Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -70,5 +70,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.40.0.dev0",
   "use_cache": true,
-  "vocab_size": 50286
+  "vocab_size": 50289
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df31b4a5e56132ea8ae35ed1bd4dea2f3c52f182a000a06969a4066c5c7514f6
-size 1625513096
+oid sha256:01bcdb51423150a134e6e9e538e83ac0241e437ee06e4f207a1520097481f789
+size 1625525396

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa96591d7d61f01c30102e1a9e61609755d2a62609e1b717c50fa7703c6f1089
-size 3250931983
+oid sha256:057757861d66f1ae8c1ae01875cb7429fe6c6dda10b3e6c3ad5f56232bde4e85
+size 3250956559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2359fee00ba5d131fe31cd30a6732127d6476bef7d18d093ccdc1436d02d130b
-size 14308
+oid sha256:333ba09bff458e71dc26fed46a13a420cd849a9ad71efe06b014f5627bab7dcc
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3639a21adec6316397ddf46df39adb14bf2c1acdddc7615711b1520a3e25eb1e
+oid sha256:441fe55200e88247d0cb84c3a5d41f73058895b59e0666b89da76a37ed964576
 size 1064

last-checkpoint/trainer_state.json

@@ -1,200 +1,35 @@
 {
-  "best_metric": 2.896005868911743,
-  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/lyrlen/bart/bart-finetuned-lyrlen-128-tokens/checkpoint-4500",
-  "epoch": 4.0,
+  "best_metric": 3.000533103942871,
+  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/lyrlen/bart/bart-finetuned-lyrlen-128-tokens/checkpoint-500",
+  "epoch": 0.3333333333333333,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.33,
-      "grad_norm": 2.3970043659210205,
-      "learning_rate": 4.5833333333333334e-05,
-      "loss": 3.2981,
+      "grad_norm": 3.941305637359619,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 3.278,
       "step": 500
     },
     {
       "epoch": 0.33,
-      "eval_loss": 3.0587222576141357,
-      "eval_runtime": 130.1009,
-      "eval_samples_per_second": 23.059,
-      "eval_steps_per_second": 1.445,
+      "eval_loss": 3.000533103942871,
+      "eval_runtime": 131.9187,
+      "eval_samples_per_second": 22.741,
+      "eval_steps_per_second": 1.425,
       "step": 500
-    },
-    {
-      "epoch": 0.67,
-      "grad_norm": 2.09039044380188,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 3.0335,
-      "step": 1000
-    },
-    {
-      "epoch": 0.67,
-      "eval_loss": 2.976158857345581,
-      "eval_runtime": 130.8207,
-      "eval_samples_per_second": 22.932,
-      "eval_steps_per_second": 1.437,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 3.244218587875366,
-      "learning_rate": 3.7500000000000003e-05,
-      "loss": 2.9525,
-      "step": 1500
-    },
-    {
-      "epoch": 1.0,
-      "eval_loss": 2.9431517124176025,
-      "eval_runtime": 129.2605,
-      "eval_samples_per_second": 23.209,
-      "eval_steps_per_second": 1.454,
-      "step": 1500
-    },
-    {
-      "epoch": 1.33,
-      "grad_norm": 2.3262383937835693,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 2.9021,
-      "step": 2000
-    },
-    {
-      "epoch": 1.33,
-      "eval_loss": 2.956195592880249,
-      "eval_runtime": 129.8737,
-      "eval_samples_per_second": 23.099,
-      "eval_steps_per_second": 1.448,
-      "step": 2000
-    },
-    {
-      "epoch": 1.67,
-      "grad_norm": 2.195279598236084,
-      "learning_rate": 2.916666666666667e-05,
-      "loss": 2.8671,
-      "step": 2500
-    },
-    {
-      "epoch": 1.67,
-      "eval_loss": 2.9502499103546143,
-      "eval_runtime": 129.9739,
-      "eval_samples_per_second": 23.082,
-      "eval_steps_per_second": 1.446,
-      "step": 2500
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 2.360499382019043,
-      "learning_rate": 2.5e-05,
-      "loss": 2.8037,
-      "step": 3000
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 2.913353204727173,
-      "eval_runtime": 130.2228,
-      "eval_samples_per_second": 23.037,
-      "eval_steps_per_second": 1.444,
-      "step": 3000
-    },
-    {
-      "epoch": 2.33,
-      "grad_norm": 2.184467077255249,
-      "learning_rate": 2.0833333333333336e-05,
-      "loss": 2.7389,
-      "step": 3500
-    },
-    {
-      "epoch": 2.33,
-      "eval_loss": 2.9057974815368652,
-      "eval_runtime": 129.5421,
-      "eval_samples_per_second": 23.158,
-      "eval_steps_per_second": 1.451,
-      "step": 3500
-    },
-    {
-      "epoch": 2.67,
-      "grad_norm": 2.1960461139678955,
-      "learning_rate": 1.6666666666666667e-05,
-      "loss": 2.7305,
-      "step": 4000
-    },
-    {
-      "epoch": 2.67,
-      "eval_loss": 2.9016354084014893,
-      "eval_runtime": 133.3947,
-      "eval_samples_per_second": 22.49,
-      "eval_steps_per_second": 1.409,
-      "step": 4000
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 2.1077606678009033,
-      "learning_rate": 1.25e-05,
-      "loss": 2.7196,
-      "step": 4500
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 2.896005868911743,
-      "eval_runtime": 133.0227,
-      "eval_samples_per_second": 22.553,
-      "eval_steps_per_second": 1.413,
-      "step": 4500
-    },
-    {
-      "epoch": 3.33,
-      "grad_norm": 2.1256420612335205,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 2.7217,
-      "step": 5000
-    },
-    {
-      "epoch": 3.33,
-      "eval_loss": 2.9097442626953125,
-      "eval_runtime": 135.8274,
-      "eval_samples_per_second": 22.087,
-      "eval_steps_per_second": 1.384,
-      "step": 5000
-    },
-    {
-      "epoch": 3.67,
-      "grad_norm": 2.5816872119903564,
-      "learning_rate": 4.166666666666667e-06,
-      "loss": 2.6659,
-      "step": 5500
-    },
-    {
-      "epoch": 3.67,
-      "eval_loss": 2.9044690132141113,
-      "eval_runtime": 151.0962,
-      "eval_samples_per_second": 19.855,
-      "eval_steps_per_second": 1.244,
-      "step": 5500
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 2.135594367980957,
-      "learning_rate": 0.0,
-      "loss": 2.6616,
-      "step": 6000
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 2.9007933139801025,
-      "eval_runtime": 134.807,
-      "eval_samples_per_second": 22.254,
-      "eval_steps_per_second": 1.395,
-      "step": 6000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 6000,
+  "max_steps": 1500,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2.6005255225344e+16,
+  "total_flos": 2167104602112000.0,
   "train_batch_size": 16,
   "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:ce994ff3b06e2eb80c3fce5805bc05343bf1dccad088e68bde239a33ab1047d0
+oid sha256:2befca1929a268b5d8512d98f0406e042b2c61d35610fcaddab16419f0b1149e
 size 5432