Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8d3488e8a40d95324b5d59d9e28f847bb4ad4337cbab29278f2d71848c8154
+oid sha256:f04b87a850c8e1978cbcc919472d319a69545cea7249b6850d0c66548817b58c
 size 1625545896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba8df3e79cea54a0cf191a9d20a258a846fea397be360663639bf8078c188e1
+oid sha256:111fc2c7739ba419a0649fff6c653fe1ac707bedea828f93414bbd7128ac5a24
 size 3250997519

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292e3c34f31addb8e5d45c64c6c5a9fa41fab6787ec343f6cc668c14137bedb2
+oid sha256:b85836ff314397b6e9cda5d18b4e61802951efe26d6873089b5a8ec8a7fb5ae8
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1b75caef8dcf16fc2c3f168095032c1c816c3b909d9e4856126e54ea281ebd
+oid sha256:dbabefdd804dedc5c232b0c700653c9873b9270f3c9973815bb3914f4fa8dadb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,95 +1,35 @@
 {
-  "best_metric": 0.45656052231788635,
-  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/kwsylgen/bart/bart-finetuned-kwsylgen-64/checkpoint-2000",
-  "epoch": 1.7385257301808066,
+  "best_metric": 0.45187193155288696,
+  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/kwsylgen/bart/bart-finetuned-kwsylgen-64/checkpoint-500",
+  "epoch": 0.17940437746681018,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.35,
-      "grad_norm": 0.5149683952331543,
-      "learning_rate": 4.5679763560500696e-05,
-      "loss": 0.4749,
+      "epoch": 0.18,
+      "grad_norm": 0.534104585647583,
+      "learning_rate": 4.910836024398995e-05,
+      "loss": 0.486,
       "step": 500
     },
     {
-      "epoch": 0.35,
-      "eval_loss": 0.4616529643535614,
-      "eval_runtime": 93.1578,
-      "eval_samples_per_second": 136.371,
-      "eval_steps_per_second": 2.136,
+      "epoch": 0.18,
+      "eval_loss": 0.45187193155288696,
+      "eval_runtime": 211.1424,
+      "eval_samples_per_second": 112.166,
+      "eval_steps_per_second": 1.757,
       "step": 500
-    },
-    {
-      "epoch": 0.7,
-      "grad_norm": 0.5068113207817078,
-      "learning_rate": 4.133344923504868e-05,
-      "loss": 0.3922,
-      "step": 1000
-    },
-    {
-      "epoch": 0.7,
-      "eval_loss": 0.4581904709339142,
-      "eval_runtime": 93.9811,
-      "eval_samples_per_second": 135.176,
-      "eval_steps_per_second": 2.117,
-      "step": 1000
-    },
-    {
-      "epoch": 1.04,
-      "grad_norm": 0.6911681890487671,
-      "learning_rate": 3.698713490959667e-05,
-      "loss": 0.3655,
-      "step": 1500
-    },
-    {
-      "epoch": 1.04,
-      "eval_loss": 0.4568086564540863,
-      "eval_runtime": 93.8201,
-      "eval_samples_per_second": 135.408,
-      "eval_steps_per_second": 2.121,
-      "step": 1500
-    },
-    {
-      "epoch": 1.39,
-      "grad_norm": 0.5658309459686279,
-      "learning_rate": 3.2640820584144646e-05,
-      "loss": 0.3455,
-      "step": 2000
-    },
-    {
-      "epoch": 1.39,
-      "eval_loss": 0.45656052231788635,
-      "eval_runtime": 94.4047,
-      "eval_samples_per_second": 134.57,
-      "eval_steps_per_second": 2.108,
-      "step": 2000
-    },
-    {
-      "epoch": 1.74,
-      "grad_norm": 0.4761568605899811,
-      "learning_rate": 2.8294506258692632e-05,
-      "loss": 0.3291,
-      "step": 2500
-    },
-    {
-      "epoch": 1.74,
-      "eval_loss": 0.4570353031158447,
-      "eval_runtime": 95.9797,
-      "eval_samples_per_second": 132.361,
-      "eval_steps_per_second": 2.073,
-      "step": 2500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 5752,
+  "max_steps": 27870,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 2.166887891651789e+16,
+  "total_flos": 4334209204224000.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e6869522a097ec64314dcf3fed02e0d24916c5cedb8b01b2170c098b079f8a
+oid sha256:6e26ab58717131c0abe643633f423bce131a8848cdbb71c5c35dc1974207a9c7
 size 5368