Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7769a8b409b9f5cc8c4fcca71fea9c10feaff3ae5f6eda49319a9524c31c745
+oid sha256:9900b3c186c079bcb23fca4d7455eb1c1fa4a6834aa080210c16cf89ed37cf6a
 size 498686648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf482bdae897d5287fa2e8b439dcd2c6189371c6a214d2ce6b7eba7aa13fa0f0
+oid sha256:79da3e9caf7d4d2e6f1dcc2334761728f64c3e8f0ede33e99992bae602b52fc1
 size 997493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee729c95a8d92e4810522cb347750f57fd0b0ec5c06f7992ee2be85d4a78ab4b
+oid sha256:721bc7a5b221d6b012d2388a6a09216865e2462e31bd2e0fe77aaddae689aeb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c4d3964df52c8d20548263cfeb8b6c3ec321803a92f2244badb7ff92803145
+oid sha256:8e27a97977fcc445cdd5c99153117efc644690cb82cdc8080515d4ff3a8dec66
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4090208411216736,
   "best_model_checkpoint": "results/checkpoint-5000",
-  "epoch": 0.948136910969944,
+  "epoch": 1.0429506020669386,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,26 @@
       "eval_samples_per_second": 57.28,
       "eval_steps_per_second": 0.45,
       "step": 5000
+    },
+    {
+      "epoch": 1.0429506020669386,
+      "grad_norm": 298623.21875,
+      "learning_rate": 9.569505025602126e-06,
+      "loss": 0.4332,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0429506020669386,
+      "eval_accuracy": 0.8806597822531658,
+      "eval_f1_macro": 0.8501793427912383,
+      "eval_f1_w": 0.8820343950051113,
+      "eval_loss": 0.4112658202648163,
+      "eval_precision": 0.8853039418950968,
+      "eval_recall": 0.8806597822531658,
+      "eval_runtime": 377.6622,
+      "eval_samples_per_second": 56.667,
+      "eval_steps_per_second": 0.445,
+      "step": 5500
     }
   ],
   "logging_steps": 500,
@@ -226,7 +246,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6842736140288e+17,
+  "total_flos": 1.8526799220115046e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null