702470461869,
109
+ "grad_norm": 15.935542106628418,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.4733,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.10741138560687433,
116
+ "grad_norm": 10.49211311340332,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.3353,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.10741138560687433,
123
+ "eval_loss": 1.3013057708740234,
124
+ "eval_runtime": 6.126,
125
+ "eval_samples_per_second": 31.995,
126
+ "eval_steps_per_second": 15.997,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 1278959891251200.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null