Hugging Face's logo

Weni
/
testing_saving_checkpoints-final

Safetensors
Model card Files
xet
Community
Mel-Iza0 commited on
Commit
c2098bc
·
verified ·
1 Parent(s): 3e6657e

Training in progress, step 10, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-10/adapter_config.json +3 -3
  2. checkpoint-10/adapter_model.safetensors +1 -1
  3. checkpoint-10/optimizer.pt +1 -1
  4. checkpoint-10/rng_state_0.pth +1 -1
  5. checkpoint-10/rng_state_1.pth +1 -1
  6. checkpoint-10/scheduler.pt +1 -1
  7. checkpoint-10/trainer_state.json +6 -6
  8. checkpoint-10/training_args.bin +1 -1
checkpoint-10/adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v_proj",
23
- "k_proj",
24
  "o_proj",
25
- "q_proj"
 
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "o_proj",
23
+ "k_proj",
24
+ "q_proj",
25
+ "v_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
checkpoint-10/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad7070c1ec07bea4213610419dc167f0cfab800ee5f60de23fd3c49beeb06874
3
  size 27297032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d2c1096abef278e1f9d94096e22aaa75c9643b5698728e060259386612f5d5
3
  size 27297032
checkpoint-10/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44c89fee97e6e713f59fe845bfb8b93093b9dafdebd9917b802a476e42a4f824
3
  size 54678010
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582f12a9ab0d01b508473d4b9248dc8f598a880544e929df492f088f047fae24
3
  size 54678010
checkpoint-10/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f446d1d665fe499a7e8afff583956eaaf2eb2926c47d7d56c7673b47ebeae0f
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f072d2e4f105a1fc8caa732c6c518a12ce8762cc6e8ea93c49e3849dc87a1af2
3
  size 14512
checkpoint-10/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:497ab6fc08fd560fe9b02413f1de651810f4bffc2b565a53ca9893254102d233
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e9963b2ec74c1be45fcdd9aaaa2ce80c8eca051e922cfb2413a015fb4bc474
3
  size 14512
checkpoint-10/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:235af9e0142e33373d5a0c3eca9b645008891b3f929de0bb9dec14be1e0a5498
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec27b56d229809317bd71fa4690986df09485352bf2a99530baf5be2ed6ac3c1
3
  size 1000
checkpoint-10/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 1.2581307888031006,
3
  "best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
4
  "epoch": 0.006199628022318661,
5
  "eval_steps": 10,
@@ -10,10 +10,10 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.01,
13
- "eval_loss": 1.2581307888031006,
14
- "eval_runtime": 215.3103,
15
- "eval_samples_per_second": 13.316,
16
- "eval_steps_per_second": 3.33,
17
  "step": 10
18
  }
19
  ],
@@ -22,7 +22,7 @@
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
  "save_steps": 10,
25
- "total_flos": 5102376050491392.0,
26
  "train_batch_size": 8,
27
  "trial_name": null,
28
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3467941284179688,
3
  "best_model_checkpoint": "./mistral/29-02-24-Weni-testing_saving_checkpoints-final_Zeroshot-2_max_steps-60_batch_8_2024-02-29_ppid_7/checkpoint-10",
4
  "epoch": 0.006199628022318661,
5
  "eval_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.01,
13
+ "eval_loss": 1.3467941284179688,
14
+ "eval_runtime": 212.9079,
15
+ "eval_samples_per_second": 13.466,
16
+ "eval_steps_per_second": 3.368,
17
  "step": 10
18
  }
19
  ],
 
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
  "save_steps": 10,
25
+ "total_flos": 4695483733770240.0,
26
  "train_batch_size": 8,
27
  "trial_name": null,
28
  "trial_params": null
checkpoint-10/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:add53164c8641f40e75a374f927c9457bbf2b0878715f67c1711793300a2b818
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faf1dfa92ebafc0c9d15ced9f905651d3504c9f2a3c32cc1a5dabfb0804edd4
3
  size 5112