Upload 18 files
Browse files- patentsberta_green_ft/checkpoint-2188/config.json +26 -0
- patentsberta_green_ft/checkpoint-2188/model.safetensors +3 -0
- patentsberta_green_ft/checkpoint-2188/optimizer.pt +3 -0
- patentsberta_green_ft/checkpoint-2188/rng_state.pth +3 -0
- patentsberta_green_ft/checkpoint-2188/scaler.pt +3 -0
- patentsberta_green_ft/checkpoint-2188/scheduler.pt +3 -0
- patentsberta_green_ft/checkpoint-2188/special_tokens_map.json +51 -0
- patentsberta_green_ft/checkpoint-2188/tokenizer.json +0 -0
- patentsberta_green_ft/checkpoint-2188/tokenizer_config.json +16 -0
- patentsberta_green_ft/checkpoint-2188/trainer_state.json +347 -0
- patentsberta_green_ft/checkpoint-2188/training_args.bin +3 -0
- patentsberta_green_ft/checkpoint-2188/vocab.txt +0 -0
- patentsberta_green_ft/config.json +26 -0
- patentsberta_green_ft/model.safetensors +3 -0
- patentsberta_green_ft/special_tokens_map.json +51 -0
- patentsberta_green_ft/tokenizer.json +0 -0
- patentsberta_green_ft/tokenizer_config.json +16 -0
- patentsberta_green_ft/vocab.txt +0 -0
patentsberta_green_ft/checkpoint-2188/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MPNetForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "mpnet",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"relative_attention_num_buckets": 32,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"transformers_version": "5.2.0",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 30527
|
| 26 |
+
}
|
patentsberta_green_ft/checkpoint-2188/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc00b66b1350d1f8663d63795ddaa31df0ad6cbebac366f7e055e9c566f92b94
|
| 3 |
+
size 437975176
|
patentsberta_green_ft/checkpoint-2188/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7dff92d6a4c3f524042c598db2cfeec96bfea7a94aa6f33307318819d67d005
|
| 3 |
+
size 876075403
|
patentsberta_green_ft/checkpoint-2188/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c71c767e6d13c4cf739b90c205b0d926fc2d192d5883a06145ba633211ef37c
|
| 3 |
+
size 14645
|
patentsberta_green_ft/checkpoint-2188/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b47b7500346b52ebe4d65e72241929f2c2e083e8f71cd1ab044cfcd2c8d3447
|
| 3 |
+
size 1383
|
patentsberta_green_ft/checkpoint-2188/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed2b9f21a4594ec5f1a7c0c98d4ee49f8bb7789fbc9b3cce6505b7d8b83a0bd8
|
| 3 |
+
size 1465
|
patentsberta_green_ft/checkpoint-2188/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
patentsberta_green_ft/checkpoint-2188/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
patentsberta_green_ft/checkpoint-2188/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
patentsberta_green_ft/checkpoint-2188/trainer_state.json
ADDED
|
@@ -0,0 +1,347 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2188,
|
| 3 |
+
"best_metric": 0.3945621848106384,
|
| 4 |
+
"best_model_checkpoint": "patentsberta_green_ft/checkpoint-2188",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2188,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.022851919561243144,
|
| 14 |
+
"grad_norm": 3.387232780456543,
|
| 15 |
+
"learning_rate": 1.9552102376599635e-05,
|
| 16 |
+
"loss": 0.6226611328125,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04570383912248629,
|
| 21 |
+
"grad_norm": 1.879778265953064,
|
| 22 |
+
"learning_rate": 1.9095063985374774e-05,
|
| 23 |
+
"loss": 0.5442704010009766,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06855575868372943,
|
| 28 |
+
"grad_norm": 1.9388929605484009,
|
| 29 |
+
"learning_rate": 1.863802559414991e-05,
