Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515b87cf0a6a3172ae5c57e520f7d2104f42512194d4ce128b9412164367303b
+oid sha256:6d1559d5c4ceadde2aa023f48dd93b8416f2f8aa0643389bcba68c12b992efa8
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3883c680b06616a54d83f9d39716d483ff373243037f1e452335ed8a9e5c4a7
+oid sha256:9f0c475760564744c662dab6ac098185417c8813fd6a2b68031142b7baf6f03e
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00d1c63ddb24d4f81ac1488700230d892db68acd5821c3502fd0057c64003c1
+oid sha256:961a595705c86d1e3825267783cc61e0ff8cf7fff9fd42c90081270529f9b97c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ab6338b810850df27c82b146a27ff4faf907486cbc0e08077af4440dd9d4fb
+oid sha256:12921cac8baef4519674a5132945a5195f3291a8d5b5367c7d05afa86f16027a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.669233772837662,
-  "best_model_checkpoint": "training_dir/checkpoint-3000",
-  "epoch": 0.31789763696089857,
+  "best_metric": 0.6877643727244785,
+  "best_model_checkpoint": "training_dir/checkpoint-4000",
+  "epoch": 0.4238635159478648,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,25 @@
       "eval_samples_per_second": 88.174,
       "eval_steps_per_second": 11.022,
       "step": 3000
+    },
+    {
+      "epoch": 0.4238635159478648,
+      "grad_norm": 9.338201522827148,
+      "learning_rate": 9.627143922445936e-06,
+      "loss": 0.5233,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4238635159478648,
+      "eval_accuracy": 0.7023601398601399,
+      "eval_f1": 0.6877643727244785,
+      "eval_loss": 0.9143859148025513,
+      "eval_precision": 0.7132978004907108,
+      "eval_recall": 0.7023601398601399,
+      "eval_runtime": 26.1039,
+      "eval_samples_per_second": 87.65,
+      "eval_steps_per_second": 10.956,
+      "step": 4000
     }
   ],
   "logging_steps": 1000,
@@ -83,7 +102,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2912647822914960.0,
+  "total_flos": 3879664659350064.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null