Upload 8 files

config (4).json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

gitattributes (1)

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f242ee095f7638b7463b942830986f1a347b04482aa841b4677146bd81ef888d
+oid sha256:779926ef6eacaa8c49422ec53a63ea389986e09c42582416073d78dbe5d11db2
 size 1629436964

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f655fa0dd0081f2268b67b7028d6c401ddca176d518cebfa125e630d681ef2
+oid sha256:aaaff72d8dbf79f67666d91e8305154d42c29a088c83cd120828aa5447dc7f5b
 size 3259184731

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8b8f78f8ab97f155a53e04798b283255c70c7d783ca3734914d92eb7738c00
+oid sha256:d10d7fda9f09c69dd21f47e30981bf0d0f2da66b58d8b117c6f5e6c4a92d90cb
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb84971a8233865d3879ef75d98a5c44792abce4fbe173916e56341b9753aae6
+oid sha256:050d49c8b90af1f7382adfd95f4f5c488aba1e2a190cd048cc2116ed1de6f673
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 3342,
+  "global_step": 11140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,552 @@
       "learning_rate": 1.4075403949730702e-05,
       "loss": 0.0488,
       "step": 3300
+    },
+    {
+      "epoch": 6.1,
+      "grad_norm": 0.014200630597770214,
+      "learning_rate": 1.3895870736086176e-05,
+      "loss": 0.0374,
+      "step": 3400
+    },
+    {
+      "epoch": 6.28,
+      "grad_norm": 0.004939161241054535,
+      "learning_rate": 1.3716337522441652e-05,
+      "loss": 0.0393,
+      "step": 3500
+    },
+    {
+      "epoch": 6.46,
+      "grad_norm": 39.326534271240234,
+      "learning_rate": 1.353680430879713e-05,
+      "loss": 0.0404,
+      "step": 3600
+    },
+    {
+      "epoch": 6.64,
+      "grad_norm": 1.0669581890106201,
+      "learning_rate": 1.3357271095152604e-05,
+      "loss": 0.03,
+      "step": 3700
+    },
+    {
+      "epoch": 6.82,
+      "grad_norm": 0.11205600947141647,
+      "learning_rate": 1.317773788150808e-05,
+      "loss": 0.0416,
+      "step": 3800
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.005933618638664484,
+      "learning_rate": 1.2998204667863557e-05,
+      "loss": 0.0498,
+      "step": 3900
+    },
+    {
+      "epoch": 7.18,
+      "grad_norm": 0.0025591508019715548,
+      "learning_rate": 1.2818671454219031e-05,
+      "loss": 0.0214,
+      "step": 4000
+    },
+    {
+      "epoch": 7.36,
+      "grad_norm": 0.0021508955396711826,
+      "learning_rate": 1.2639138240574507e-05,
+      "loss": 0.0346,
+      "step": 4100
+    },
+    {
+      "epoch": 7.54,
+      "grad_norm": 0.002263248898088932,
+      "learning_rate": 1.2459605026929983e-05,
+      "loss": 0.0315,
+      "step": 4200
+    },
+    {
+      "epoch": 7.72,
+      "grad_norm": 0.0016491829883307219,
+      "learning_rate": 1.2280071813285459e-05,
+      "loss": 0.0238,
+      "step": 4300
+    },
+    {
+      "epoch": 7.9,
+      "grad_norm": 0.0034240155946463346,
+      "learning_rate": 1.2100538599640935e-05,
+      "loss": 0.0319,
+      "step": 4400
+    },
+    {
+      "epoch": 8.08,
+      "grad_norm": 0.002759799361228943,
+      "learning_rate": 1.1921005385996409e-05,
+      "loss": 0.0487,
+      "step": 4500
+    },
+    {
+      "epoch": 8.26,
+      "grad_norm": 34.639888763427734,
+      "learning_rate": 1.1741472172351887e-05,
+      "loss": 0.053,
+      "step": 4600
+    },
+    {
+      "epoch": 8.44,
+      "grad_norm": 0.001209100242704153,
+      "learning_rate": 1.1561938958707361e-05,
+      "loss": 0.0143,
+      "step": 4700
+    },
+    {
+      "epoch": 8.62,
+      "grad_norm": 0.0022134396713227034,
+      "learning_rate": 1.1382405745062837e-05,
+      "loss": 0.0291,
