Training in progress, step 2000, checkpoint

last-checkpoint/generation_config.json

@@ -1,13 +1,24 @@
 {
-  "_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,
-  "no_repeat_ngram_size": 3,
+  "max_new_tokens": 64,
+  "n_examples": null,
+  "no_repeat_ngram_size": 2,
   "num_beams": 4,
-  "pad_token_id": 1,
-  "transformers_version": "4.38.2"
+  "pad_to_max_length": true,
+  "pad_token_id": 2,
+  "padding": "max_length",
+  "renormalize_logits": true,
+  "skip_special_tokens": true,
+  "temperature": 0.85,
+  "top_k": 0,
+  "top_p": 0.9,
+  "transformers_version": "4.38.2",
+  "truncation": true
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659581b09e5435748aa277550674f0f183b697f5746c508d9651061cf462dbdc
+oid sha256:d2ba30ac64371eeec3bd9f7d0012d18ad31fd4368aa5d5c706726544da918373
 size 1625545896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8c99e5062570ad4317ac2151da95c1bd97ba41c7778e5f6b3e94ba9039c805
+oid sha256:3511177efc1c7eb3119fc64d63abdc1a1ca2b56b0204fccca0ec090d4b49e3b7
 size 3250997519

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16834af344003484ce1ba6dc7abd13a4095886a927379926cec2957d37a23fe9
+oid sha256:36c96bc430eb6a2b1f5305099d0805f117cad183edcf598d7c9e7eefabcd26d1
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5799947fee402d2d731ff73eaff922e4f5de0fe21f2d43fabaefdb89f537da
+oid sha256:c1474d57875cd322d43d7b30e8e912f7e2d36108fe51ad2985da2b427239c760
 size 1064

last-checkpoint/trainer_state.json

@@ -1,42 +1,72 @@
 {
-  "best_metric": 0.4577435553073883,
-  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/kwsylgen/bart/bart-finetuned-kwsylgen-64/checkpoint-1000",
-  "epoch": 0.6954102920723226,
+  "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": 1.3908205841446453,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.35,
-      "grad_norm": 0.605933427810669,
+      "grad_norm": 0.5149683952331543,
       "learning_rate": 4.5679763560500696e-05,
-      "loss": 0.476,
+      "loss": 0.4749,
       "step": 500
     },
     {
       "epoch": 0.35,
-      "eval_loss": 0.4631631374359131,
-      "eval_runtime": 98.3831,
-      "eval_samples_per_second": 129.128,
-      "eval_steps_per_second": 2.023,
+      "eval_loss": 0.4616529643535614,
+      "eval_runtime": 93.1578,
+      "eval_samples_per_second": 136.371,
+      "eval_steps_per_second": 2.136,
       "step": 500
     },
     {
       "epoch": 0.7,
-      "grad_norm": 0.46590879559516907,
+      "grad_norm": 0.5068113207817078,
       "learning_rate": 4.133344923504868e-05,
-      "loss": 0.3918,
+      "loss": 0.3922,
       "step": 1000
     },
     {
       "epoch": 0.7,
-      "eval_loss": 0.4577435553073883,
-      "eval_runtime": 102.7478,
-      "eval_samples_per_second": 123.643,
-      "eval_steps_per_second": 1.937,
+      "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
     }
   ],
   "logging_steps": 500,
@@ -44,7 +74,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 8668418408448000.0,
+  "total_flos": 1.7334669712293888e+16,
   "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:a49400ed8744cf57f1a96430857f2cb498143627b7bf3e102c3bef48e432100f
+oid sha256:17e6869522a097ec64314dcf3fed02e0d24916c5cedb8b01b2170c098b079f8a
 size 5368