Commit
•
62a9d89
1
Parent(s):
8aa5a38
Upload folder using huggingface_hub
Browse files- config.json +88 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +380 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "AnnaWegmann/Style-Embedding",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5",
|
| 20 |
+
"6": "LABEL_6",
|
| 21 |
+
"7": "LABEL_7",
|
| 22 |
+
"8": "LABEL_8",
|
| 23 |
+
"9": "LABEL_9",
|
| 24 |
+
"10": "LABEL_10",
|
| 25 |
+
"11": "LABEL_11",
|
| 26 |
+
"12": "LABEL_12",
|
| 27 |
+
"13": "LABEL_13",
|
| 28 |
+
"14": "LABEL_14",
|
| 29 |
+
"15": "LABEL_15",
|
| 30 |
+
"16": "LABEL_16",
|
| 31 |
+
"17": "LABEL_17",
|
| 32 |
+
"18": "LABEL_18",
|
| 33 |
+
"19": "LABEL_19",
|
| 34 |
+
"20": "LABEL_20",
|
| 35 |
+
"21": "LABEL_21",
|
| 36 |
+
"22": "LABEL_22",
|
| 37 |
+
"23": "LABEL_23",
|
| 38 |
+
"24": "LABEL_24",
|
| 39 |
+
"25": "LABEL_25",
|
| 40 |
+
"26": "LABEL_26",
|
| 41 |
+
"27": "LABEL_27"
|
| 42 |
+
},
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 3072,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"LABEL_0": 0,
|
| 47 |
+
"LABEL_1": 1,
|
| 48 |
+
"LABEL_10": 10,
|
| 49 |
+
"LABEL_11": 11,
|
| 50 |
+
"LABEL_12": 12,
|
| 51 |
+
"LABEL_13": 13,
|
| 52 |
+
"LABEL_14": 14,
|
| 53 |
+
"LABEL_15": 15,
|
| 54 |
+
"LABEL_16": 16,
|
| 55 |
+
"LABEL_17": 17,
|
| 56 |
+
"LABEL_18": 18,
|
| 57 |
+
"LABEL_19": 19,
|
| 58 |
+
"LABEL_2": 2,
|
| 59 |
+
"LABEL_20": 20,
|
| 60 |
+
"LABEL_21": 21,
|
| 61 |
+
"LABEL_22": 22,
|
| 62 |
+
"LABEL_23": 23,
|
| 63 |
+
"LABEL_24": 24,
|
| 64 |
+
"LABEL_25": 25,
|
| 65 |
+
"LABEL_26": 26,
|
| 66 |
+
"LABEL_27": 27,
|
| 67 |
+
"LABEL_3": 3,
|
| 68 |
+
"LABEL_4": 4,
|
| 69 |
+
"LABEL_5": 5,
|
| 70 |
+
"LABEL_6": 6,
|
| 71 |
+
"LABEL_7": 7,
|
| 72 |
+
"LABEL_8": 8,
|
| 73 |
+
"LABEL_9": 9
|
| 74 |
+
},
|
| 75 |
+
"layer_norm_eps": 1e-05,
|
| 76 |
+
"max_position_embeddings": 514,
|
| 77 |
+
"model_type": "roberta",
|
| 78 |
+
"num_attention_heads": 12,
|
| 79 |
+
"num_hidden_layers": 12,
|
| 80 |
+
"pad_token_id": 1,
|
| 81 |
+
"position_embedding_type": "absolute",
|
| 82 |
+
"problem_type": "single_label_classification",
|
| 83 |
+
"torch_dtype": "float32",
|
| 84 |
+
"transformers_version": "4.44.0",
|
| 85 |
+
"type_vocab_size": 1,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3d7032f2d01b63fd55564f0e299ebda4bd46f9833c2bc81c205be38640f19ce
|
| 3 |
+
size 498692800
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28b595dd7cbec86e9a176c5a208e4374dda13f20a364b5dab8021bdb2bae9a0b
|
| 3 |
+
size 997505402
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a519d1bf8ba697f2e18793f16648fbf4bbcd5e14a46008c796a7599c8c6d879e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6469c36f0240285ab1d8cc8805f681bac9315091ed463838135084f454ef2237
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,380 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4956,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.041969330104923326,
|
| 13 |
+
"grad_norm": 13.489130973815918,
|
| 14 |
+
"learning_rate": 4.930051116491795e-05,
|
| 15 |
+
"loss": 3.1245,
|
| 16 |
+
"step": 104
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08393866020984665,
|
| 20 |
+
"grad_norm": 9.602147102355957,
|
| 21 |
+
"learning_rate": 4.8601022329835895e-05,
|
| 22 |
+
"loss": 2.919,
|
| 23 |
+
"step": 208
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12590799031476999,
|
| 27 |
+
"grad_norm": 8.955652236938477,
|
| 28 |
+
"learning_rate": 4.7901533494753834e-05,
|
| 29 |
+
"loss": 2.865,
|
| 30 |
+
"step": 312
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1678773204196933,
|
| 34 |
+
"grad_norm": 9.70827579498291,
|
| 35 |
+
"learning_rate": 4.720204465967178e-05,
