Training in progress, step 5000

{checkpoint-4000 → checkpoint-5000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e017f3e5e3f71805ff6a4c99f2f878632fdd85ec1aadaf54c97e664f2e90325
+oid sha256:bee161d119a3ea04cbc152488336fe12942c45f8c6440c64d581a6ae7a63e196
 size 267028677

{checkpoint-4000 → checkpoint-5000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44d535140a434239ed465428ed5b9d4e245326c2f44d0f879e5cd00fe2d8957
+oid sha256:352e9a72b0498ab48a08358e98d0673b58915c4301f40fcfe731efb083ca1d46
 size 133523761

{checkpoint-4000 → checkpoint-5000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e111cd6a3fa0777b933b67a9b687f8b1a6cdffcb7b78c30980ed10a25fd236
+oid sha256:a0555291b2a6c57ddfbb94f07b1757a918e0eee55f74c1919774fc03e4c73ad3
 size 14575

{checkpoint-4000 → checkpoint-5000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea5d0fb071177180fb9d5725b5e9c9e593749104f2b2b5042fb0640b36dd92a8
+oid sha256:c13f5c121b0ca6f58116019336ba0d3c1b65f5195038f1617b67d9c0d670124f
 size 627

{checkpoint-4000 → checkpoint-5000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6,
-  "global_step": 4000,
+  "epoch": 2.0,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -168,11 +168,63 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 3.822803497314453,
       "step": 3750
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.30032e-05,
+      "loss": 0.8229,
+      "step": 4375
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.7347,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.4658203125,
+      "eval_f1": 0.7306008054961884,
+      "eval_gpu_ram_allocated": 0.3934760093688965,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 32,
+      "eval_loss": 0.8477036952972412,
+      "eval_precision": 0.7313531828325577,
+      "eval_recall": 0.7347,
+      "eval_runtime": 15.2385,
+      "eval_samples_per_second": 1312.463,
+      "eval_steps_per_second": 41.014,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.870433807373047,
+      "step": 4375
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2003200000000002e-05,
+      "loss": 0.8227,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7321,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.466053009033203,
+      "eval_f1": 0.729989989450906,
+      "eval_gpu_ram_allocated": 0.3935103416442871,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 34,
+      "eval_loss": 0.8513504862785339,
+      "eval_precision": 0.7342944597310201,
+      "eval_recall": 0.7321,
+      "eval_runtime": 15.2256,
+      "eval_samples_per_second": 1313.581,
+      "eval_steps_per_second": 41.049,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.8656463623046875,
+      "step": 5000
     }
   ],
   "max_steps": 12500,
   "num_train_epochs": 5,
-  "total_flos": 2029323862226304.0,
+  "total_flos": 2542920841875456.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92dd031ea0147cdd11efa827459da3ffad496bcc0ec309a05d86228fd1c75a6
+oid sha256:352e9a72b0498ab48a08358e98d0673b58915c4301f40fcfe731efb083ca1d46
 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 sha256:648cc85381d7e688f83f96d7ca557848678b8614de251a966af0fa8b70c31bb2
-size 12596
+oid sha256:fd2b39e54f4352ae95d2ac35fe20b48d1b9a815dd5b0a3cb67935a686b5bee85
+size 13698