Training in progress, step 3000

{checkpoint-2000 → checkpoint-3000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58f2992dce0a276542ee3f8a596878b450adfca2d0f5d0e4de79226ca26aeb4
+oid sha256:64edb2197e4a02d1438df6c12e0bbb460d1e6673d1fb9174ba614a5a07e80957
 size 267028677

{checkpoint-2000 → checkpoint-3000}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8826b5e400ad3e74a54646acac0427e30e9c65f59b522624a3b1972f74b63272
+oid sha256:4eaa6bb4f1349cc4cec62d98240c0f477ed3a72cdf61a64e107136111005e5b2
 size 133523761

{checkpoint-2000 → checkpoint-3000}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54afc05d1dccae527b37df270cb8239795e29851782c9bf4a45384c9f6328912
+oid sha256:7c4cf95fbdc5632d53278c37bf071ac945c409d09bf836b347e9a859e4e511dd
 size 14575

{checkpoint-2000 → checkpoint-3000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48528e3911b6482b407d43a6edd7a9bb566d94b939b0306e61e4d57fa64d1556
+oid sha256:28ebf07f702c69565fa7a80d4c72262cbf4c345b85539534a32cfd12ad3e3ec2
 size 627

{checkpoint-2000 → checkpoint-3000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
-  "global_step": 2000,
+  "epoch": 1.2,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,11 +90,37 @@
       "eval_system_ram_total": 83.48074722290039,
       "eval_system_ram_used": 3.863994598388672,
       "step": 1875
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6001600000000003e-05,
+      "loss": 0.9244,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7286,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 26.464874267578125,
+      "eval_f1": 0.721912767172515,
+      "eval_gpu_ram_allocated": 0.39352893829345703,
+      "eval_gpu_ram_cached": 16.05078125,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 32,
+      "eval_loss": 0.8794927000999451,
+      "eval_precision": 0.7265669055087627,
+      "eval_recall": 0.7286,
+      "eval_runtime": 15.2593,
+      "eval_samples_per_second": 1310.678,
+      "eval_steps_per_second": 40.959,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 3.881519317626953,
+      "step": 2500
     }
   ],
   "max_steps": 12500,
   "num_train_epochs": 5,
-  "total_flos": 1019551625041152.0,
+  "total_flos": 1524703331219712.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf78805be3130057169a1af6519260a1ffe7f065200afed84d70add13a521e3
+oid sha256:4eaa6bb4f1349cc4cec62d98240c0f477ed3a72cdf61a64e107136111005e5b2
 size 133523761