Upload folder using huggingface_hub
Browse files- all_results.json +17 -0
- checkpoint-140/config.json +33 -0
- checkpoint-140/model.safetensors +3 -0
- checkpoint-140/optimizer.pt +3 -0
- checkpoint-140/rng_state.pth +3 -0
- checkpoint-140/scheduler.pt +3 -0
- checkpoint-140/special_tokens_map.json +30 -0
- checkpoint-140/tokenizer.json +0 -0
- checkpoint-140/tokenizer_config.json +67 -0
- checkpoint-140/trainer_state.json +64 -0
- checkpoint-140/training_args.bin +3 -0
- config.json +33 -0
- eval_results.json +11 -0
- model.safetensors +3 -0
- predictions.txt +53 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +67 -0
- train_results.json +9 -0
- trainer_state.json +106 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.6153846383094788,
|
| 4 |
+
"eval_f1": 0.47368421052631576,
|
| 5 |
+
"eval_loss": 0.6848027110099792,
|
| 6 |
+
"eval_mcc": 0.17256712249065836,
|
| 7 |
+
"eval_runtime": 0.1138,
|
| 8 |
+
"eval_samples": 52,
|
| 9 |
+
"eval_samples_per_second": 456.859,
|
| 10 |
+
"eval_steps_per_second": 61.5,
|
| 11 |
+
"total_flos": 163423735633920.0,
|
| 12 |
+
"train_loss": 0.7042514474051339,
|
| 13 |
+
"train_runtime": 33.2199,
|
| 14 |
+
"train_samples": 554,
|
| 15 |
+
"train_samples_per_second": 333.536,
|
| 16 |
+
"train_steps_per_second": 42.143
|
| 17 |
+
}
|
checkpoint-140/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/ubuntu/utah/babylm-24/data/training/models/10M_babylm_ascii/SPM-Unigram_6144/DebertaV2-Base-10M_babylm-A",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 1536,
|
| 12 |
+
"label2id": {
|
| 13 |
+
"0": 0,
|
| 14 |
+
"1": 1
|
| 15 |
+
},
|
| 16 |
+
"layer_norm_eps": 1e-07,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"max_relative_positions": -1,
|
| 19 |
+
"model_type": "deberta-v2",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 8,
|
| 22 |
+
"pad_token_id": 3,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": null,
|
| 27 |
+
"position_biased_input": true,
|
| 28 |
+
"relative_attention": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.44.2",
|
| 31 |
+
"type_vocab_size": 0,
|
| 32 |
+
"vocab_size": 6144
|
| 33 |
+
}
|
checkpoint-140/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4be62a77ab9dedd098777ad54755f3a8d9eb3e26d6b7474ff9b99866cc9718c
|
| 3 |
+
size 174103504
|
checkpoint-140/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:807a6867e65c07bd7f0b0feed36bff29ed7574dd35edcb7ae3696b5e9f02f01f
|
| 3 |
+
size 348288250
|
checkpoint-140/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef6a994db5bb1ef20bc55033427d0b425bf9998852b81744fdc8bb4262e3d6d
|
| 3 |
+
size 14244
|
checkpoint-140/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50792edf44512d0536e32cea049bc3f5b58cbcd3e88ef4b503aa86670047127c
|
| 3 |
+
size 1064
|
checkpoint-140/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-140/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-140/tokenizer_config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "[PAR]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "[TAB]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"clean_up_tokenization_spaces": false,
|
| 61 |
+
"cls_token": "[CLS]",
|
| 62 |
+
"mask_token": "[MASK]",
|
| 63 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 64 |
+
"pad_token": "[PAD]",
|
| 65 |
+
"sep_token": "[SEP]",
|
| 66 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 67 |
+
}
|
checkpoint-140/trainer_state.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.47368421052631576,
|
| 3 |
+
"best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/wsc/checkpoint-140",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 140,
|
| 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": 0.6153846383094788,
|
| 14 |
+
"eval_f1": 0.0,
|
| 15 |
+
"eval_loss": 0.6650720834732056,
|
| 16 |
+
"eval_mcc": 0.0,
|
| 17 |
+
"eval_runtime": 0.1205,
|
| 18 |
+
"eval_samples_per_second": 431.51,
|
| 19 |
+
"eval_steps_per_second": 58.088,
