Training in progress, step 7000

{checkpoint-6000 → checkpoint-7000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbbd04456094b8f62f81be236b8f37719fbf607db2f5317a245e9f96531d3614
+oid sha256:e5ce3f709d5bf2ef52f9be3ee11720c11875cd7c7cbc5b113ff2ec13fbdcfad0
 size 267028677

{checkpoint-6000 → checkpoint-7000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5fe9ab1af707e6e666bf9069b7b56e145d52944efdb70375f4c403eaca7195
+oid sha256:4fdd9c25a3b2561db68e4954c56b65812fa0e930619abfda842bc9c9be92f795
 size 133523761

{checkpoint-6000 → checkpoint-7000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b084a0eea70333dcd8dbab59962a7694134fa08b5d76a92944b1542c36edaf1
+oid sha256:29da9df454e7746cda5ce0c1f5109f66bd169affee62d8d85c9b49f078e94f24
 size 14575

{checkpoint-6000 → checkpoint-7000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd027476f4332bd868b6e552f26649d456aa519924fdc5327d6864bb44c7b9e
+oid sha256:faac9c70fa11627d95e4ba1e0d56c13061abc404909001c070224e133cd0adf8
 size 627

{checkpoint-6000 → checkpoint-7000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4,
-  "global_step": 6000,
+  "epoch": 2.8,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -246,11 +246,63 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 4.057643890380859,
       "step": 5625
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.0004800000000001e-05,
+      "loss": 0.7523,
+      "step": 6250
+    },
+    {
+      "epoch": 2.5,
+      "eval_accuracy": 0.734,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.46658706665039,
+      "eval_f1": 0.7295923418650617,
+      "eval_gpu_ram_allocated": 0.39351463317871094,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 32,
+      "eval_loss": 0.8498074412345886,
+      "eval_precision": 0.7313935171526833,
+      "eval_recall": 0.734,
+      "eval_runtime": 15.7189,
+      "eval_samples_per_second": 1272.356,
+      "eval_steps_per_second": 39.761,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.8655662536621094,
+      "step": 6250
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.0048e-06,
+      "loss": 0.7396,
+      "step": 6875
+    },
+    {
+      "epoch": 2.75,
+      "eval_accuracy": 0.73645,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.466869354248047,
+      "eval_f1": 0.7326318327243708,
+      "eval_gpu_ram_allocated": 0.3934817314147949,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 33,
+      "eval_loss": 0.8402908444404602,
+      "eval_precision": 0.7323211491997443,
+      "eval_recall": 0.73645,
+      "eval_runtime": 15.1367,
+      "eval_samples_per_second": 1321.295,
+      "eval_steps_per_second": 41.29,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.8685684204101562,
+      "step": 6875
     }
   ],
   "max_steps": 12500,
   "num_train_epochs": 5,
-  "total_flos": 3048208430074752.0,
+  "total_flos": 3558041889513216.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54529faf9f7f062e28808f303e29fbb6fd53466445f34fc24c3b8832206ef78e
+oid sha256:4fdd9c25a3b2561db68e4954c56b65812fa0e930619abfda842bc9c9be92f795
 size 133523761

runs/Jul23_01-08-06_df8adf32a670/events.out.tfevents.1690074496.df8adf32a670.1420.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35db62b0f69c0659ee7f59a1fe2522d3881646109a0efa1ddab0e713d968a77c
-size 15902
+oid sha256:b9ac7f792ea22fc235d1b87725973015b45c098e2f1fae9c2407a9a80a92549f
+size 17004