+      "step": 4800
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.06826081871986389,
+      "learning_rate": 1.1202872531418314e-05,
+      "loss": 0.0301,
+      "step": 4900
+    },
+    {
+      "epoch": 8.98,
+      "grad_norm": 0.0025578713975846767,
+      "learning_rate": 1.1023339317773789e-05,
+      "loss": 0.0194,
+      "step": 5000
+    },
+    {
+      "epoch": 9.16,
+      "grad_norm": 0.01461367029696703,
+      "learning_rate": 1.0843806104129264e-05,
+      "loss": 0.0152,
+      "step": 5100
+    },
+    {
+      "epoch": 9.34,
+      "grad_norm": 0.0008313595899380744,
+      "learning_rate": 1.0664272890484742e-05,
+      "loss": 0.0163,
+      "step": 5200
+    },
+    {
+      "epoch": 9.52,
+      "grad_norm": 1.5908000469207764,
+      "learning_rate": 1.0484739676840216e-05,
+      "loss": 0.0352,
+      "step": 5300
+    },
+    {
+      "epoch": 9.69,
+      "grad_norm": 0.0016398399602621794,
+      "learning_rate": 1.0305206463195692e-05,
+      "loss": 0.0268,
+      "step": 5400
+    },
+    {
+      "epoch": 9.87,
+      "grad_norm": 0.005051742307841778,
+      "learning_rate": 1.0125673249551166e-05,
+      "loss": 0.0244,
+      "step": 5500
+    },
+    {
+      "epoch": 10.05,
+      "grad_norm": 0.11044131964445114,
+      "learning_rate": 9.946140035906644e-06,
+      "loss": 0.0318,
+      "step": 5600
+    },
+    {
+      "epoch": 10.23,
+      "grad_norm": 0.02652016654610634,
+      "learning_rate": 9.76660682226212e-06,
+      "loss": 0.0224,
+      "step": 5700
+    },
+    {
+      "epoch": 10.41,
+      "grad_norm": 0.0051875789649784565,
+      "learning_rate": 9.587073608617595e-06,
+      "loss": 0.0086,
+      "step": 5800
+    },
+    {
+      "epoch": 10.59,
+      "grad_norm": 0.0023671940434724092,
+      "learning_rate": 9.40754039497307e-06,
+      "loss": 0.0061,
+      "step": 5900
+    },
+    {
+      "epoch": 10.77,
+      "grad_norm": 0.14054147899150848,
+      "learning_rate": 9.228007181328547e-06,
+      "loss": 0.0222,
+      "step": 6000
+    },
+    {
+      "epoch": 10.95,
+      "grad_norm": 0.002135949907824397,
+      "learning_rate": 9.048473967684023e-06,
+      "loss": 0.0205,
+      "step": 6100
+    },
+    {
+      "epoch": 11.13,
+      "grad_norm": 0.5219959616661072,
+      "learning_rate": 8.868940754039497e-06,
+      "loss": 0.0243,
+      "step": 6200
+    },
+    {
+      "epoch": 11.31,
+      "grad_norm": 0.004496410954743624,
+      "learning_rate": 8.689407540394975e-06,
+      "loss": 0.0232,
+      "step": 6300
+    },
+    {
+      "epoch": 11.49,
+      "grad_norm": 0.0012191541027277708,
+      "learning_rate": 8.509874326750449e-06,
+      "loss": 0.0174,
+      "step": 6400
+    },
+    {
+      "epoch": 11.67,
+      "grad_norm": 0.0010406944202259183,
+      "learning_rate": 8.330341113105925e-06,
+      "loss": 0.0002,
+      "step": 6500
+    },
+    {
+      "epoch": 11.85,
+      "grad_norm": 0.0007079216302372515,
+      "learning_rate": 8.1508078994614e-06,
+      "loss": 0.0181,
+      "step": 6600
+    },
+    {
+      "epoch": 12.03,
+      "grad_norm": 0.0031879213638603687,
+      "learning_rate": 7.971274685816877e-06,
+      "loss": 0.0029,
+      "step": 6700
+    },
+    {
+      "epoch": 12.21,
+      "grad_norm": 0.07363840192556381,
+      "learning_rate": 7.791741472172353e-06,
+      "loss": 0.012,
+      "step": 6800
+    },
+    {
+      "epoch": 12.39,
+      "grad_norm": 0.0074967676773667336,
+      "learning_rate": 7.6122082585278276e-06,
+      "loss": 0.0297,
+      "step": 6900
+    },
+    {
+      "epoch": 12.57,
+      "grad_norm": 0.03205731883645058,
