Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f0bf969e7c4f10819387c514099288befb4d6a92b18fedb97919efb7838146
+oid sha256:cc781d4fe42e6432654e1870cb89122dc1779571f97b3368cac763d149c179c6
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50326021a12350d0fd340fb39b69dcb99c4d9d7625607f1ea78848e8533735ef
+oid sha256:c480a79986a9324e56009cbfffe3ce2c159495030d19916cb8eceb85e6eb6c47
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aba6f3b60d25e9d80bfa48704513608d3c51338a99fc68164f2cda5539a2e88
+oid sha256:f88d979933c32dc472f41ac1057650933f8e3f97e8756c84857a83fcd3723c20
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b18b3eda07668461b2815107443aa6a6c68056a4e1c0be8b74117cc02ff9391
+oid sha256:50284aeeef15b76b3e429d017933740783393c66d3932640c0600cbe6c9ede27
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2167d86470a0af7e2c7e124cb3b9e089d70c4424875cd5dabb7a3f9dabe21d16
+oid sha256:32ea2c91d36474b100bc2bfe7dbfa12a58f0438100ede285e747c4f76e5d7201
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 6500,
-  "best_metric": 1.5628445148468018,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-6500",
-  "epoch": 2.894058717128148,
+  "best_global_step": 7000,
+  "best_metric": 1.5605802536010742,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-7000",
+  "epoch": 3.1171003200222622,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1022,6 +1022,84 @@
       "eval_samples_per_second": 389.105,
       "eval_steps_per_second": 48.653,
       "step": 6500
+    },
+    {
+      "epoch": 2.916321135383331,
+      "grad_norm": 1.0452390909194946,
+      "learning_rate": 5e-05,
+      "loss": 1.6794,
+      "step": 6550
+    },
+    {
+      "epoch": 2.938583553638514,
+      "grad_norm": 1.338881254196167,
+      "learning_rate": 5e-05,
+      "loss": 1.6678,
+      "step": 6600
+    },
+    {
+      "epoch": 2.960845971893697,
+      "grad_norm": 0.989860475063324,
+      "learning_rate": 5e-05,
+      "loss": 1.6753,
+      "step": 6650
+    },
+    {
+      "epoch": 2.98310839014888,
+      "grad_norm": 1.1380687952041626,
+      "learning_rate": 5e-05,
+      "loss": 1.6639,
+      "step": 6700
+    },
+    {
+      "epoch": 3.0057882287463475,
+      "grad_norm": 1.2292852401733398,
+      "learning_rate": 5e-05,
+      "loss": 1.697,
+      "step": 6750
+    },
+    {
+      "epoch": 3.0280506470015305,
+      "grad_norm": 1.1919242143630981,
+      "learning_rate": 5e-05,
+      "loss": 1.6714,
+      "step": 6800
+    },
+    {
+      "epoch": 3.0503130652567134,
+      "grad_norm": 1.1312869787216187,
+      "learning_rate": 5e-05,
+      "loss": 1.6641,
+      "step": 6850
+    },
+    {
+      "epoch": 3.0725754835118964,
+      "grad_norm": 1.3589369058609009,
+      "learning_rate": 5e-05,
+      "loss": 1.655,
+      "step": 6900
+    },
+    {
+      "epoch": 3.0948379017670793,
+      "grad_norm": 1.257063627243042,
+      "learning_rate": 5e-05,
+      "loss": 1.6661,
+      "step": 6950
+    },
+    {
+      "epoch": 3.1171003200222622,
+      "grad_norm": 1.3228737115859985,
+      "learning_rate": 5e-05,
+      "loss": 1.653,
+      "step": 7000
+    },
+    {
+      "epoch": 3.1171003200222622,
+      "eval_loss": 1.5605802536010742,
+      "eval_runtime": 42.9947,
+      "eval_samples_per_second": 371.464,
+      "eval_steps_per_second": 46.448,
+      "step": 7000
     }
   ],
   "logging_steps": 50,
@@ -1050,7 +1128,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8160444868950016e+16,
+  "total_flos": 2.864099321051136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null