Hugging Face's logo

tuanna08go
/
ef5b1810-cd19-47cb-a47d-0e18ee6c1860

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
8a02a55
·
verified ·
1 Parent(s): 816b3cc

Training in progress, step 50, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +41 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:284341141ff1fe4936ebd263b6af34f535c062fe68017ff42d5526003f381bda
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f796c5ff4981cf7df79848a861570343327e762f515e7b66285c41c34de8087
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23dd3d5e73f16182bbd3106b6de584b42c45867e1ebee05b58c3904807d440f9
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699cffc700feffbaf304fbe95e980542de62e5eef989dfc2f23c317dc2295897
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb8f5ec392ada8612a53a2987ca87e8e5cb830908e2443b405e1740d41af8ba1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d2645df4118113389cf0a8d71de6e864b916859f80db2df6497d2b9d5d1148
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": 0.005980219274706739,
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": 0.5896,
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": 4678737482219520.0,
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": 0.007666947788085563,
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": 0.5896,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.006133558230468451,
94
+ "grad_norm": 0.4432980418205261,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.5936,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.006133558230468451,
101
+ "eval_loss": 0.546730637550354,
102
+ "eval_runtime": 204.8893,
103
+ "eval_samples_per_second": 13.402,
104
+ "eval_steps_per_second": 6.701,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0069002530092770065,
109
+ "grad_norm": 0.42805182933807373,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.5344,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.007666947788085563,
116
+ "grad_norm": 0.4148527681827545,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.577,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.007666947788085563,
123
+ "eval_loss": 0.5442895293235779,
124
+ "eval_runtime": 204.4204,
125
+ "eval_samples_per_second": 13.433,
126
+ "eval_steps_per_second": 6.717,
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": 6052790497443840.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null