|
| 30 |
+
"loss": 0.5037535095214843,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09140767824497258,
|
| 35 |
+
"grad_norm": 4.263214588165283,
|
| 36 |
+
"learning_rate": 1.8180987202925047e-05,
|
| 37 |
+
"loss": 0.5054629898071289,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11425959780621572,
|
| 42 |
+
"grad_norm": 5.635115146636963,
|
| 43 |
+
"learning_rate": 1.7723948811700184e-05,
|
| 44 |
+
"loss": 0.49037540435791016,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13711151736745886,
|
| 49 |
+
"grad_norm": 3.149095058441162,
|
| 50 |
+
"learning_rate": 1.7266910420475323e-05,
|
| 51 |
+
"loss": 0.49361869812011716,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.15996343692870202,
|
| 56 |
+
"grad_norm": 3.4925954341888428,
|
| 57 |
+
"learning_rate": 1.6809872029250456e-05,
|
| 58 |
+
"loss": 0.45195068359375,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.18281535648994515,
|
| 63 |
+
"grad_norm": 2.773059844970703,
|
| 64 |
+
"learning_rate": 1.6352833638025596e-05,
|
| 65 |
+
"loss": 0.4709346771240234,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2056672760511883,
|
| 70 |
+
"grad_norm": 3.7442731857299805,
|
| 71 |
+
"learning_rate": 1.5895795246800733e-05,
|
| 72 |
+
"loss": 0.46303668975830076,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.22851919561243145,
|
| 77 |
+
"grad_norm": 1.752357006072998,
|
| 78 |
+
"learning_rate": 1.543875685557587e-05,
|
| 79 |
+
"loss": 0.46448593139648436,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2513711151736746,
|
| 84 |
+
"grad_norm": 4.759559154510498,
|
| 85 |
+
"learning_rate": 1.4981718464351007e-05,
|
| 86 |
+
"loss": 0.4524075698852539,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.2742230347349177,
|
| 91 |
+
"grad_norm": 4.357444763183594,
|
| 92 |
+
"learning_rate": 1.4524680073126144e-05,
|
| 93 |
+
"loss": 0.4454657745361328,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2970749542961609,
|
| 98 |
+
"grad_norm": 2.421372175216675,
|
| 99 |
+
"learning_rate": 1.406764168190128e-05,
|
| 100 |
+
"loss": 0.4586004638671875,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.31992687385740404,
|
| 105 |
+
"grad_norm": 2.279892921447754,
|
| 106 |
+
"learning_rate": 1.3610603290676418e-05,
|
| 107 |
+
"loss": 0.5000552368164063,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.34277879341864714,
|
| 112 |
+
"grad_norm": 2.7829952239990234,
|
| 113 |
+
"learning_rate": 1.3153564899451555e-05,
|
| 114 |
+
"loss": 0.45607608795166016,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3656307129798903,
|
| 119 |
+
"grad_norm": 1.878724217414856,
|
| 120 |
+
"learning_rate": 1.2696526508226693e-05,
|
| 121 |
+
"loss": 0.47104820251464846,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.38848263254113347,
|
| 126 |
+
"grad_norm": 5.223470211029053,
|
| 127 |
+
"learning_rate": 1.2239488117001829e-05,
|
| 128 |
+
"loss": 0.4357754135131836,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4113345521023766,
|
| 133 |
+
"grad_norm": 4.424527168273926,
|
| 134 |
+
"learning_rate": 1.1782449725776965e-05,
|
| 135 |
+
"loss": 0.40907974243164064,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.43418647166361973,
|
| 140 |
+
"grad_norm": 2.798241376876831,
|
| 141 |
+
"learning_rate": 1.1325411334552104e-05,
|
| 142 |
+
"loss": 0.4346627426147461,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4570383912248629,
|
| 147 |
+
"grad_norm": 5.228867530822754,
|
| 148 |
+
"learning_rate": 1.0868372943327242e-05,
|
| 149 |
+