|
| 20 |
+
"step": 70
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"eval_accuracy": 0.6153846383094788,
|
| 25 |
+
"eval_f1": 0.47368421052631576,
|
| 26 |
+
"eval_loss": 0.6848027110099792,
|
| 27 |
+
"eval_mcc": 0.17256712249065836,
|
| 28 |
+
"eval_runtime": 0.096,
|
| 29 |
+
"eval_samples_per_second": 541.411,
|
| 30 |
+
"eval_steps_per_second": 72.882,
|
| 31 |
+
"step": 140
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"logging_steps": 500,
|
| 35 |
+
"max_steps": 1400,
|
| 36 |
+
"num_input_tokens_seen": 0,
|
| 37 |
+
"num_train_epochs": 20,
|
| 38 |
+
"save_steps": 500,
|
| 39 |
+
"stateful_callbacks": {
|
| 40 |
+
"EarlyStoppingCallback": {
|
| 41 |
+
"args": {
|
| 42 |
+
"early_stopping_patience": 3,
|
| 43 |
+
"early_stopping_threshold": 0.001
|
| 44 |
+
},
|
| 45 |
+
"attributes": {
|
| 46 |
+
"early_stopping_patience_counter": 0
|
| 47 |
+
}
|
| 48 |
+
},
|
| 49 |
+
"TrainerControl": {
|
| 50 |
+
"args": {
|
| 51 |
+
"should_epoch_stop": false,
|
| 52 |
+
"should_evaluate": false,
|
| 53 |
+
"should_log": false,
|
| 54 |
+
"should_save": true,
|
| 55 |
+
"should_training_stop": false
|
| 56 |
+
},
|
| 57 |
+
"attributes": {}
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"total_flos": 65369494253568.0,
|
| 61 |
+
"train_batch_size": 8,
|
| 62 |
+
"trial_name": null,
|
| 63 |
+
"trial_params": null
|
| 64 |
+
}
|
checkpoint-140/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d0fbc45d3adb0d70b538cfee67e5365bd5c29a4be56d5a6c0bc6f25d0772611
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/ubuntu/utah/babylm-24/data/training/models/10M_babylm_ascii/SPM-Unigram_6144/DebertaV2-Base-10M_babylm-A",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 1536,
|
| 12 |
+
"label2id": {
|
| 13 |
+
"0": 0,
|
| 14 |
+
"1": 1
|
| 15 |
+
},
|
| 16 |
+
"layer_norm_eps": 1e-07,
|
| 17 |
+
"max_position_embeddings": 512,
|
| 18 |
+
"max_relative_positions": -1,
|
| 19 |
+
"model_type": "deberta-v2",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 8,
|
| 22 |
+
"pad_token_id": 3,
|
| 23 |
+
"pooler_dropout": 0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": null,
|
| 27 |
+
"position_biased_input": true,
|
| 28 |
+
"relative_attention": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.44.2",
|
| 31 |
+
"type_vocab_size": 0,
|
| 32 |
+
"vocab_size": 6144
|
| 33 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.6153846383094788,
|
| 4 |
+
"eval_f1": 0.47368421052631576,
|
| 5 |
+
"eval_loss": 0.6848027110099792,
|
| 6 |
+
"eval_mcc": 0.17256712249065836,
|
| 7 |
+
"eval_runtime": 0.1138,
|
| 8 |
+
"eval_samples": 52,
|
| 9 |
+
"eval_samples_per_second": 456.859,
|
| 10 |
+
"eval_steps_per_second": 61.5
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4be62a77ab9dedd098777ad54755f3a8d9eb3e26d6b7474ff9b99866cc9718c
|
| 3 |
+
size 174103504
|
predictions.txt
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
index prediction
|
| 2 |
+
0 1
|
| 3 |
+
1 0
|
| 4 |
+
2 0
|
| 5 |
+
3 0
|
| 6 |
+
4 1
|
| 7 |
+
5 0
|
| 8 |
+
6 0
|
| 9 |
+
7 1
|
| 10 |
+
8 0
|
| 11 |
+
9 0
|
| 12 |
+
10 1
|
| 13 |
+
11 1
|
| 14 |
+
12 0
|
| 15 |
+
13 1
|
| 16 |
+
14 0
|
| 17 |
+
15 1
|
| 18 |
+
16 1
|
| 19 |
+
17 0
|
| 20 |
+
18 0
|
| 21 |
+
19 0
|
| 22 |
+
20 0
|
| 23 |
+
21 0
|
| 24 |
+
22 1
|
| 25 |
+
23 0
|
| 26 |
+
24 1
|
| 27 |
+
25 0
|
| 28 |
+
26 1
|
| 29 |
+
27 0
|
| 30 |
+
28 0
|
| 31 |
+
29 0
|
| 32 |
+
30 1
|
| 33 |
+
31 1
|
| 34 |
+
32 0
|
| 35 |
+
33 0
|
| 36 |
+
34 1
|
| 37 |
+
35 1
|
| 38 |
+
36 0
|
| 39 |
+
37 0
|
| 40 |
+
38 1
|
| 41 |
+
39 1
|
| 42 |
+
40 0
|
| 43 |
+
41 0
|
| 44 |
+
42 0
|
| 45 |
+
43 0
|
| 46 |
+
44 0
|
| 47 |
+
45 0
|
| 48 |
+
46 0
|
| 49 |
+
47 1
|
| 50 |
+
48 0
|
| 51 |
+
49 0
|
| 52 |
+
50 0
|
| 53 |
+
51 0
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "[PAR]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "[TAB]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"clean_up_tokenization_spaces": false,
