dimasik87 commited on
Commit
5cb4419
1 Parent(s): 9f4d106

Training in progress, step 8, 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:a56b496c8cc60110f21380e0d0daa440a02946d09ff17a64b2adb7a47cd81f79
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f7bb679170c1929f66e5937e42f4cfe292c22eb413b8bc8f2cff99f4fa97ba1
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:133d94d62cc6a0d9e77ef132684f85fd38e77c533985319da2a98323a77a3fd8
3
  size 90310010
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ee98da1ed76eceb7ea803315aa0bf87e2f388b46eaa5c26615f1f50d7e1013
3
  size 90310010
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83ccae148eee587ae93f6957a30ef36e7134b0b765a678b4303ed6014551eed7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c4506a7d3a06ecce76a1df0b877b07017760972bbc99bac25d0adfd8d8ced7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.00019565483226674277,
5
  "eval_steps": 2,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -81,6 +81,28 @@
81
  "eval_samples_per_second": 16.089,
82
  "eval_steps_per_second": 16.089,
83
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  }
85
  ],
86
  "logging_steps": 1,
@@ -100,7 +122,7 @@
100
  "attributes": {}
101
  }
102
  },
103
- "total_flos": 580633541738496.0,
104
  "train_batch_size": 1,
105
  "trial_name": null,
106
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0002608731096889903,
5
  "eval_steps": 2,
6
+ "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
81
  "eval_samples_per_second": 16.089,
82
  "eval_steps_per_second": 16.089,
83
  "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.00022826397097786656,
87
+ "grad_norm": 3.325737953186035,
88
+ "learning_rate": 0.00014,
89
+ "loss": 2.9736,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.0002608731096889903,
94
+ "grad_norm": 2.959261894226074,
95
+ "learning_rate": 0.00016,
96
+ "loss": 2.8115,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.0002608731096889903,
101
+ "eval_loss": 2.495354413986206,
102
+ "eval_runtime": 400.9211,
103
+ "eval_samples_per_second": 16.105,
104
+ "eval_steps_per_second": 16.105,
105
+ "step": 8
106
  }
107
  ],
108
  "logging_steps": 1,
 
122
  "attributes": {}
123
  }
124
  },
125
+ "total_flos": 774178055651328.0,
126
  "train_batch_size": 1,
127
  "trial_name": null,
128
  "trial_params": null