Upload folder using huggingface_hub
Browse files- all_results.json +17 -0
- checkpoint-312/config.json +33 -0
- checkpoint-312/model.safetensors +3 -0
- checkpoint-312/optimizer.pt +3 -0
- checkpoint-312/rng_state.pth +3 -0
- checkpoint-312/scheduler.pt +3 -0
- checkpoint-312/special_tokens_map.json +30 -0
- checkpoint-312/tokenizer.json +0 -0
- checkpoint-312/tokenizer_config.json +67 -0
- checkpoint-312/trainer_state.json +53 -0
- checkpoint-312/training_args.bin +3 -0
- config.json +33 -0
- eval_results.json +11 -0
- model.safetensors +3 -0
- predictions.txt +140 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +67 -0
- train_results.json +9 -0
- trainer_state.json +109 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.5179855823516846,
|
| 4 |
+
"eval_f1": 0.6127167630057804,
|
| 5 |
+
"eval_loss": 0.6988222599029541,
|
| 6 |
+
"eval_mcc": 0.09869207097117276,
|
| 7 |
+
"eval_runtime": 0.257,
|
| 8 |
+
"eval_samples": 139,
|
| 9 |
+
"eval_samples_per_second": 540.852,
|
| 10 |
+
"eval_steps_per_second": 70.038,
|
| 11 |
+
"total_flos": 587617475420160.0,
|
| 12 |
+
"train_loss": 0.5243261960836557,
|
| 13 |
+
"train_runtime": 82.8963,
|
| 14 |
+
"train_samples": 2490,
|
| 15 |
+
"train_samples_per_second": 600.751,
|
| 16 |
+
"train_steps_per_second": 75.275
|
| 17 |
+
}
|
checkpoint-312/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-312/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1903e0b3bec7906948786c7724b47a7361ad86bfd8e4fe5b914d254342ebb413
|
| 3 |
+
size 174103504
|
checkpoint-312/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:307c551d490a088f10492ad9e224d0fe702b090e654a844de6a361fbd1086b4d
|
| 3 |
+
size 348288250
|
checkpoint-312/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feeb7ed71196744e1340d4d4adb484f14f6b41af20fccdd9e9c15c9f0f9ad88f
|
| 3 |
+
size 14244
|
checkpoint-312/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6175e59510c6b0293bd93d0ede49b65bf27a38ddbf9738854a6ada0b7f5e0d86
|
| 3 |
+
size 1064
|
checkpoint-312/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-312/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-312/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-312/trainer_state.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6127167630057804,
|
| 3 |
+
"best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/rte/checkpoint-312",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 312,
|
| 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": 0.5179855823516846,
|
| 14 |
+
"eval_f1": 0.6127167630057804,
|
| 15 |
+
"eval_loss": 0.6988222599029541,
|
| 16 |
+
"eval_mcc": 0.09869207097117276,
|
| 17 |
+
"eval_runtime": 0.2603,
|
| 18 |
+
"eval_samples_per_second": 534.027,
|
| 19 |
+
"eval_steps_per_second": 69.155,
|
| 20 |
+
"step": 312
|
| 21 |
+
}
|
| 22 |
+
],
|
| 23 |
+
"logging_steps": 500,
|
| 24 |
+
"max_steps": 6240,
|
| 25 |
+
"num_input_tokens_seen": 0,
|
| 26 |
+
"num_train_epochs": 20,
|
| 27 |
+
"save_steps": 500,
|
| 28 |
+
"stateful_callbacks": {
|
| 29 |
+
"EarlyStoppingCallback": {
|
| 30 |
+
"args": {
|
| 31 |
+
"early_stopping_patience": 3,
|
| 32 |
+
"early_stopping_threshold": 0.001
|
| 33 |
+
},
|
| 34 |
+
"attributes": {
|
| 35 |
+
"early_stopping_patience_counter": 0
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"TrainerControl": {
|
| 39 |
+
"args": {
|
| 40 |
+
"should_epoch_stop": false,
|
| 41 |
+
"should_evaluate": false,
|
| 42 |
+
"should_log": false,
|
| 43 |
+
"should_save": true,
|
| 44 |
+
"should_training_stop": false
|
| 45 |
+
},
|
| 46 |
