Hugging Face's logo

tuantmdev
/
6860d41c-54b0-429a-b48d-4e896b5c9961

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
cd43885
·
verified ·
1 Parent(s): d1ab33b

Training in progress, step 300, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +2 -2
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +20 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7ce9575af73f4c250802c095ca9e0a84a59961d961928e9285dd494381eb149
3
  size 2436967616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11e6d209148544acb18b4a8bd842d9dbb98a810f6a020d89f9359c42762dfc8
3
  size 2436967616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6516bc4d8c6f54abe8b9f3b4597dea9ea861ad6cb711236d40fb7d5de34f868
3
- size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c41836182a36eb57cfd91220c427d52ed1f15bf75b93a6a6c632269855d6ab
3
+ size 170920532
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c605e83c4f568f78dd8ddf3ee5cc46f84435323472643ef3617eec247c6b6371
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda7dfaa785e89c1c3fd04d94117e45d1a8fef595eb33b17fe54e47fafcad92a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5182c64d745614fbc9217a3122cffdaa4b9683ea7cfb2e6909f3ad8f175d0a03
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9686b06e8feaa36ed10d72ecd8afef7e62f88744e516a900f077a3e6a083d3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5806567668914795,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
- "epoch": 0.015414258188824663,
5
  "eval_steps": 50,
6
- "global_step": 250,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -97,6 +97,21 @@
97
  "eval_samples_per_second": 13.118,
98
  "eval_steps_per_second": 6.559,
99
  "step": 250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100
  }
101
  ],
102
  "logging_steps": 40,
@@ -125,7 +140,7 @@
125
  "attributes": {}
126
  }
127
  },
128
- "total_flos": 1.0252986685902029e+17,
129
  "train_batch_size": 2,
130
  "trial_name": null,
131
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5710722208023071,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-300",
4
+ "epoch": 0.018497109826589597,
5
  "eval_steps": 50,
6
+ "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
97
  "eval_samples_per_second": 13.118,
98
  "eval_steps_per_second": 6.559,
99
  "step": 250
100
+ },
101
+ {
102
+ "epoch": 0.017263969171483623,
103
+ "grad_norm": 0.8200499415397644,
104
+ "learning_rate": 3.086582838174551e-05,
105
+ "loss": 1.6022,
106
+ "step": 280
107
+ },
108
+ {
109
+ "epoch": 0.018497109826589597,
110
+ "eval_loss": 1.5710722208023071,
111
+ "eval_runtime": 1041.1766,
112
+ "eval_samples_per_second": 13.118,
113
+ "eval_steps_per_second": 6.559,
114
+ "step": 300
115
  }
116
  ],
117
  "logging_steps": 40,
 
140
  "attributes": {}
141
  }
142
  },
143
+ "total_flos": 1.2295191400965734e+17,
144
  "train_batch_size": 2,
145
  "trial_name": null,
146
  "trial_params": null