Training in progress, step 4998, checkpoint

checkpoint-4998/config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "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,
+  "dropout": 0.1,
+  "early_stopping": null,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "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_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "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": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-4998/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "max_length": 128,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.1"
+}

checkpoint-4998/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45552a6778bd7eff3494f40f736f2238076ac7ae4d408e7d57f41e1d9ed45159
+size 557912620

checkpoint-4998/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1f69abb159c57412ce151e333867fe09bf850de982abbc8d5b7acdf49c79c1
+size 1115579898

checkpoint-4998/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d46ca55773e965cfbc05fb2a9408b481830ad8a416a00187db643cb27a7696
+size 14244

checkpoint-4998/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0605d693dbc5f2e9771bae27073a3d4badeb77e270340899c12bc9ad05301b
+size 1064

checkpoint-4998/special_tokens_map.json

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

checkpoint-4998/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-4998/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8746937346867344,
+  "eval_steps": 1142,
+  "global_step": 4998,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08750437521876094,
+      "grad_norm": 8.797028541564941,
+      "learning_rate": 1.824991249562478e-05,
+      "loss": 3.9704,
+      "step": 500
+    },
+    {
+      "epoch": 0.17500875043752187,
+      "grad_norm": 7.093753337860107,
+      "learning_rate": 1.6499824991249566e-05,
+      "loss": 3.6946,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19985999299965,
+      "eval_gen_len": 36.008,
+      "eval_loss": 3.3878133296966553,
+      "eval_rouge1": 0.1544,
+      "eval_rouge2": 0.0339,
+      "eval_rougeL": 0.1176,
+      "eval_rougeLsum": 0.1369,
+      "eval_runtime": 204.0944,
+      "eval_samples_per_second": 2.45,
+      "eval_steps_per_second": 0.157,
+      "step": 1142
+    },
+    {
+      "epoch": 0.2625131256562828,
+      "grad_norm": 9.073663711547852,
+      "learning_rate": 1.4749737486874345e-05,
+      "loss": 3.6103,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35001750087504374,
+      "grad_norm": 6.332721710205078,
+      "learning_rate": 1.2999649982499125e-05,
+      "loss": 3.5426,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3997199859993,
+      "eval_gen_len": 35.828,
+      "eval_loss": 3.291989326477051,
+      "eval_rouge1": 0.1731,
+      "eval_rouge2": 0.0402,
+      "eval_rougeL": 0.1319,
+      "eval_rougeLsum": 0.1527,
+      "eval_runtime": 208.9687,
+      "eval_samples_per_second": 2.393,
+      "eval_steps_per_second": 0.153,
+      "step": 2284
+    },
+    {
+      "epoch": 0.43752187609380466,
+      "grad_norm": 6.205784320831299,
+      "learning_rate": 1.1249562478123908e-05,
+      "loss": 3.4922,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5250262513125656,
+      "grad_norm": 6.974767208099365,
+      "learning_rate": 9.499474973748688e-06,
+      "loss": 3.4693,
+      "step": 3000
+    },
+    {
+      "epoch": 0.59957997899895,
+      "eval_gen_len": 40.762,
+      "eval_loss": 3.243711233139038,
+      "eval_rouge1": 0.1798,
+      "eval_rouge2": 0.0435,
+      "eval_rougeL": 0.1346,
+      "eval_rougeLsum": 0.1589,
+      "eval_runtime": 213.904,
+      "eval_samples_per_second": 2.337,
+      "eval_steps_per_second": 0.15,
+      "step": 3426
+    },
+    {
+      "epoch": 0.6125306265313266,
+      "grad_norm": 6.394979953765869,
+      "learning_rate": 7.749387469373469e-06,
+      "loss": 3.4334,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7000350017500875,
+      "grad_norm": 5.80218505859375,
+      "learning_rate": 5.999299964998251e-06,
+      "loss": 3.4327,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7875393769688485,
+      "grad_norm": 6.386791706085205,
+      "learning_rate": 4.2492124606230315e-06,
+      "loss": 3.3834,
+      "step": 4500
+    },
+    {
+      "epoch": 0.7994399719986,
+      "eval_gen_len": 46.808,
+      "eval_loss": 3.208350658416748,
+      "eval_rouge1": 0.1844,
+      "eval_rouge2": 0.0455,
+      "eval_rougeL": 0.1354,
+      "eval_rougeLsum": 0.1646,
+      "eval_runtime": 220.4208,
+      "eval_samples_per_second": 2.268,
+      "eval_steps_per_second": 0.145,
+      "step": 4568
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5714,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 714,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.75286608293888e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4998/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017e9030f15c6b5ed1ee902c56be0874b46cc54d0d58f23196bfc389bd6d9e2d
+size 5496