"loss": 0.4466738510131836,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.47989031078610606,
|
| 154 |
+
"grad_norm": 3.639314651489258,
|
| 155 |
+
"learning_rate": 1.0411334552102376e-05,
|
| 156 |
+
"loss": 0.4898922729492188,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5027422303473492,
|
| 161 |
+
"grad_norm": 4.599398136138916,
|
| 162 |
+
"learning_rate": 9.954296160877514e-06,
|
| 163 |
+
"loss": 0.4627768325805664,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5255941499085923,
|
| 168 |
+
"grad_norm": 2.93489146232605,
|
| 169 |
+
"learning_rate": 9.497257769652651e-06,
|
| 170 |
+
"loss": 0.4082163238525391,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5484460694698354,
|
| 175 |
+
"grad_norm": 2.580263376235962,
|
| 176 |
+
"learning_rate": 9.040219378427789e-06,
|
| 177 |
+
"loss": 0.4768526077270508,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5712979890310786,
|
| 182 |
+
"grad_norm": 5.402170658111572,
|
| 183 |
+
"learning_rate": 8.583180987202925e-06,
|
| 184 |
+
"loss": 0.39115142822265625,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5941499085923218,
|
| 189 |
+
"grad_norm": 5.495348930358887,
|
| 190 |
+
"learning_rate": 8.126142595978063e-06,
|
| 191 |
+
"loss": 0.40422657012939456,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6170018281535649,
|
| 196 |
+
"grad_norm": 3.5335493087768555,
|
| 197 |
+
"learning_rate": 7.6691042047532e-06,
|
| 198 |
+
"loss": 0.443400993347168,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6398537477148081,
|
| 203 |
+
"grad_norm": 4.166231632232666,
|
| 204 |
+
"learning_rate": 7.212065813528337e-06,
|
| 205 |
+
"loss": 0.44326675415039063,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6627056672760512,
|
| 210 |
+
"grad_norm": 4.153471946716309,
|
| 211 |
+
"learning_rate": 6.7550274223034736e-06,
|
| 212 |
+
"loss": 0.4378884506225586,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6855575868372943,
|
| 217 |
+
"grad_norm": 7.0348801612854,
|
| 218 |
+
"learning_rate": 6.297989031078611e-06,
|
| 219 |
+
"loss": 0.40130287170410156,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.7084095063985375,
|
| 224 |
+
"grad_norm": 2.4332053661346436,
|
| 225 |
+
"learning_rate": 5.840950639853749e-06,
|
| 226 |
+
"loss": 0.4363275146484375,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7312614259597806,
|
| 231 |
+
"grad_norm": 3.8347222805023193,
|
| 232 |
+
"learning_rate": 5.383912248628885e-06,
|
| 233 |
+
"loss": 0.48528797149658204,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.7541133455210237,
|
| 238 |
+
"grad_norm": 5.028531551361084,
|
| 239 |
+
"learning_rate": 4.9268738574040226e-06,
|
| 240 |
+
"loss": 0.40475738525390625,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7769652650822669,
|
| 245 |
+
"grad_norm": 5.7849249839782715,
|
| 246 |
+
"learning_rate": 4.469835466179159e-06,
|
| 247 |
+
"loss": 0.4265980911254883,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.79981718464351,
|
| 252 |
+
"grad_norm": 4.249039649963379,
|
| 253 |
+
"learning_rate": 4.012797074954296e-06,
|
| 254 |
+
"loss": 0.42519081115722657,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8226691042047533,
|
| 259 |
+
"grad_norm": 3.1753153800964355,
|
| 260 |
+
"learning_rate": 3.5557586837294335e-06,
|
| 261 |
+
"loss": 0.4285478210449219,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.8455210237659964,
|
| 266 |
+
"grad_norm": 5.429496765136719,
|
| 267 |
+
"learning_rate": 3.0987202925045707e-06,
|
| 268 |
+