|
| 36 |
+
"loss": 2.8891,
|
| 37 |
+
"step": 416
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20984665052461662,
|
| 41 |
+
"grad_norm": 9.555304527282715,
|
| 42 |
+
"learning_rate": 4.6502555824589726e-05,
|
| 43 |
+
"loss": 2.8066,
|
| 44 |
+
"step": 520
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.25181598062953997,
|
| 48 |
+
"grad_norm": 7.922400951385498,
|
| 49 |
+
"learning_rate": 4.580306698950767e-05,
|
| 50 |
+
"loss": 2.775,
|
| 51 |
+
"step": 624
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2937853107344633,
|
| 55 |
+
"grad_norm": 12.1842041015625,
|
| 56 |
+
"learning_rate": 4.510357815442561e-05,
|
| 57 |
+
"loss": 2.7193,
|
| 58 |
+
"step": 728
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3357546408393866,
|
| 62 |
+
"grad_norm": 63.8215446472168,
|
| 63 |
+
"learning_rate": 4.4404089319343565e-05,
|
| 64 |
+
"loss": 2.9175,
|
| 65 |
+
"step": 832
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.37772397094430993,
|
| 69 |
+
"grad_norm": 8.268672943115234,
|
| 70 |
+
"learning_rate": 4.3704600484261504e-05,
|
| 71 |
+
"loss": 2.8031,
|
| 72 |
+
"step": 936
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.41969330104923325,
|
| 76 |
+
"grad_norm": 10.684550285339355,
|
| 77 |
+
"learning_rate": 4.300511164917945e-05,
|
| 78 |
+
"loss": 2.8335,
|
| 79 |
+
"step": 1040
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.46166263115415657,
|
| 83 |
+
"grad_norm": 15.027052879333496,
|
| 84 |
+
"learning_rate": 4.230562281409739e-05,
|
| 85 |
+
"loss": 2.7266,
|
| 86 |
+
"step": 1144
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5036319612590799,
|
| 90 |
+
"grad_norm": 11.817206382751465,
|
| 91 |
+
"learning_rate": 4.1606133979015336e-05,
|
| 92 |
+
"loss": 2.6513,
|
| 93 |
+
"step": 1248
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5456012913640033,
|
| 97 |
+
"grad_norm": 13.562594413757324,
|
| 98 |
+
"learning_rate": 4.090664514393328e-05,
|
| 99 |
+
"loss": 2.6641,
|
| 100 |
+
"step": 1352
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5875706214689266,
|
| 104 |
+
"grad_norm": 18.43484878540039,
|
| 105 |
+
"learning_rate": 4.020715630885122e-05,
|
| 106 |
+
"loss": 2.7054,
|
| 107 |
+
"step": 1456
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6295399515738499,
|
| 111 |
+
"grad_norm": 8.890129089355469,
|
| 112 |
+
"learning_rate": 3.9507667473769174e-05,
|
| 113 |
+
"loss": 2.676,
|
| 114 |
+
"step": 1560
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6715092816787732,
|
| 118 |
+
"grad_norm": 7.976245403289795,
|
| 119 |
+
"learning_rate": 3.8808178638687113e-05,
|
| 120 |
+
"loss": 2.6769,
|
| 121 |
+
"step": 1664
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.7134786117836965,
|
| 125 |
+
"grad_norm": 16.992326736450195,
|
| 126 |
+
"learning_rate": 3.810868980360506e-05,
|
| 127 |
+
"loss": 2.7139,
|
| 128 |
+
"step": 1768
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7554479418886199,
|
| 132 |
+
"grad_norm": 30.8548526763916,
|
| 133 |
+
"learning_rate": 3.7409200968523006e-05,
|
| 134 |
+
"loss": 2.5842,
|
| 135 |
+
"step": 1872
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7974172719935432,
|
| 139 |
+
"grad_norm": 19.750226974487305,
|
| 140 |
+
"learning_rate": 3.670971213344095e-05,
|
| 141 |
+
"loss": 2.5971,
|
| 142 |
+
"step": 1976
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8393866020984665,
|
| 146 |
+
"grad_norm": 8.788566589355469,
|
| 147 |
+
"learning_rate": 3.601022329835889e-05,
|
| 148 |
+
"loss": 2.583,
|
| 149 |
+
"step": 2080
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8813559322033898,
|
| 153 |
+
"grad_norm": 11.469756126403809,
