Hugging Face's logo

mllm-dev
/
gpt2_f_experiment_0_1000

Text Classification
Transformers
Safetensors
gpt2
Model card Files
xet
Community
mllm-dev commited on
Commit
52efdbe
·
verified ·
1 Parent(s): d3e7e9b

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. model.safetensors +1 -1
  2. optimizer.pt +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. tokenizer.json +6 -1
  6. trainer_state.json +11 -11
  7. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b53bd7864340cb1ff1be471b28dee889de95392185238f095ad7f4b5989f938
3
  size 497789648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4951c9ca55af2a64eabf581fa46f012f12ef690c81807e05e7792b23dbb1cf8c
3
  size 497789648
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1c9c7b693c69c0e056f9b41ac6a02ce6cf95c3c12c97fe91ceccaf497c1fac8
3
  size 995673413
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66dfada35c9e04780d5608496e44775e6366d37f0d52208087efebacac06f35e
3
  size 995673413
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5a82e145bcb51281f0e3288b6286d1b334761ba440e10daf30143b33986f384
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de74e9b16c4b31513ab9159be73bd327e14e0226148dd1efca153f7515ab4dad
3
  size 14575
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54f4f1b94cd49b030804b6e9c96d8faa07f56dfc10847cc9c67d1bcd0647a578
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25691735045c5749946dfe06471e1c5eb87438b273847d8c5a01062be5dc2158
3
  size 627
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 1024,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
trainer_state.json CHANGED
@@ -1,29 +1,29 @@
1
  {
2
- "best_metric": 1.5173566341400146,
3
- "best_model_checkpoint": "sean_test_out/checkpoint-42",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.3621,
14
- "eval_loss": 1.5173566341400146,
15
- "eval_runtime": 58.2076,
16
- "eval_samples_per_second": 171.799,
17
- "eval_steps_per_second": 7.164,
18
- "step": 42
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 42,
23
  "num_input_tokens_seen": 0,
24
  "num_train_epochs": 1,
25
  "save_steps": 500,
26
- "total_flos": 306840103464960.0,
27
  "train_batch_size": 24,
28
  "trial_name": null,
29
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.178378701210022,
3
+ "best_model_checkpoint": "sean_test_out/checkpoint-84",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
+ "global_step": 84,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.4797,
14
+ "eval_loss": 1.178378701210022,
15
+ "eval_runtime": 79.7887,
16
+ "eval_samples_per_second": 125.331,
17
+ "eval_steps_per_second": 5.226,
18
+ "step": 84
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 84,
23
  "num_input_tokens_seen": 0,
24
  "num_train_epochs": 1,
25
  "save_steps": 500,
26
+ "total_flos": 638116197765120.0,
27
  "train_batch_size": 24,
28
  "trial_name": null,
29
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:015a81ea3c368db7e1478620d19710f9ad4e6ca3deab48d719162901636ec025
3
  size 4539
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f9144f67da7983d88ccf259eb25a569660f027c553cd313e11d713f3b713b6
3
  size 4539