Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:989292e28f46dd6f0df4532e0dda10c72a82df895ad59806e1ad4eb0f00f3737
+oid sha256:97477183783427f4a0e6c4c64c89c2ff713711937ba50a0a7f0ebc2c0beb19eb
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f1f84bc456597fb5c2700b82cca9533a78045c18a462826756c01550f7ba36
+oid sha256:8e3b341e9e13369ba57399436690c86adca73b7a520cae93fbc7be3f277f55d6
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49210297757a71fde0369659ddff3f1ed351704ff09f7c069bf6fb7a6ca02751
+oid sha256:04491054115f5fca09d38960caedd814323b1326ebd99907da9bf3fbd799e184
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196ac9dde7c4927b37b8bc53da35fc7da10f580fa77c1ee80824d56438d0a24c
+oid sha256:20335469f0ec66a4e6ceae2c6f0f5a5eb0bddc566fe7b367e2d26bc30cb02212
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6979166210878224,
-  "best_model_checkpoint": "training_dir/checkpoint-5000",
-  "epoch": 0.6357952739217971,
+  "best_metric": 0.7023119335505582,
+  "best_model_checkpoint": "training_dir/checkpoint-7000",
+  "epoch": 0.7417611529087634,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -121,6 +121,25 @@
       "eval_samples_per_second": 87.806,
       "eval_steps_per_second": 10.976,
       "step": 6000
+    },
+    {
+      "epoch": 0.7417611529087634,
+      "grad_norm": 2.134586811065674,
+      "learning_rate": 9.307552998828167e-06,
+      "loss": 0.4972,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7417611529087634,
+      "eval_accuracy": 0.715472027972028,
+      "eval_f1": 0.7023119335505582,
+      "eval_loss": 0.8132364749908447,
+      "eval_precision": 0.7209094583908723,
+      "eval_recall": 0.715472027972028,
+      "eval_runtime": 26.036,
+      "eval_samples_per_second": 87.878,
+      "eval_steps_per_second": 10.985,
+      "step": 7000
     }
   ],
   "logging_steps": 1000,
@@ -140,7 +159,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5815153429751520.0,
+  "total_flos": 6790124661368112.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null