|
| 154 |
+
"learning_rate": 3.531073446327684e-05,
|
| 155 |
+
"loss": 2.567,
|
| 156 |
+
"step": 2184
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.9233252623083131,
|
| 160 |
+
"grad_norm": 11.528902053833008,
|
| 161 |
+
"learning_rate": 3.4611245628194784e-05,
|
| 162 |
+
"loss": 2.6214,
|
| 163 |
+
"step": 2288
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9652945924132365,
|
| 167 |
+
"grad_norm": 13.25121021270752,
|
| 168 |
+
"learning_rate": 3.391175679311272e-05,
|
| 169 |
+
"loss": 2.6326,
|
| 170 |
+
"step": 2392
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.0,
|
| 174 |
+
"eval_accuracy": 0.22509578544061304,
|
| 175 |
+
"eval_loss": 2.676828145980835,
|
| 176 |
+
"eval_runtime": 18.7388,
|
| 177 |
+
"eval_samples_per_second": 55.713,
|
| 178 |
+
"eval_steps_per_second": 6.991,
|
| 179 |
+
"step": 2478
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.0072639225181599,
|
| 183 |
+
"grad_norm": 7.456902980804443,
|
| 184 |
+
"learning_rate": 3.3212267958030676e-05,
|
| 185 |
+
"loss": 2.5498,
|
| 186 |
+
"step": 2496
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.0492332526230832,
|
| 190 |
+
"grad_norm": 14.628376960754395,
|
| 191 |
+
"learning_rate": 3.2512779122948615e-05,
|
| 192 |
+
"loss": 2.5027,
|
| 193 |
+
"step": 2600
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.0912025827280065,
|
| 197 |
+
"grad_norm": 17.166057586669922,
|
| 198 |
+
"learning_rate": 3.181329028786656e-05,
|
| 199 |
+
"loss": 2.4437,
|
| 200 |
+
"step": 2704
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.1331719128329298,
|
| 204 |
+
"grad_norm": 8.214387893676758,
|
| 205 |
+
"learning_rate": 3.111380145278451e-05,
|
| 206 |
+
"loss": 2.4622,
|
| 207 |
+
"step": 2808
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.1751412429378532,
|
| 211 |
+
"grad_norm": 12.298638343811035,
|
| 212 |
+
"learning_rate": 3.041431261770245e-05,
|
| 213 |
+
"loss": 2.4839,
|
| 214 |
+
"step": 2912
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.2171105730427765,
|
| 218 |
+
"grad_norm": 10.392972946166992,
|
| 219 |
+
"learning_rate": 2.9714823782620393e-05,
|
| 220 |
+
"loss": 2.4826,
|
| 221 |
+
"step": 3016
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.2590799031476998,
|
| 225 |
+
"grad_norm": 10.585667610168457,
|
| 226 |
+
"learning_rate": 2.9015334947538336e-05,
|
| 227 |
+
"loss": 2.4243,
|
| 228 |
+
"step": 3120
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.3010492332526231,
|
| 232 |
+
"grad_norm": 10.92833137512207,
|
| 233 |
+
"learning_rate": 2.8315846112456285e-05,
|
| 234 |
+
"loss": 2.4804,
|
| 235 |
+
"step": 3224
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.3430185633575464,
|
| 239 |
+
"grad_norm": 10.050086975097656,
|
| 240 |
+
"learning_rate": 2.7616357277374228e-05,
|
| 241 |
+
"loss": 2.4112,
|
| 242 |
+
"step": 3328
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.3849878934624698,
|
| 246 |
+
"grad_norm": 8.787351608276367,
|
| 247 |
+
"learning_rate": 2.691686844229217e-05,
|
| 248 |
+
"loss": 2.3694,
|
| 249 |
+
"step": 3432
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.426957223567393,
|
| 253 |
+
"grad_norm": 10.800174713134766,
|
| 254 |
+
"learning_rate": 2.621737960721012e-05,
|
| 255 |
+
"loss": 2.4382,
|
| 256 |
+
"step": 3536
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.4689265536723164,
|
| 260 |
+
"grad_norm": 10.92818832397461,
|
| 261 |
+
"learning_rate": 2.5517890772128063e-05,
|
| 262 |
+
"loss": 2.432,
|
| 263 |
+
"step": 3640
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.5108958837772397,
|
| 267 |
+
"grad_norm": 12.755341529846191,
|
| 268 |
+