+
"attributes": {}
|
| 47 |
+
}
|
| 48 |
+
},
|
| 49 |
+
"total_flos": 146904368855040.0,
|
| 50 |
+
"train_batch_size": 8,
|
| 51 |
+
"trial_name": null,
|
| 52 |
+
"trial_params": null
|
| 53 |
+
}
|
checkpoint-312/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81de75fec8e9df0468cf7d13e4ddf920d0e2af32c69cde8ff0341b09bc00d3d8
|
| 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": 4.0,
|
| 3 |
+
"eval_accuracy": 0.5179855823516846,
|
| 4 |
+
"eval_f1": 0.6127167630057804,
|
| 5 |
+
"eval_loss": 0.6988222599029541,
|
| 6 |
+
"eval_mcc": 0.09869207097117276,
|
| 7 |
+
"eval_runtime": 0.257,
|
| 8 |
+
"eval_samples": 139,
|
| 9 |
+
"eval_samples_per_second": 540.852,
|
| 10 |
+
"eval_steps_per_second": 70.038
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1903e0b3bec7906948786c7724b47a7361ad86bfd8e4fe5b914d254342ebb413
|
| 3 |
+
size 174103504
|
predictions.txt
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
index prediction
|
| 2 |
+
0 1
|
| 3 |
+
1 1
|
| 4 |
+
2 0
|
| 5 |
+
3 1
|
| 6 |
+
4 1
|
| 7 |
+
5 1
|
| 8 |
+
6 1
|
| 9 |
+
7 1
|
| 10 |
+
8 1
|
| 11 |
+
9 1
|
| 12 |
+
10 1
|
| 13 |
+
11 1
|
| 14 |
+
12 1
|
| 15 |
+
13 0
|
| 16 |
+
14 0
|
| 17 |
+
15 1
|
| 18 |
+
16 0
|
| 19 |
+
17 1
|
| 20 |
+
18 1
|
| 21 |
+
19 0
|
| 22 |
+
20 0
|
| 23 |
+
21 1
|
| 24 |
+
22 0
|
| 25 |
+
23 1
|
| 26 |
+
24 1
|
| 27 |
+
25 0
|
| 28 |
+
26 1
|
| 29 |
+
27 1
|
| 30 |
+
28 1
|
| 31 |
+
29 0
|
| 32 |
+
30 1
|
| 33 |
+
31 0
|
| 34 |
+
32 0
|
| 35 |
+
33 0
|
| 36 |
+
34 0
|
| 37 |
+
35 1
|
| 38 |
+
36 1
|
| 39 |
+
37 1
|
| 40 |
+
38 1
|
| 41 |
+
39 0
|
| 42 |
+
40 1
|
| 43 |
+
41 1
|
| 44 |
+
42 0
|
| 45 |
+
43 1
|
| 46 |
+
44 0
|
| 47 |
+
45 0
|
| 48 |
+
46 1
|
| 49 |
+
47 1
|
| 50 |
+
48 1
|
| 51 |
+
49 1
|
| 52 |
+
50 1
|
| 53 |
+
51 1
|
| 54 |
+
52 1
|
| 55 |
+
53 0
|
| 56 |
+
54 1
|
| 57 |
+
55 1
|
| 58 |
+
56 1
|
| 59 |
+
57 1
|
| 60 |
+
58 1
|
| 61 |
+
59 1
|
| 62 |
+
60 1
|
| 63 |
+
61 0
|
| 64 |
+
62 1
|
| 65 |
+
63 1
|
| 66 |
+
64 1
|
| 67 |
+
65 1
|
| 68 |
+
66 1
|
| 69 |
+
67 1
|
| 70 |
+
68 1
|
| 71 |
+
69 0
|
| 72 |
+
70 1
|
| 73 |
+
71 1
|
| 74 |
+
72 1
|
| 75 |
+
73 1
|
| 76 |
+
74 1
|
| 77 |
+
75 1
|
| 78 |
+
76 1
|
| 79 |
+
77 1
|
| 80 |
+
78 1
|
| 81 |
+
79 1
|
| 82 |
+
80 1
|
| 83 |
+
81 1
|
| 84 |
+
82 1
|
| 85 |
+
83 1
|
| 86 |
+
84 1
|
| 87 |
+
85 1
|
| 88 |
+
86 1
|
| 89 |
+
87 1
|
| 90 |
+
88 1
|
| 91 |
+
89 1
|
| 92 |
+
90 0
|
| 93 |
+
91 1
|
| 94 |
+
92 1
|
| 95 |
+
93 0
|
| 96 |
+
94 0
|
| 97 |
+
95 1
|
| 98 |
+
96 1
|
| 99 |
+
97 1
|
| 100 |
+
98 0
|
| 101 |
+
99 1
|
| 102 |
+
100 0
|
| 103 |
+
101 1
|
| 104 |
+
102 1
|
| 105 |
+
103 1
|
| 106 |
+
104 1
|
| 107 |
+
105 1
|
| 108 |
+
106 1
|
| 109 |
+
107 1
|
| 110 |
+
108 1
|
| 111 |
+
109 1
|
| 112 |
+
110 1
|
| 113 |
+
111 1
|
| 114 |
+
112 0
|
| 115 |
+
113 1
|
| 116 |
+
114 1
|
| 117 |
+
115 1
|
| 118 |
+
116 1
|
| 119 |
+
117 1
|
| 120 |
+
118 1
|
| 121 |
+
119 0
|
| 122 |
+
120 1
|
| 123 |
+
121 1
|
| 124 |
+
122 0
|
| 125 |
+
123 1
|
| 126 |
+
124 0
|
| 127 |
+
125 1
|
| 128 |
+
126 1
|
| 129 |
+
127 1
|
| 130 |
+
128 1
|
| 131 |
+
129 1
|
| 132 |
+
130 1
|
| 133 |
+
131 1
|
| 134 |
+
132 1
|
| 135 |
+
133 1
|
| 136 |
+
134 1
|
| 137 |
+
135 0
|
| 138 |
+
136 1
|
| 139 |
+
137 1
|
| 140 |
+
138 1
|
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": 4.0,
|
| 3 |
+
"total_flos": 587617475420160.0,
|
| 4 |
+
"train_loss": 0.5243261960836557,
|
| 5 |
+
"train_runtime": 82.8963,
|
| 6 |
+
"train_samples": 2490,
|
| 7 |
+
"train_samples_per_second": 600.751,
|
| 8 |
+
