Training in progress, epoch 7, checkpoint

checkpoint-26201/config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "nour4286/ArabartModel",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "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": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tokenizer_class": "BarthezTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50002
+}

checkpoint-26201/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_new_tokens": 100,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.2"
+}

checkpoint-26201/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e86420b69e22813c0cb0f2baa2ff0db2f03639967c1e0361e38deccaa2163b8
+size 557116312

checkpoint-26201/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48265cce9227550611f5de5befa26ead2ef603e8cc5d8aafeb05c3d8b65279b5
+size 1113991930

checkpoint-26201/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46706643e9fdd754a7791b22ec8e176025bfdeee1a5d0beba609f0c29de735c
+size 14244

checkpoint-26201/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279ec6ea9d4ea2811a5ac191fdeea4e6dd1d71d1e0d64247f58b880aed00e6ad
+size 1064

checkpoint-26201/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
+size 1315170

checkpoint-26201/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-26201/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BarthezTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-26201/trainer_state.json

@@ -0,0 +1,540 @@
+{
+  "best_metric": 27.7286,
+  "best_model_checkpoint": "/content/drive/MyDrive/ArabartModel/checkpoint-26201",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 26201,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32722513089005234,
+      "grad_norm": 1.563672423362732,
+      "learning_rate": 4.6727748691099475e-05,
+      "loss": 0.0195,
+      "step": 500
+    },
+    {
+      "epoch": 0.6544502617801047,
+      "grad_norm": 1.7397737503051758,
+      "learning_rate": 4.3455497382198955e-05,
+      "loss": 0.0244,
+      "step": 1000
+    },
+    {
+      "epoch": 0.981675392670157,
+      "grad_norm": 3.006633758544922,
+      "learning_rate": 4.018324607329843e-05,
+      "loss": 0.0293,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.626201629638672,
+      "eval_rouge1": 25.2705,
+      "eval_rouge2": 9.9865,
+      "eval_rougeL": 21.8678,
+      "eval_runtime": 372.5145,
+      "eval_samples_per_second": 5.892,
+      "eval_steps_per_second": 0.591,
+      "step": 1528
+    },
+    {
+      "epoch": 1.3089005235602094,
+      "grad_norm": 3.4732136726379395,
+      "learning_rate": 4.3455497382198955e-05,
+      "loss": 0.0456,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6361256544502618,
+      "grad_norm": 2.2575156688690186,
+      "learning_rate": 4.181937172774869e-05,
+      "loss": 0.0619,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9633507853403143,
+      "grad_norm": 6.030032157897949,
+      "learning_rate": 4.018324607329843e-05,
+      "loss": 0.0993,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.542174339294434,
+      "eval_rouge1": 25.0744,
+      "eval_rouge2": 9.8534,
+      "eval_rougeL": 21.6992,
+      "eval_runtime": 411.9676,
+      "eval_samples_per_second": 5.328,
+      "eval_steps_per_second": 0.534,
+      "step": 3056
+    },
+    {
+      "epoch": 2.2905759162303667,
+      "grad_norm": 6.401626110076904,
+      "learning_rate": 3.8547120418848174e-05,
+      "loss": 0.21,
+      "step": 3500
+    },
+    {
+      "epoch": 2.6178010471204187,
+      "grad_norm": 5.806931495666504,
+      "learning_rate": 3.691099476439791e-05,
+      "loss": 0.3595,
+      "step": 4000
+    },
+    {
+      "epoch": 2.945026178010471,
+      "grad_norm": 5.840355396270752,
+      "learning_rate": 3.5274869109947647e-05,