"learning_rate": 2.4818401937046006e-05,
|
| 269 |
+
"loss": 2.4453,
|
| 270 |
+
"step": 3744
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.552865213882163,
|
| 274 |
+
"grad_norm": 12.561775207519531,
|
| 275 |
+
"learning_rate": 2.411891310196395e-05,
|
| 276 |
+
"loss": 2.3501,
|
| 277 |
+
"step": 3848
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.5948345439870864,
|
| 281 |
+
"grad_norm": 11.288426399230957,
|
| 282 |
+
"learning_rate": 2.3419424266881895e-05,
|
| 283 |
+
"loss": 2.4433,
|
| 284 |
+
"step": 3952
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.6368038740920097,
|
| 288 |
+
"grad_norm": 13.944038391113281,
|
| 289 |
+
"learning_rate": 2.271993543179984e-05,
|
| 290 |
+
"loss": 2.3851,
|
| 291 |
+
"step": 4056
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.678773204196933,
|
| 295 |
+
"grad_norm": 12.919787406921387,
|
| 296 |
+
"learning_rate": 2.2020446596717783e-05,
|
| 297 |
+
"loss": 2.4121,
|
| 298 |
+
"step": 4160
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.7207425343018563,
|
| 302 |
+
"grad_norm": 19.511533737182617,
|
| 303 |
+
"learning_rate": 2.132095776163573e-05,
|
| 304 |
+
"loss": 2.3032,
|
| 305 |
+
"step": 4264
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.7627118644067796,
|
| 309 |
+
"grad_norm": 13.31141471862793,
|
| 310 |
+
"learning_rate": 2.0621468926553672e-05,
|
| 311 |
+
"loss": 2.3692,
|
| 312 |
+
"step": 4368
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.804681194511703,
|
| 316 |
+
"grad_norm": 14.81092357635498,
|
| 317 |
+
"learning_rate": 1.992198009147162e-05,
|
| 318 |
+
"loss": 2.341,
|
| 319 |
+
"step": 4472
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.8466505246166263,
|
| 323 |
+
"grad_norm": 16.881967544555664,
|
| 324 |
+
"learning_rate": 1.9222491256389565e-05,
|
| 325 |
+
"loss": 2.3533,
|
| 326 |
+
"step": 4576
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.8886198547215496,
|
| 330 |
+
"grad_norm": 13.03023624420166,
|
| 331 |
+
"learning_rate": 1.8523002421307507e-05,
|
| 332 |
+
"loss": 2.3374,
|
| 333 |
+
"step": 4680
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.9305891848264731,
|
| 337 |
+
"grad_norm": 9.3682861328125,
|
| 338 |
+
"learning_rate": 1.782351358622545e-05,
|
| 339 |
+
"loss": 2.3585,
|
| 340 |
+
"step": 4784
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.9725585149313964,
|
| 344 |
+
"grad_norm": 13.498007774353027,
|
| 345 |
+
"learning_rate": 1.7124024751143396e-05,
|
| 346 |
+
"loss": 2.3383,
|
| 347 |
+
"step": 4888
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.0,
|
| 351 |
+
"eval_accuracy": 0.2835249042145594,
|
| 352 |
+
"eval_loss": 2.457916259765625,
|
| 353 |
+
"eval_runtime": 18.7722,
|
| 354 |
+
"eval_samples_per_second": 55.614,
|
| 355 |
+
"eval_steps_per_second": 6.978,
|
| 356 |
+
"step": 4956
|
| 357 |
+
}
|
| 358 |
+
],
|
| 359 |
+
"logging_steps": 104,
|
| 360 |
+
"max_steps": 7434,
|
| 361 |
+
"num_input_tokens_seen": 0,
|
| 362 |
+
"num_train_epochs": 3,
|
| 363 |
+
"save_steps": 500,
|
| 364 |
+
"stateful_callbacks": {
|
| 365 |
+
"TrainerControl": {
|
| 366 |
+
"args": {
|
| 367 |
+
"should_epoch_stop": false,
|
| 368 |
+
"should_evaluate": false,
|
| 369 |
+
"should_log": false,
|
| 370 |
+
"should_save": true,
|
| 371 |
+
"should_training_stop": false
|
| 372 |
+
},
|
| 373 |
+
"attributes": {}
|
| 374 |
+
}
|
| 375 |
+
},
|
| 376 |
+
"total_flos": 1.0431630640472064e+16,
|
| 377 |
+
"train_batch_size": 8,
|
| 378 |
+
"trial_name": null,
|
| 379 |
+
"trial_params": null
|
| 380 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52cc942f0e8d19a95ae0732a999934bc8373c9b84c459977b70e0e78e87a4ca2
|
| 3 |
+
size 5176
|