"train_steps_per_second": 75.275
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6127167630057804,
|
| 3 |
+
"best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/rte/checkpoint-312",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1248,
|
| 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": 0.5179855823516846,
|
| 14 |
+
"eval_f1": 0.6127167630057804,
|
| 15 |
+
"eval_loss": 0.6988222599029541,
|
| 16 |
+
"eval_mcc": 0.09869207097117276,
|
| 17 |
+
"eval_runtime": 0.2603,
|
| 18 |
+
"eval_samples_per_second": 534.027,
|
| 19 |
+
"eval_steps_per_second": 69.155,
|
| 20 |
+
"step": 312
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.6025641025641026,
|
| 24 |
+
"grad_norm": 2.8960421085357666,
|
| 25 |
+
"learning_rate": 2.7596153846153846e-05,
|
| 26 |
+
"loss": 0.6829,
|
| 27 |
+
"step": 500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"eval_accuracy": 0.5899280309677124,
|
| 32 |
+
"eval_f1": 0.4864864864864865,
|
| 33 |
+
"eval_loss": 0.6877012848854065,
|
| 34 |
+
"eval_mcc": 0.1635282583804096,
|
| 35 |
+
"eval_runtime": 0.2394,
|
| 36 |
+
"eval_samples_per_second": 580.645,
|
| 37 |
+
"eval_steps_per_second": 75.191,
|
| 38 |
+
"step": 624
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_accuracy": 0.46043166518211365,
|
| 43 |
+
"eval_f1": 0.5714285714285714,
|
| 44 |
+
"eval_loss": 1.203949213027954,
|
| 45 |
+
"eval_mcc": -0.03987122665174367,
|
| 46 |
+
"eval_runtime": 0.2479,
|
| 47 |
+
"eval_samples_per_second": 560.646,
|
| 48 |
+
"eval_steps_per_second": 72.602,
|
| 49 |
+
"step": 936
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.2051282051282053,
|
| 53 |
+
"grad_norm": 10.899106979370117,
|
| 54 |
+
"learning_rate": 2.5192307692307694e-05,
|
| 55 |
+
"loss": 0.4839,
|
| 56 |
+
"step": 1000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_accuracy": 0.49640288949012756,
|
| 61 |
+
"eval_f1": 0.5454545454545454,
|
| 62 |
+
"eval_loss": 1.811629295349121,
|
| 63 |
+
"eval_mcc": 0.016953317256112287,
|
| 64 |
+
"eval_runtime": 0.2418,
|
| 65 |
+
"eval_samples_per_second": 574.756,
|
| 66 |
+
"eval_steps_per_second": 74.429,
|
| 67 |
+
"step": 1248
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 4.0,
|
| 71 |
+
"step": 1248,
|
| 72 |
+
"total_flos": 587617475420160.0,
|
| 73 |
+
"train_loss": 0.5243261960836557,
|
| 74 |
+
"train_runtime": 82.8963,
|
| 75 |
+
"train_samples_per_second": 600.751,
|
| 76 |
+
"train_steps_per_second": 75.275
|
| 77 |
+
}
|
| 78 |
+
],
|
| 79 |
+
"logging_steps": 500,
|
| 80 |
+
"max_steps": 6240,
|
| 81 |
+
"num_input_tokens_seen": 0,
|
| 82 |
+
"num_train_epochs": 20,
|
| 83 |
+
"save_steps": 500,
|
| 84 |
+
"stateful_callbacks": {
|
| 85 |
+
"EarlyStoppingCallback": {
|
| 86 |
+
"args": {
|
| 87 |
+
"early_stopping_patience": 3,
|
| 88 |
+
"early_stopping_threshold": 0.001
|
| 89 |
+
},
|
| 90 |
+
"attributes": {
|
| 91 |
+
"early_stopping_patience_counter": 0
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
"TrainerControl": {
|
| 95 |
+
"args": {
|
| 96 |
+
"should_epoch_stop": false,
|
| 97 |
+
"should_evaluate": false,
|
| 98 |
+
"should_log": false,
|
| 99 |
+
"should_save": true,
|
| 100 |
+
"should_training_stop": true
|
| 101 |
+
},
|
| 102 |
+
"attributes": {}
|
| 103 |
+
}
|
| 104 |
+
},
|
| 105 |
+
"total_flos": 587617475420160.0,
|
| 106 |
+
"train_batch_size": 8,
|
| 107 |
+
"trial_name": null,
|
| 108 |
+
"trial_params": null
|
| 109 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81de75fec8e9df0468cf7d13e4ddf920d0e2af32c69cde8ff0341b09bc00d3d8
|
| 3 |
+
size 5368
|