+      "learning_rate": 7.432675044883304e-06,
+      "loss": 0.0172,
+      "step": 7000
+    },
+    {
+      "epoch": 12.75,
+      "grad_norm": 0.0017446995479986072,
+      "learning_rate": 7.25314183123878e-06,
+      "loss": 0.0095,
+      "step": 7100
+    },
+    {
+      "epoch": 12.93,
+      "grad_norm": 62.21705627441406,
+      "learning_rate": 7.073608617594255e-06,
+      "loss": 0.0216,
+      "step": 7200
+    },
+    {
+      "epoch": 13.11,
+      "grad_norm": 0.0004949498688802123,
+      "learning_rate": 6.894075403949732e-06,
+      "loss": 0.0025,
+      "step": 7300
+    },
+    {
+      "epoch": 13.29,
+      "grad_norm": 1.0483726263046265,
+      "learning_rate": 6.714542190305207e-06,
+      "loss": 0.0124,
+      "step": 7400
+    },
+    {
+      "epoch": 13.46,
+      "grad_norm": 0.0011325060622766614,
+      "learning_rate": 6.535008976660683e-06,
+      "loss": 0.0176,
+      "step": 7500
+    },
+    {
+      "epoch": 13.64,
+      "grad_norm": 0.0004886816022917628,
+      "learning_rate": 6.355475763016159e-06,
+      "loss": 0.0005,
+      "step": 7600
+    },
+    {
+      "epoch": 13.82,
+      "grad_norm": 0.0002447882143314928,
+      "learning_rate": 6.175942549371634e-06,
+      "loss": 0.0,
+      "step": 7700
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.0033621052280068398,
+      "learning_rate": 5.99640933572711e-06,
+      "loss": 0.0151,
+      "step": 7800
+    },
+    {
+      "epoch": 14.18,
+      "grad_norm": 0.37218067049980164,
+      "learning_rate": 5.8168761220825854e-06,
+      "loss": 0.0062,
+      "step": 7900
+    },
+    {
+      "epoch": 14.36,
+      "grad_norm": 0.00017587828915566206,
+      "learning_rate": 5.637342908438061e-06,
+      "loss": 0.0004,
+      "step": 8000
+    },
+    {
+      "epoch": 14.54,
+      "grad_norm": 0.00030748211429454386,
+      "learning_rate": 5.457809694793538e-06,
+      "loss": 0.0,
+      "step": 8100
+    },
+    {
+      "epoch": 14.72,
+      "grad_norm": 0.0006639692583121359,
+      "learning_rate": 5.278276481149013e-06,
+      "loss": 0.0301,
+      "step": 8200
+    },
+    {
+      "epoch": 14.9,
+      "grad_norm": 0.0006772920023649931,
+      "learning_rate": 5.098743267504489e-06,
+      "loss": 0.015,
+      "step": 8300
+    },
+    {
+      "epoch": 15.08,
+      "grad_norm": 0.0017782676732167602,
+      "learning_rate": 4.919210053859965e-06,
+      "loss": 0.0184,
+      "step": 8400
+    },
+    {
+      "epoch": 15.26,
+      "grad_norm": 0.0006229325663298368,
+      "learning_rate": 4.739676840215441e-06,
+      "loss": 0.0053,
+      "step": 8500
+    },
+    {
+      "epoch": 15.44,
+      "grad_norm": 0.0011186526389792562,
+      "learning_rate": 4.560143626570916e-06,
+      "loss": 0.0076,
+      "step": 8600
+    },
+    {
+      "epoch": 15.62,
+      "grad_norm": 0.0009836511453613639,
+      "learning_rate": 4.380610412926392e-06,
+      "loss": 0.0054,
+      "step": 8700
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 0.002876699436455965,
+      "learning_rate": 4.2010771992818675e-06,
+      "loss": 0.0011,
+      "step": 8800
+    },
+    {
+      "epoch": 15.98,
+      "grad_norm": 0.0004506981058511883,
+      "learning_rate": 4.021543985637343e-06,
+      "loss": 0.0142,
+      "step": 8900
+    },
+    {
+      "epoch": 16.16,
+      "grad_norm": 143.88809204101562,
+      "learning_rate": 3.842010771992819e-06,
+      "loss": 0.0136,
+      "step": 9000
+    },
+    {
+      "epoch": 16.34,
+      "grad_norm": 0.0012065657647326589,
+      "learning_rate": 3.6624775583482946e-06,
+      "loss": 0.0025,
+      "step": 9100
+    },
+    {