+      "loss": 0.6436,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.927168369293213,
+      "eval_rouge1": 25.5914,
+      "eval_rouge2": 10.2904,
+      "eval_rougeL": 22.3089,
+      "eval_runtime": 412.3529,
+      "eval_samples_per_second": 5.323,
+      "eval_steps_per_second": 0.534,
+      "step": 4584
+    },
+    {
+      "epoch": 3.2722513089005236,
+      "grad_norm": 5.320337772369385,
+      "learning_rate": 3.3638743455497386e-05,
+      "loss": 0.7617,
+      "step": 5000
+    },
+    {
+      "epoch": 3.599476439790576,
+      "grad_norm": 5.708410739898682,
+      "learning_rate": 3.2002617801047126e-05,
+      "loss": 0.9186,
+      "step": 5500
+    },
+    {
+      "epoch": 3.9267015706806285,
+      "grad_norm": 6.043923377990723,
+      "learning_rate": 3.036649214659686e-05,
+      "loss": 1.112,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2077620029449463,
+      "eval_rouge1": 26.5258,
+      "eval_rouge2": 11.116,
+      "eval_rougeL": 23.3381,
+      "eval_runtime": 397.8337,
+      "eval_samples_per_second": 5.517,
+      "eval_steps_per_second": 0.553,
+      "step": 6112
+    },
+    {
+      "epoch": 4.2539267015706805,
+      "grad_norm": 5.179211139678955,
+      "learning_rate": 2.87303664921466e-05,
+      "loss": 1.0997,
+      "step": 6500
+    },
+    {
+      "epoch": 4.581151832460733,
+      "grad_norm": 4.997713565826416,
+      "learning_rate": 2.709424083769634e-05,
+      "loss": 1.0736,
+      "step": 7000
+    },
+    {
+      "epoch": 4.908376963350785,
+      "grad_norm": 5.441833972930908,
+      "learning_rate": 2.545811518324607e-05,
+      "loss": 1.0866,
+      "step": 7500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.3156800270080566,
+      "eval_rouge1": 26.4275,
+      "eval_rouge2": 10.8484,
+      "eval_rougeL": 23.0503,
+      "eval_runtime": 402.2407,
+      "eval_samples_per_second": 5.457,
+      "eval_steps_per_second": 0.547,
+      "step": 7640
+    },
+    {
+      "epoch": 5.2356020942408374,
+      "grad_norm": 4.417330741882324,
+      "learning_rate": 2.382198952879581e-05,
+      "loss": 0.9343,
+      "step": 8000
+    },
+    {
+      "epoch": 5.56282722513089,
+      "grad_norm": 5.149570465087891,
+      "learning_rate": 2.218586387434555e-05,
+      "loss": 0.9473,
+      "step": 8500
+    },
+    {
+      "epoch": 5.890052356020942,
+      "grad_norm": 5.305272102355957,
+      "learning_rate": 2.054973821989529e-05,
+      "loss": 0.9589,
+      "step": 9000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.433619737625122,
+      "eval_rouge1": 26.3479,
+      "eval_rouge2": 10.8544,
+      "eval_rougeL": 23.0206,
+      "eval_runtime": 385.2891,
+      "eval_samples_per_second": 5.697,
+      "eval_steps_per_second": 0.571,
+      "step": 9168
+    },
+    {
+      "epoch": 6.217277486910994,
+      "grad_norm": 5.96689510345459,
+      "learning_rate": 1.8913612565445027e-05,
+      "loss": 0.8437,
+      "step": 9500
+    },
+    {
+      "epoch": 6.544502617801047,
+      "grad_norm": 5.179261207580566,
+      "learning_rate": 1.7277486910994763e-05,
+      "loss": 0.8582,
+      "step": 10000
+    },
+    {
+      "epoch": 6.871727748691099,
+      "grad_norm": 4.92213773727417,
+      "learning_rate": 1.5641361256544503e-05,
+      "loss": 0.8669,
+      "step": 10500
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.551990032196045,
+      "eval_rouge1": 26.0878,
+      "eval_rouge2": 10.6444,
+      "eval_rougeL": 22.7671,
+      "eval_runtime": 413.1448,
+      "eval_samples_per_second": 5.313,
+      "eval_steps_per_second": 0.533,
+      "step": 10696
+    },
+    {
+      "epoch": 7.198952879581152,
+      "grad_norm": 4.538914203643799,
+      "learning_rate": 1.4005235602094241e-05,
