Training in progress, step 9000

{checkpoint-8000 → checkpoint-9000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abe0e8f69303d52151b969a2c04c7af80d0cf5c07bb60230685b54fb6a90681
+oid sha256:b2aaa514a645b3543ce5eed9aa79ddf13738a23c43efec01f7783f6f91edc976
 size 267028677

{checkpoint-8000 → checkpoint-9000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b50c95651d8742468f5f1edbb4c2a14528dd86e25791b998adf152efec55c433
+oid sha256:79f5061e5a30af545971dc68a923c602fdcaefe82abfb235cb7eb3cfc6f0461e
 size 133523761

{checkpoint-8000 → checkpoint-9000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc55218bdc42ff7df739a80eaf2657105d315fc0b250d25ef07f483b21f49a9
+oid sha256:b8905509a997e07d858d9bf12354f357592c998338dceb452007c9f660165126
 size 14575

{checkpoint-8000 → checkpoint-9000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671cc681d0ecb84643611d2563b43c627f5dae632f0d2170fd28d187ec353ec1
+oid sha256:119e088f3274dbc64560596e1bafffa29de6f0e97bfe9f98610ffd8b8271fda9
 size 627

{checkpoint-8000 → checkpoint-9000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.2,
-  "global_step": 8000,
+  "epoch": 3.6,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -324,11 +324,63 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 3.8610610961914062,
       "step": 7500
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 7.0048e-06,
+      "loss": 0.6929,
+      "step": 8125
+    },
+    {
+      "epoch": 3.25,
+      "eval_accuracy": 0.73505,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.468040466308594,
+      "eval_f1": 0.7321519443896675,
+      "eval_gpu_ram_allocated": 0.39360761642456055,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 29,
+      "eval_loss": 0.855096697807312,
+      "eval_precision": 0.7376195934146232,
+      "eval_recall": 0.73505,
+      "eval_runtime": 15.2462,
+      "eval_samples_per_second": 1311.799,
+      "eval_steps_per_second": 40.994,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.056495666503906,
+      "step": 8125
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 6.0048000000000005e-06,
+      "loss": 0.6772,
+      "step": 8750
+    },
+    {
+      "epoch": 3.5,
+      "eval_accuracy": 0.738,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.468387603759766,
+      "eval_f1": 0.7334835535994888,
+      "eval_gpu_ram_allocated": 0.3935232162475586,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 31,
+      "eval_loss": 0.84714674949646,
+      "eval_precision": 0.7326757628965238,
+      "eval_recall": 0.738,
+      "eval_runtime": 15.3571,
+      "eval_samples_per_second": 1302.33,
+      "eval_steps_per_second": 40.698,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.835094451904297,
+      "step": 8750
     }
   ],
   "max_steps": 12500,
   "num_train_epochs": 5,
-  "total_flos": 4064276534220672.0,
+  "total_flos": 4574352934241664.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d19e08ba096c383cb407dec2f4cecd928204b303f09a66a53ca72692cc9ce44
+oid sha256:79f5061e5a30af545971dc68a923c602fdcaefe82abfb235cb7eb3cfc6f0461e
 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 sha256:04c5b433cdb9e1eccd5068c69d47c3726823edfdd4d7bc5d52c436d1954f52bb
-size 19208
+oid sha256:391f5f9f0ccddb11061193f1ce4a643a7a8ea6d38d9ce3a93250aa260c6e5b18
+size 20310