Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f04b87a850c8e1978cbcc919472d319a69545cea7249b6850d0c66548817b58c
+oid sha256:30bf6de385d691535d4c1d22fdfb3ba49448e62983d75bf56c54f75c3c1a8b1d
 size 1625545896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111fc2c7739ba419a0649fff6c653fe1ac707bedea828f93414bbd7128ac5a24
+oid sha256:fbd44a9b8822712623754f153b3e10a8a4606b43a9ed80e250d8fa95644c6bbb
 size 3250997519

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85836ff314397b6e9cda5d18b4e61802951efe26d6873089b5a8ec8a7fb5ae8
-size 14308
+oid sha256:2e0dee2946d739abedea828dc5f18e5164afb995d6abef97fe5c41e0ee0ce17c
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbabefdd804dedc5c232b0c700653c9873b9270f3c9973815bb3914f4fa8dadb
+oid sha256:004fc499cb40e3b895611c295aa6eacd35ec3d64c3847db0861c8802b04353a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "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,
+  "best_metric": 0.40889972448349,
+  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/kwsylgen/bart/bart-finetuned-kwsylgen-64/checkpoint-5000",
+  "epoch": 1.794043774668102,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,141 @@
       "eval_samples_per_second": 112.166,
       "eval_steps_per_second": 1.757,
       "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.4796440005302429,
+      "learning_rate": 4.82113383566559e-05,
+      "loss": 0.4133,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.43858015537261963,
+      "eval_runtime": 212.329,
+      "eval_samples_per_second": 111.539,
+      "eval_steps_per_second": 1.747,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.4028351306915283,
+      "learning_rate": 4.731431646932185e-05,
+      "loss": 0.3907,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.43201687932014465,
+      "eval_runtime": 213.8428,
+      "eval_samples_per_second": 110.75,
+      "eval_steps_per_second": 1.735,
+      "step": 1500
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6824278235435486,
+      "learning_rate": 4.6417294581987804e-05,
+      "loss": 0.3752,
+      "step": 2000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.4287361800670624,
+      "eval_runtime": 211.3439,
+      "eval_samples_per_second": 112.059,
+      "eval_steps_per_second": 1.755,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4877581298351288,
+      "learning_rate": 4.5520272694653755e-05,
+      "loss": 0.362,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.42700710892677307,
+      "eval_runtime": 211.5555,
+      "eval_samples_per_second": 111.947,
+      "eval_steps_per_second": 1.754,
+      "step": 2500
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.5196011066436768,
+      "learning_rate": 4.46232508073197e-05,
+      "loss": 0.3496,
+      "step": 3000
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.4205136299133301,
+      "eval_runtime": 217.1988,
+      "eval_samples_per_second": 109.038,
+      "eval_steps_per_second": 1.708,
+      "step": 3000
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.6311954855918884,
+      "learning_rate": 4.372622891998565e-05,
+      "loss": 0.3413,
+      "step": 3500
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.41408446431159973,
+      "eval_runtime": 217.6178,
+      "eval_samples_per_second": 108.828,
+      "eval_steps_per_second": 1.705,
+      "step": 3500
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.6342439651489258,
+      "learning_rate": 4.2829207032651594e-05,
+      "loss": 0.3315,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.4208415150642395,
+      "eval_runtime": 221.8644,
+      "eval_samples_per_second": 106.745,
+      "eval_steps_per_second": 1.672,
+      "step": 4000
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.7352110743522644,
+      "learning_rate": 4.1932185145317545e-05,
+      "loss": 0.3235,
+      "step": 4500
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.41450121998786926,
+      "eval_runtime": 212.3824,
+      "eval_samples_per_second": 111.511,
+      "eval_steps_per_second": 1.747,
+      "step": 4500
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.7556421160697937,
+      "learning_rate": 4.1035163257983496e-05,
+      "loss": 0.3171,
+      "step": 5000
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 0.40889972448349,
+      "eval_runtime": 213.3008,
+      "eval_samples_per_second": 111.031,
+      "eval_steps_per_second": 1.739,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -29,7 +164,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 4334209204224000.0,
+  "total_flos": 4.334019582571315e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null