Training in progress, epoch 69, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa7b71f0186326e5dfcd1ebc696485cf4085109a236a1a5e231389a112749b6
+oid sha256:247791b25e1ae4add138e7227ed13cc2d6026bec2a436315a86d315f780e5f05
 size 672610316

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c757045631650e1b5afc471f91c69405d6f765f948c7a10620d8501d09b3b218
+oid sha256:f201711d26dce4748090ae33db3e3808c1d3c95ec23a22353e06c8a632ddcfb2
 size 1345341690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ba5062855bc5b787b9131a380b45c1ef093b8f5bda042958f933465fdfe6e2
+oid sha256:827a0d427586f5124064647455e6a166beb4ca620d95c3ccbb8e558f5f888f08
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a72a0f03788668d35910cde40b02ba0eb590aa49feadc63f673cede562ba7d
+oid sha256:ea9ea2935d057334cc98150650e98c17b6bacf2fe7222d479a5d4e08bcbac6e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8533899487562311,
   "best_model_checkpoint": "./results/checkpoint-1200",
-  "epoch": 65.0,
+  "epoch": 69.0,
   "eval_steps": 500,
-  "global_step": 1560,
+  "global_step": 1656,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1047,6 +1047,70 @@
       "eval_samples_per_second": 897.779,
       "eval_steps_per_second": 16.473,
       "step": 1560
+    },
+    {
+      "epoch": 66.0,
+      "grad_norm": 0.001049485057592392,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.0001,
+      "step": 1584
+    },
+    {
+      "epoch": 66.0,
+      "eval_f1": 0.8471931986968837,
+      "eval_loss": 1.180769443511963,
+      "eval_runtime": 0.2525,
+      "eval_samples_per_second": 863.258,
+      "eval_steps_per_second": 15.84,
+      "step": 1584
+    },
+    {
+      "epoch": 67.0,
+      "grad_norm": 0.0010408489033579826,
+      "learning_rate": 1.65e-05,
+      "loss": 0.0001,
+      "step": 1608
+    },
+    {
+      "epoch": 67.0,
+      "eval_f1": 0.8471931986968837,
+      "eval_loss": 1.1815507411956787,
+      "eval_runtime": 0.2505,
+      "eval_samples_per_second": 870.186,
+      "eval_steps_per_second": 15.967,
+      "step": 1608
+    },
+    {
+      "epoch": 68.0,
+      "grad_norm": 0.0012064232723787427,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0001,
+      "step": 1632
+    },
+    {
+      "epoch": 68.0,
+      "eval_f1": 0.8471931986968837,
+      "eval_loss": 1.182210922241211,
+      "eval_runtime": 0.2583,
+      "eval_samples_per_second": 844.028,
+      "eval_steps_per_second": 15.487,
+      "step": 1632
+    },
+    {
+      "epoch": 69.0,
+      "grad_norm": 0.0014143523294478655,
+      "learning_rate": 1.55e-05,
+      "loss": 0.0001,
+      "step": 1656
+    },
+    {
+      "epoch": 69.0,
+      "eval_f1": 0.8524668435013261,
+      "eval_loss": 1.1818993091583252,
+      "eval_runtime": 0.2452,
+      "eval_samples_per_second": 888.962,
+      "eval_steps_per_second": 16.311,
+      "step": 1656
     }
   ],
   "logging_steps": 500,
@@ -1066,7 +1130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2403310835213736.0,
+  "total_flos": 2551863638350032.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null