+      "loss": 0.7803,
+      "step": 11000
+    },
+    {
+      "epoch": 7.526178010471204,
+      "grad_norm": 5.420250415802002,
+      "learning_rate": 1.236910994764398e-05,
+      "loss": 0.7777,
+      "step": 11500
+    },
+    {
+      "epoch": 7.853403141361256,
+      "grad_norm": 4.503458023071289,
+      "learning_rate": 1.0732984293193717e-05,
+      "loss": 0.7894,
+      "step": 12000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.652216672897339,
+      "eval_rouge1": 26.1239,
+      "eval_rouge2": 10.689,
+      "eval_rougeL": 22.8303,
+      "eval_runtime": 389.5703,
+      "eval_samples_per_second": 5.634,
+      "eval_steps_per_second": 0.565,
+      "step": 12224
+    },
+    {
+      "epoch": 8.180628272251308,
+      "grad_norm": 4.9211812019348145,
+      "learning_rate": 9.096858638743457e-06,
+      "loss": 0.7505,
+      "step": 12500
+    },
+    {
+      "epoch": 8.507853403141361,
+      "grad_norm": 4.948258876800537,
+      "learning_rate": 7.4607329842931935e-06,
+      "loss": 0.731,
+      "step": 13000
+    },
+    {
+      "epoch": 8.835078534031414,
+      "grad_norm": 4.717357158660889,
+      "learning_rate": 5.824607329842932e-06,
+      "loss": 0.7331,
+      "step": 13500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.7317800521850586,
+      "eval_rouge1": 26.2374,
+      "eval_rouge2": 10.7166,
+      "eval_rougeL": 22.9298,
+      "eval_runtime": 385.8895,
+      "eval_samples_per_second": 5.688,
+      "eval_steps_per_second": 0.57,
+      "step": 13752
+    },
+    {
+      "epoch": 9.162303664921467,
+      "grad_norm": 4.790928363800049,
+      "learning_rate": 4.18848167539267e-06,
+      "loss": 0.7187,
+      "step": 14000
+    },
+    {
+      "epoch": 9.489528795811518,
+      "grad_norm": 4.424731254577637,
+      "learning_rate": 2.5523560209424085e-06,
+      "loss": 0.6988,
+      "step": 14500
+    },
+    {
+      "epoch": 9.81675392670157,
+      "grad_norm": 4.868335723876953,
+      "learning_rate": 9.162303664921465e-07,
+      "loss": 0.7027,
+      "step": 15000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.772279739379883,
+      "eval_rouge1": 26.1242,
+      "eval_rouge2": 10.7689,
+      "eval_rougeL": 22.8692,
+      "eval_runtime": 387.9211,
+      "eval_samples_per_second": 5.658,
+      "eval_steps_per_second": 0.567,
+      "step": 15280
+    },
+    {
+      "epoch": 4.141063318193962,
+      "grad_norm": 4.127313613891602,
+      "learning_rate": 3.619645560602013e-05,
+      "loss": 2.3856,
+      "step": 15500
+    },
+    {
+      "epoch": 4.2746460058776385,
+      "grad_norm": 3.7080917358398438,
+      "learning_rate": 3.575117998040787e-05,
+      "loss": 2.2343,
+      "step": 16000
+    },
+    {
+      "epoch": 4.408228693561314,
+      "grad_norm": 3.771442413330078,
+      "learning_rate": 3.530590435479562e-05,
+      "loss": 2.2498,
+      "step": 16500
+    },
+    {
+      "epoch": 4.54181138124499,
+      "grad_norm": 3.3883867263793945,
+      "learning_rate": 3.486062872918336e-05,
+      "loss": 2.2734,
+      "step": 17000
+    },
+    {
+      "epoch": 4.675394068928667,
+      "grad_norm": 3.82869029045105,
+      "learning_rate": 3.441535310357111e-05,
+      "loss": 2.2957,
+      "step": 17500
+    },
+    {
+      "epoch": 4.808976756612343,
+      "grad_norm": 3.480701208114624,
+      "learning_rate": 3.397007747795886e-05,
+      "loss": 2.255,
+      "step": 18000
+    },
+    {
+      "epoch": 4.94255944429602,
+      "grad_norm": 3.433276891708374,
+      "learning_rate": 3.3524801852346606e-05,
+      "loss": 2.2527,
+      "step": 18500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.624432325363159,
+      "eval_rouge1": 27.5622,
+      "eval_rouge2": 11.8188,