"loss": 0.4121986389160156,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8683729433272395,
|
| 273 |
+
"grad_norm": 4.798526763916016,
|
| 274 |
+
"learning_rate": 2.641681901279708e-06,
|
| 275 |
+
"loss": 0.43618728637695314,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.8912248628884827,
|
| 280 |
+
"grad_norm": 5.206924915313721,
|
| 281 |
+
"learning_rate": 2.184643510054845e-06,
|
| 282 |
+
"loss": 0.41448020935058594,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9140767824497258,
|
| 287 |
+
"grad_norm": 2.6320886611938477,
|
| 288 |
+
"learning_rate": 1.7276051188299819e-06,
|
| 289 |
+
"loss": 0.42696685791015626,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.9369287020109689,
|
| 294 |
+
"grad_norm": 3.3105645179748535,
|
| 295 |
+
"learning_rate": 1.270566727605119e-06,
|
| 296 |
+
"loss": 0.4143737030029297,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.9597806215722121,
|
| 301 |
+
"grad_norm": 1.9642584323883057,
|
| 302 |
+
"learning_rate": 8.13528336380256e-07,
|
| 303 |
+
"loss": 0.44643726348876955,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9826325411334552,
|
| 308 |
+
"grad_norm": 2.8586716651916504,
|
| 309 |
+
"learning_rate": 3.5648994515539306e-07,
|
| 310 |
+
"loss": 0.4438472366333008,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0,
|
| 315 |
+
"eval_accuracy": 0.8197333333333333,
|
| 316 |
+
"eval_f1": 0.8152500683246788,
|
| 317 |
+
"eval_loss": 0.3945621848106384,
|
| 318 |
+
"eval_precision": 0.83417225950783,
|
| 319 |
+
"eval_recall": 0.7971672902191341,
|
| 320 |
+
"eval_runtime": 36.2612,
|
| 321 |
+
"eval_samples_per_second": 206.833,
|
| 322 |
+
"eval_steps_per_second": 6.481,
|
| 323 |
+
"step": 2188
|
| 324 |
+
}
|
| 325 |
+
],
|
| 326 |
+
"logging_steps": 50,
|
| 327 |
+
"max_steps": 2188,
|
| 328 |
+
"num_input_tokens_seen": 0,
|
| 329 |
+
"num_train_epochs": 1,
|
| 330 |
+
"save_steps": 500,
|
| 331 |
+
"stateful_callbacks": {
|
| 332 |
+
"TrainerControl": {
|
| 333 |
+
"args": {
|
| 334 |
+
"should_epoch_stop": false,
|
| 335 |
+
"should_evaluate": false,
|
| 336 |
+
"should_log": false,
|
| 337 |
+
"should_save": true,
|
| 338 |
+
"should_training_stop": true
|
| 339 |
+
},
|
| 340 |
+
"attributes": {}
|
| 341 |
+
}
|
| 342 |
+
},
|
| 343 |
+
"total_flos": 4600842136229760.0,
|
| 344 |
+
"train_batch_size": 16,
|
| 345 |
+
"trial_name": null,
|
| 346 |
+
"trial_params": null
|
| 347 |
+
}
|
patentsberta_green_ft/checkpoint-2188/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30eb8a6285d4dc9867cc5a28e888b6fe21283511d6dbf0b2171dd7ac375e9775
|
| 3 |
+
size 5201
|
patentsberta_green_ft/checkpoint-2188/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
patentsberta_green_ft/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MPNetForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "mpnet",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"relative_attention_num_buckets": 32,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"transformers_version": "5.2.0",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 30527
|
| 26 |
+
}
|
patentsberta_green_ft/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc00b66b1350d1f8663d63795ddaa31df0ad6cbebac366f7e055e9c566f92b94
|
| 3 |
+
size 437975176
|
patentsberta_green_ft/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
patentsberta_green_ft/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
patentsberta_green_ft/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
patentsberta_green_ft/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|