Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c12d7f2593a757af810a868812a1d71436bdcae28efdf85ea7f38a4fc746ec5
+oid sha256:b6827d008d9d4aa1d33ebd5114f2e6aec21c34611adb57234406e55f04767d8d
 size 1625422896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6ec307772c725d237ce53ed00072c43daaa5b943c6ff8a9da9770286617faa
+oid sha256:32937b908f067c2992afcbd5006376f6501d018d1543873b1adbc0eb3af78b66
 size 3250751759

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88b29d6e52643dde49d0cb58cc10992cdfe46f6b308a65f4ae40f4c3e286477
+oid sha256:9739f47ce3993debf7abf052444a7cacfe7a7344541e97f8d68b5bcccd87df17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688b62605b5df52f5fec25b0648081ab1c61e87d91d24d2c5606b1fd6ec87baf
+oid sha256:f703cd7922f54f41516d5ce900f74f70f626e6131121e3f10bc8556c6d3d8af4
 size 1064

last-checkpoint/tokenizer_config.json

@@ -48,10 +48,17 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 256,
   "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9896907216494846,
+  "epoch": 1.9896907216494846,
   "eval_steps": 500,
-  "global_step": 63,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27,6 +27,26 @@
       "eval_samples_per_second": 0.351,
       "eval_steps_per_second": 0.088,
       "step": 63
+    },
+    {
+      "epoch": 1.9896907216494846,
+      "grad_norm": 1.331000566482544,
+      "learning_rate": 9e-06,
+      "loss": 2.6117,
+      "step": 126
+    },
+    {
+      "epoch": 1.9896907216494846,
+      "eval_gen_len": 254.757744,
+      "eval_loss": 2.461825132369995,
+      "eval_rouge1": 0.378265,
+      "eval_rouge2": 0.077138,
+      "eval_rougeL": 0.182503,
+      "eval_rougeLsum": 0.351427,
+      "eval_runtime": 3653.2761,
+      "eval_samples_per_second": 0.345,
+      "eval_steps_per_second": 0.086,
+      "step": 126
     }
   ],
   "logging_steps": 500,
@@ -34,7 +54,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 1.765106698420224e+16,
+  "total_flos": 3.530213396840448e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caad959ae301f6d09f2d4b89a83e21da46692e815b332784c72ea6ba5f60dc2b
+oid sha256:9345dd68c98da773799b72393992df8416b90fe1be028abc820aaf776d08511d
 size 5112