Hugging Face's logo

filipesantoscv11
/
e913668d-907c-4372-b6be-e98f019104ed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
filipesantoscv11 commited on
Commit
ad10510
·
verified ·
1 Parent(s): e5c6ff3

Training in progress, step 30, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +48 -4
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96e4cf0a14390d8c3cec2477094799900764970c6a2458451fd1ced00c131dac
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834a36ea1cfd02e7e18959231609e52774ed3c3936a64d28fc36a0952234edd4
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a2721d9797680bada7824495ced0fb99bce5e40e55f13ebe900c47ed6b7a447
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c96f3b336c13560d27873d352560120f7ff9ec01c8459d628ba019672b8e249
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
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": 0.027643400138217002,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -89,6 +89,50 @@
89
  "eval_samples_per_second": 55.415,
90
  "eval_steps_per_second": 27.798,
91
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -103,12 +147,12 @@
103
  "should_evaluate": false,
104
  "should_log": false,
105
  "should_save": true,
106
- "should_training_stop": false
107
  },
108
  "attributes": {}
109
  }
110
  },
111
- "total_flos": 1029368772034560.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0414651002073255,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 55.415,
90
  "eval_steps_per_second": 27.798,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.02902557014512785,
95
+ "grad_norm": NaN,
96
+ "learning_rate": 4.2178276747988446e-05,
97
+ "loss": 0.0,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.0331720801658604,
102
+ "grad_norm": NaN,
103
+ "learning_rate": 2.061073738537635e-05,
104
+ "loss": 0.0,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 0.03455425017277125,
109
+ "eval_loss": NaN,
110
+ "eval_runtime": 5.5219,
111
+ "eval_samples_per_second": 55.235,
112
+ "eval_steps_per_second": 27.708,
113
+ "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.03731859018659295,
117
+ "grad_norm": NaN,
118
+ "learning_rate": 5.449673790581611e-06,
119
+ "loss": 0.0,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.0414651002073255,
124
+ "grad_norm": NaN,
125
+ "learning_rate": 0.0,
126
+ "loss": 0.0,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.0414651002073255,
131
+ "eval_loss": NaN,
132
+ "eval_runtime": 5.5446,
133
+ "eval_samples_per_second": 55.008,
134
+ "eval_steps_per_second": 27.594,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
147
  "should_evaluate": false,
148
  "should_log": false,
149
  "should_save": true,
150
+ "should_training_stop": true
151
  },
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 1544053158051840.0,
156
  "train_batch_size": 2,
157
  "trial_name": null,
158
  "trial_params": null