Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bcdb51423150a134e6e9e538e83ac0241e437ee06e4f207a1520097481f789
+oid sha256:15bdcc4341a2712fd2b7ed826f5620086eb78fa487c5a45b254a2bdd4edfffef
 size 1625525396

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057757861d66f1ae8c1ae01875cb7429fe6c6dda10b3e6c3ad5f56232bde4e85
+oid sha256:3fb22564fe20913a05418ec34066edda9eda8601abf3ec0ae336fd3e5dbb5b6b
 size 3250956559

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333ba09bff458e71dc26fed46a13a420cd849a9ad71efe06b014f5627bab7dcc
-size 14244
+oid sha256:2a3a7c42f21aa6b5889a1847211138f7a68b52d5fe02636e7e81b54607fa833f
+size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441fe55200e88247d0cb84c3a5d41f73058895b59e0666b89da76a37ed964576
+oid sha256:e7592e941fa77449d9f7015724b6a3901e596c11e155596880b96def1f284283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "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,
+  "best_metric": 2.9601285457611084,
+  "best_model_checkpoint": "/content/drive/MyDrive/W210 Capstone - Lyric Generation with Melody/loaf/models/lyrlen/bart/bart-finetuned-lyrlen-128-tokens/checkpoint-1500",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,36 @@
       "eval_samples_per_second": 22.741,
       "eval_steps_per_second": 1.425,
       "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.5961496829986572,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.0614,
+      "step": 1000
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 3.0103020668029785,
+      "eval_runtime": 130.3818,
+      "eval_samples_per_second": 23.009,
+      "eval_steps_per_second": 1.442,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.4491631984710693,
+      "learning_rate": 0.0,
+      "loss": 3.0034,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.9601285457611084,
+      "eval_runtime": 134.9259,
+      "eval_samples_per_second": 22.234,
+      "eval_steps_per_second": 1.393,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -29,7 +59,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2167104602112000.0,
+  "total_flos": 6501313806336000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null