Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0abba34b52babffefb2f82cba7c36009ccaef311c6e4a28b418739a2a151c5
+oid sha256:eb61f4a482e6ffcf6d7b5f16f9bcd3ca9590a5954036318506e89a67e62fb396
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033376ece8b36a6f876ffc10a01626d819a545ec1afca952a95679b36d9772f6
+oid sha256:ff95c1975c47fefd9ccd0fef1a23b06211a1da604ecd300c56deebc9ed6b57ad
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e846afe3582f2fcd477783bade1200b6489d8d42923fdbc3868c5774daae483
+oid sha256:9c1b7080d07b1169a02459851d423f5e1ffc70f5f33eacf6a46972b5250a9c5b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27ebe124b49d962b3686f19f4ac88c29ccf1175d00244819004baf43745fc5ca
+oid sha256:87a047fc70d34ba9e25294567dfd8e018dbff83f6d11a990d60dd7e409be4fbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7466934407427619,
-  "best_model_checkpoint": "training_dir/checkpoint-5000",
-  "epoch": 0.7829627309740056,
+  "best_metric": 0.7624731472235634,
+  "best_model_checkpoint": "training_dir/checkpoint-6000",
+  "epoch": 0.9395552771688067,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,25 @@
       "eval_samples_per_second": 48.123,
       "eval_steps_per_second": 6.015,
       "step": 5000
+    },
+    {
+      "epoch": 0.9395552771688067,
+      "grad_norm": 16.726686477661133,
+      "learning_rate": 9.131944444444445e-06,
+      "loss": 0.4505,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9395552771688067,
+      "eval_accuracy": 0.7670454545454546,
+      "eval_f1": 0.7624731472235634,
+      "eval_loss": 0.7416993379592896,
+      "eval_precision": 0.7669396954578515,
+      "eval_recall": 0.7670454545454546,
+      "eval_runtime": 47.5056,
+      "eval_samples_per_second": 48.163,
+      "eval_steps_per_second": 6.02,
+      "step": 6000
     }
   ],
   "logging_steps": 1000,
@@ -121,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0241393782467456e+16,
+  "total_flos": 1.2293550995184144e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null