Training in progress, epoch 0, checkpoint

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533a1fcff8670c30efaa23c1be076b1d5340afaec166739ee9b809d991510639
+size 1209927755

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbcf3a3f13e215815b7693e944a918928f7a3b03a38618d5564792012673e52c
+size 647700299

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c6d9c0320b45978c58f80575f066a636e621b61da460971046ab700393175e
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb791a2e6ed026a65ee8f5b003e276d36a70eb9547c8946e86b432cc72953c05
+size 1465

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 13.574521383946667,
+  "best_model_checkpoint": "./routed_longformer_docmt/checkpoint-786",
+  "epoch": 0.9993642720915448,
+  "eval_steps": 500,
+  "global_step": 786,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12714558169103624,
+      "grad_norm": 2.349264621734619,
+      "learning_rate": 2.875318066157761e-05,
+      "loss": 3.6286,
+      "step": 100
+    },
+    {
+      "epoch": 0.25429116338207247,
+      "grad_norm": 1.9311673641204834,
+      "learning_rate": 2.7480916030534352e-05,
+      "loss": 2.9688,
+      "step": 200
+    },
+    {
+      "epoch": 0.3814367450731087,
+      "grad_norm": 3.087153673171997,
+      "learning_rate": 2.6208651399491097e-05,
+      "loss": 2.7041,
+      "step": 300
+    },
+    {
+      "epoch": 0.5085823267641449,
+      "grad_norm": 1.7739580869674683,
+      "learning_rate": 2.494910941475827e-05,
+      "loss": 2.5374,
+      "step": 400
+    },
+    {
+      "epoch": 0.6357279084551812,
+      "grad_norm": 1.8503930568695068,
+      "learning_rate": 2.3676844783715012e-05,
+      "loss": 2.4237,
+      "step": 500
+    },
+    {
+      "epoch": 0.7628734901462174,
+      "grad_norm": 1.7974401712417603,
+      "learning_rate": 2.2417302798982186e-05,
+      "loss": 2.3547,
+      "step": 600
+    },
+    {
+      "epoch": 0.8900190718372537,
+      "grad_norm": 1.7522088289260864,
+      "learning_rate": 2.1157760814249364e-05,
+      "loss": 2.2865,
+      "step": 700
+    },
+    {
+      "epoch": 0.9993642720915448,
+      "eval_bleu": 13.574521383946667,
+      "eval_comet": 0.3645593269124563,
+      "eval_loss": 2.1787571907043457,
+      "eval_meteor": 0.2980500580872142,
+      "eval_runtime": 789.446,
+      "eval_samples_per_second": 1.771,
+      "eval_steps_per_second": 0.222,
+      "step": 786
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2358,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d595be4c6bce79b196dc595b0358180d19909846f5bc0199fe97844197fe3e3d
+size 5713