Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -70,5 +70,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50266
 }

last-checkpoint/generation_config.json

@@ -1,13 +1,25 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
+  "clean_up_tokenization_spaces": true,
   "decoder_start_token_id": 2,
+  "do_sample": true,
   "early_stopping": true,
   "eos_token_id": 2,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "max_new_tokens": 512,
+  "min_new_tokens": 128,
+  "n_examples": null,
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.39.3"
+  "padding": "max_length",
+  "renormalize_logits": true,
+  "repetition_penalty": 0.6,
+  "skip_special_tokens": true,
+  "temperature": 0.85,
+  "top_k": 0,
+  "top_p": 0.9,
+  "transformers_version": "4.39.3",
+  "truncation": true
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a524d8ba515353da172f3ea29869d4f5f00248b6d2240eed45c56334429fd438
-size 1625426996
+oid sha256:bd0c5d1a06334178c514a152dd882e679196e9868a59af7410748d27894ac32c
+size 1625431096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0027089ec21b8d311f17fffcc479548564f54962fcf65bad2bca1f5a26f0401
-size 3250759951
+oid sha256:6ac5ac3c62d050e51d00061c2322dbd23123261ca56b37d80731f50d946fc74a
+size 3250768143

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1cd061e18f9b50a57b16facc0f8e912690855b9236bc6da220d4623bf5e43d
+oid sha256:7e0a4e9ea4482d0bb626a007aaa253cff387f0e1939224e8a014c99a65084df8
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed6fc6c0be5639a175fb541ebe63899052d1e643a0aac07601ff1059d2c27f3
+oid sha256:8efdbb74ab678951ea69a6311703aa1542d2a82a0472c9e6d420dde455af8e63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,140 +1,35 @@
 {
-  "best_metric": 0.8160156011581421,
-  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/loaf/bart/bart-finetuned-loaf-512-lyrictoplan/checkpoint-4000",
-  "epoch": 3.5618878005342833,
+  "best_metric": 3.263693332672119,
+  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/loaf/bart/bart-finetuned-loaf-512-lyrictoplan/checkpoint-500",
+  "epoch": 0.4452359750667854,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.45,
-      "grad_norm": 5.676259994506836,
-      "learning_rate": 4.443455031166518e-05,
-      "loss": 1.4176,
+      "grad_norm": 29.74579620361328,
+      "learning_rate": 4.271297120807361e-05,
+      "loss": 2.451,
       "step": 500
     },
     {
       "epoch": 0.45,
-      "eval_loss": 1.1072946786880493,
-      "eval_runtime": 98.8901,
-      "eval_samples_per_second": 6.29,
-      "eval_steps_per_second": 1.578,
+      "eval_loss": 3.263693332672119,
+      "eval_runtime": 39.3865,
+      "eval_samples_per_second": 15.792,
+      "eval_steps_per_second": 3.961,
       "step": 500
-    },
-    {
-      "epoch": 0.89,
-      "grad_norm": 7.331023216247559,
-      "learning_rate": 3.886910062333037e-05,
-      "loss": 1.1228,
-      "step": 1000
-    },
-    {
-      "epoch": 0.89,
-      "eval_loss": 0.9914930462837219,
-      "eval_runtime": 99.0385,
-      "eval_samples_per_second": 6.28,
-      "eval_steps_per_second": 1.575,
-      "step": 1000
-    },
-    {
-      "epoch": 1.34,
-      "grad_norm": 2.772461414337158,
-      "learning_rate": 3.330365093499555e-05,
-      "loss": 0.9568,
-      "step": 1500
-    },
-    {
-      "epoch": 1.34,
-      "eval_loss": 0.9346542358398438,
-      "eval_runtime": 99.0311,
-      "eval_samples_per_second": 6.281,
-      "eval_steps_per_second": 1.575,
-      "step": 1500
-    },
-    {
-      "epoch": 1.78,
-      "grad_norm": 4.1792778968811035,
-      "learning_rate": 2.7738201246660732e-05,
-      "loss": 0.888,
-      "step": 2000
-    },
-    {
-      "epoch": 1.78,
-      "eval_loss": 0.8794981241226196,
-      "eval_runtime": 98.9567,
-      "eval_samples_per_second": 6.286,
-      "eval_steps_per_second": 1.576,
-      "step": 2000
-    },
-    {
-      "epoch": 2.23,
-      "grad_norm": 2.9945931434631348,
-      "learning_rate": 2.2172751558325912e-05,
-      "loss": 0.8179,
-      "step": 2500
-    },
-    {
-      "epoch": 2.23,
-      "eval_loss": 0.8773565888404846,
-      "eval_runtime": 99.5216,
-      "eval_samples_per_second": 6.25,
-      "eval_steps_per_second": 1.567,
-      "step": 2500
-    },
-    {
-      "epoch": 2.67,
-      "grad_norm": 1.6972075700759888,
-      "learning_rate": 1.6607301869991096e-05,
-      "loss": 0.7929,
-      "step": 3000
-    },
-    {
-      "epoch": 2.67,
-      "eval_loss": 0.8550799489021301,
-      "eval_runtime": 99.4863,
-      "eval_samples_per_second": 6.252,
-      "eval_steps_per_second": 1.568,
-      "step": 3000
-    },
-    {
-      "epoch": 3.12,
-      "grad_norm": 1.3822712898254395,
-      "learning_rate": 1.1041852181656279e-05,
-      "loss": 0.7256,
-      "step": 3500
-    },
-    {
-      "epoch": 3.12,
-      "eval_loss": 0.8212681412696838,
-      "eval_runtime": 99.4565,
-      "eval_samples_per_second": 6.254,
-      "eval_steps_per_second": 1.569,
-      "step": 3500
-    },
-    {
-      "epoch": 3.56,
-      "grad_norm": 2.2662038803100586,
-      "learning_rate": 5.476402493321461e-06,
-      "loss": 0.6979,
-      "step": 4000
-    },
-    {
-      "epoch": 3.56,
-      "eval_loss": 0.8160156011581421,
-      "eval_runtime": 99.3184,
-      "eval_samples_per_second": 6.263,
-      "eval_steps_per_second": 1.571,
-      "step": 4000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4492,
+  "max_steps": 3369,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1.7327084846186496e+16,
+  "total_flos": 2167104602112000.0,
   "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:f998e93eefaec729748687a686b83a7b841a02229dd7c4807b29862479a3dc23
+oid sha256:14ba679ed25fed17e1d592e85271f6f57742fd304dbe529e46555f0566aaa169
 size 5432