|
| 61 |
+
"cls_token": "[CLS]",
|
| 62 |
+
"mask_token": "[MASK]",
|
| 63 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 64 |
+
"pad_token": "[PAD]",
|
| 65 |
+
"sep_token": "[SEP]",
|
| 66 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 67 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 163423735633920.0,
|
| 4 |
+
"train_loss": 0.7042514474051339,
|
| 5 |
+
"train_runtime": 33.2199,
|
| 6 |
+
"train_samples": 554,
|
| 7 |
+
"train_samples_per_second": 333.536,
|
| 8 |
+
"train_steps_per_second": 42.143
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.47368421052631576,
|
| 3 |
+
"best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/wsc/checkpoint-140",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 350,
|
| 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": 0.6153846383094788,
|
| 14 |
+
"eval_f1": 0.0,
|
| 15 |
+
"eval_loss": 0.6650720834732056,
|
| 16 |
+
"eval_mcc": 0.0,
|
| 17 |
+
"eval_runtime": 0.1205,
|
| 18 |
+
"eval_samples_per_second": 431.51,
|
| 19 |
+
"eval_steps_per_second": 58.088,
|
| 20 |
+
"step": 70
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.0,
|
| 24 |
+
"eval_accuracy": 0.6153846383094788,
|
| 25 |
+
"eval_f1": 0.47368421052631576,
|
| 26 |
+
"eval_loss": 0.6848027110099792,
|
| 27 |
+
"eval_mcc": 0.17256712249065836,
|
| 28 |
+
"eval_runtime": 0.096,
|
| 29 |
+
"eval_samples_per_second": 541.411,
|
| 30 |
+
"eval_steps_per_second": 72.882,
|
| 31 |
+
"step": 140
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.0,
|
| 35 |
+
"eval_accuracy": 0.5961538553237915,
|
| 36 |
+
"eval_f1": 0.16,
|
| 37 |
+
"eval_loss": 0.6839962005615234,
|
| 38 |
+
"eval_mcc": 0.010314212462587935,
|
| 39 |
+
"eval_runtime": 0.0965,
|
| 40 |
+
"eval_samples_per_second": 539.131,
|
| 41 |
+
"eval_steps_per_second": 72.575,
|
| 42 |
+
"step": 210
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_accuracy": 0.6153846383094788,
|
| 47 |
+
"eval_f1": 0.0,
|
| 48 |
+
"eval_loss": 0.6632354259490967,
|
| 49 |
+
"eval_mcc": 0.0,
|
| 50 |
+
"eval_runtime": 0.0974,
|
| 51 |
+
"eval_samples_per_second": 533.999,
|
| 52 |
+
"eval_steps_per_second": 71.884,
|
| 53 |
+
"step": 280
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.0,
|
| 57 |
+
"eval_accuracy": 0.6153846383094788,
|
| 58 |
+
"eval_f1": 0.0,
|
| 59 |
+
"eval_loss": 0.6646058559417725,
|
| 60 |
+
"eval_mcc": 0.0,
|
| 61 |
+
"eval_runtime": 0.0979,
|
| 62 |
+
"eval_samples_per_second": 530.989,
|
| 63 |
+
"eval_steps_per_second": 71.479,
|
| 64 |
+
"step": 350
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"step": 350,
|
| 69 |
+
"total_flos": 163423735633920.0,
|
| 70 |
+
"train_loss": 0.7042514474051339,
|
| 71 |
+
"train_runtime": 33.2199,
|
| 72 |
+
"train_samples_per_second": 333.536,
|
| 73 |
+
"train_steps_per_second": 42.143
|
| 74 |
+
}
|
| 75 |
+
],
|
| 76 |
+
"logging_steps": 500,
|
| 77 |
+
"max_steps": 1400,
|
| 78 |
+
"num_input_tokens_seen": 0,
|
| 79 |
+
"num_train_epochs": 20,
|
| 80 |
+
"save_steps": 500,
|
| 81 |
+
"stateful_callbacks": {
|
| 82 |
+
"EarlyStoppingCallback": {
|
| 83 |
+
"args": {
|
| 84 |
+
"early_stopping_patience": 3,
|
| 85 |
+
"early_stopping_threshold": 0.001
|
| 86 |
+
},
|
| 87 |
+
"attributes": {
|
| 88 |
+
"early_stopping_patience_counter": 0
|
| 89 |
+
}
|
| 90 |
+
},
|
| 91 |
+
"TrainerControl": {
|
| 92 |
+
"args": {
|
| 93 |
+
"should_epoch_stop": false,
|
| 94 |
+
"should_evaluate": false,
|
| 95 |
+
"should_log": false,
|
| 96 |
+
"should_save": true,
|
| 97 |
+
"should_training_stop": true
|
| 98 |
+
},
|
| 99 |
+
"attributes": {}
|
| 100 |
+
}
|
| 101 |
+
},
|
| 102 |
+
"total_flos": 163423735633920.0,
|
| 103 |
+
"train_batch_size": 8,
|
| 104 |
+
"trial_name": null,
|
| 105 |
+
"trial_params": null
|
| 106 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d0fbc45d3adb0d70b538cfee67e5365bd5c29a4be56d5a6c0bc6f25d0772611
|
| 3 |
+
size 5368
|