+      "epoch": 16.52,
+      "grad_norm": 0.0008388046990148723,
+      "learning_rate": 3.48294434470377e-06,
+      "loss": 0.0054,
+      "step": 9200
+    },
+    {
+      "epoch": 16.7,
+      "grad_norm": 0.0005097670364193618,
+      "learning_rate": 3.3034111310592464e-06,
+      "loss": 0.0,
+      "step": 9300
+    },
+    {
+      "epoch": 16.88,
+      "grad_norm": 0.00020445660629775375,
+      "learning_rate": 3.1238779174147223e-06,
+      "loss": 0.0019,
+      "step": 9400
+    },
+    {
+      "epoch": 17.06,
+      "grad_norm": 0.00033040347625501454,
+      "learning_rate": 2.9443447037701977e-06,
+      "loss": 0.002,
+      "step": 9500
+    },
+    {
+      "epoch": 17.24,
+      "grad_norm": 0.00017785438103601336,
+      "learning_rate": 2.7648114901256736e-06,
+      "loss": 0.0011,
+      "step": 9600
+    },
+    {
+      "epoch": 17.41,
+      "grad_norm": 0.0003500489692669362,
+      "learning_rate": 2.585278276481149e-06,
+      "loss": 0.023,
+      "step": 9700
+    },
+    {
+      "epoch": 17.59,
+      "grad_norm": 0.0002393827890045941,
+      "learning_rate": 2.405745062836625e-06,
+      "loss": 0.0001,
+      "step": 9800
+    },
+    {
+      "epoch": 17.77,
+      "grad_norm": 0.00016358286666218191,
+      "learning_rate": 2.2262118491921008e-06,
+      "loss": 0.0017,
+      "step": 9900
+    },
+    {
+      "epoch": 17.95,
+      "grad_norm": 0.0005156854167580605,
+      "learning_rate": 2.0466786355475767e-06,
+      "loss": 0.0022,
+      "step": 10000
+    },
+    {
+      "epoch": 18.13,
+      "grad_norm": 0.0001992402976611629,
+      "learning_rate": 1.8671454219030521e-06,
+      "loss": 0.006,
+      "step": 10100
+    },
+    {
+      "epoch": 18.31,
+      "grad_norm": 0.00023926289577502757,
+      "learning_rate": 1.687612208258528e-06,
+      "loss": 0.0026,
+      "step": 10200
+    },
+    {
+      "epoch": 18.49,
+      "grad_norm": 0.00018842410645447671,
+      "learning_rate": 1.5080789946140036e-06,
+      "loss": 0.0063,
+      "step": 10300
+    },
+    {
+      "epoch": 18.67,
+      "grad_norm": 0.00017712044063955545,
+      "learning_rate": 1.3285457809694793e-06,
+      "loss": 0.0,
+      "step": 10400
+    },
+    {
+      "epoch": 18.85,
+      "grad_norm": 0.00030714995227754116,
+      "learning_rate": 1.1490125673249552e-06,
+      "loss": 0.0,
+      "step": 10500
+    },
+    {
+      "epoch": 19.03,
+      "grad_norm": 0.0004120106459595263,
+      "learning_rate": 9.694793536804308e-07,
+      "loss": 0.0041,
+      "step": 10600
+    },
+    {
+      "epoch": 19.21,
+      "grad_norm": 0.00010405273496871814,
+      "learning_rate": 7.899461400359067e-07,
+      "loss": 0.0,
+      "step": 10700
+    },
+    {
+      "epoch": 19.39,
+      "grad_norm": 9.223635424859822e-05,
+      "learning_rate": 6.104129263913825e-07,
+      "loss": 0.0001,
+      "step": 10800
+    },
+    {
+      "epoch": 19.57,
+      "grad_norm": 0.00015765101124998182,
+      "learning_rate": 4.3087971274685824e-07,
+      "loss": 0.0042,
+      "step": 10900
+    },
+    {
+      "epoch": 19.75,
+      "grad_norm": 0.00016278728435281664,
+      "learning_rate": 2.5134649910233396e-07,
+      "loss": 0.0003,
+      "step": 11000
+    },
+    {
+      "epoch": 19.93,
+      "grad_norm": 0.00011305743100820109,
+      "learning_rate": 7.18132854578097e-08,
+      "loss": 0.0,
+      "step": 11100
     }
   ],
   "logging_steps": 100,
@@ -245,7 +791,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 3.4115676633458784e+16,
+  "total_flos": 1.1371892211152928e+17,
   "train_batch_size": 14,
   "trial_name": null,
   "trial_params": null