+      "eval_rougeL": 24.2339,
+      "eval_runtime": 862.1361,
+      "eval_samples_per_second": 5.439,
+      "eval_steps_per_second": 0.544,
+      "step": 18715
+    },
+    {
+      "epoch": 5.0761421319796955,
+      "grad_norm": 3.8290796279907227,
+      "learning_rate": 3.307952622673435e-05,
+      "loss": 2.1614,
+      "step": 19000
+    },
+    {
+      "epoch": 5.209724819663371,
+      "grad_norm": 4.148732662200928,
+      "learning_rate": 3.2634250601122095e-05,
+      "loss": 2.028,
+      "step": 19500
+    },
+    {
+      "epoch": 5.343307507347048,
+      "grad_norm": 3.9491941928863525,
+      "learning_rate": 3.218897497550984e-05,
+      "loss": 2.0413,
+      "step": 20000
+    },
+    {
+      "epoch": 5.476890195030724,
+      "grad_norm": 4.000278472900391,
+      "learning_rate": 3.174369934989759e-05,
+      "loss": 2.1058,
+      "step": 20500
+    },
+    {
+      "epoch": 5.6104728827144,
+      "grad_norm": 4.109215259552002,
+      "learning_rate": 3.129842372428534e-05,
+      "loss": 2.0563,
+      "step": 21000
+    },
+    {
+      "epoch": 5.744055570398077,
+      "grad_norm": 3.3794937133789062,
+      "learning_rate": 3.085314809867308e-05,
+      "loss": 2.0737,
+      "step": 21500
+    },
+    {
+      "epoch": 5.8776382580817526,
+      "grad_norm": 3.326864719390869,
+      "learning_rate": 3.0407872473060827e-05,
+      "loss": 2.085,
+      "step": 22000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.6439783573150635,
+      "eval_rouge1": 27.1127,
+      "eval_rouge2": 11.6364,
+      "eval_rougeL": 23.8039,
+      "eval_runtime": 879.7933,
+      "eval_samples_per_second": 5.33,
+      "eval_steps_per_second": 0.533,
+      "step": 22458
+    },
+    {
+      "epoch": 6.011220945765428,
+      "grad_norm": 3.5264782905578613,
+      "learning_rate": 2.9962596847448572e-05,
+      "loss": 1.8559,
+      "step": 22500
+    },
+    {
+      "epoch": 6.144803633449105,
+      "grad_norm": 3.7577388286590576,
+      "learning_rate": 2.951732122183632e-05,
+      "loss": 1.8982,
+      "step": 23000
+    },
+    {
+      "epoch": 6.278386321132781,
+      "grad_norm": 3.2084107398986816,
+      "learning_rate": 2.907204559622406e-05,
+      "loss": 1.8801,
+      "step": 23500
+    },
+    {
+      "epoch": 6.411969008816458,
+      "grad_norm": 4.275125503540039,
+      "learning_rate": 2.8626769970611812e-05,
+      "loss": 1.9144,
+      "step": 24000
+    },
+    {
+      "epoch": 6.545551696500134,
+      "grad_norm": 3.5503015518188477,
+      "learning_rate": 2.8181494344999553e-05,
+      "loss": 1.9229,
+      "step": 24500
+    },
+    {
+      "epoch": 6.67913438418381,
+      "grad_norm": 3.489950656890869,
+      "learning_rate": 2.77362187193873e-05,
+      "loss": 1.9033,
+      "step": 25000
+    },
+    {
+      "epoch": 6.812717071867486,
+      "grad_norm": 3.5493781566619873,
+      "learning_rate": 2.7290943093775046e-05,
+      "loss": 1.9058,
+      "step": 25500
+    },
+    {
+      "epoch": 6.946299759551162,
+      "grad_norm": 3.603605031967163,
+      "learning_rate": 2.6845667468162793e-05,
+      "loss": 1.8774,
+      "step": 26000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.670841693878174,
+      "eval_rouge1": 27.7286,
+      "eval_rouge2": 11.9572,
+      "eval_rougeL": 24.3316,
+      "eval_runtime": 903.5292,
+      "eval_samples_per_second": 5.19,
+      "eval_steps_per_second": 0.519,
+      "step": 26201
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 56145,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3626813542691226e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-26201/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9414c9eeaaab303ed5167bf6ea848b944aeeea9d5c2edfef10ea3671a79573
+size 6904