Training in progress, epoch 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63c757cfe1b66daf4609c2f13d4900cdfe43821df23a67209acf97f9a2e8419
+oid sha256:4ad97021c9edd0c79d091d25cde9ab7626cab464147b73271b9de544b7ec9855
 size 672306188

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f084d5926e59a3ffa249e786e4d89278c7283808642a27fc35d34d74ba779e
+oid sha256:0557c5d1053d50f1be7edee8e9c956804d8872eee36601f2a451d7263225eff6
 size 1344733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5696a251659df2f172bd890dcf03ce2fac64383f19d14c4514efbf1162018f10
+oid sha256:57157cd9f95486998d5edb43493bad394494cc7e7197aea8618f7269139843fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3139ff08ad94102fd693b2cbd7537c5760aa3ddae6d1e6468b14555d576f0d
+oid sha256:dfa9c4b8788b88383723af92d82ec3d6b3070a72a1e1c3260a0e5607acf7a181
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7793118854247427,
-  "best_model_checkpoint": "./results/checkpoint-384",
-  "epoch": 16.0,
+  "best_metric": 0.7944218814891261,
+  "best_model_checkpoint": "./results/checkpoint-432",
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 384,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -263,6 +263,70 @@
       "eval_samples_per_second": 2153.098,
       "eval_steps_per_second": 39.506,
       "step": 384
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 7.26137638092041,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1857,
+      "step": 408
+    },
+    {
+      "epoch": 17.0,
+      "eval_f1": 0.7756879125919374,
+      "eval_loss": 0.5410326719284058,
+      "eval_runtime": 0.1055,
+      "eval_samples_per_second": 2065.917,
+      "eval_steps_per_second": 37.907,
+      "step": 408
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 5.544007301330566,
+      "learning_rate": 1.0208333333333334e-06,
+      "loss": 0.1712,
+      "step": 432
+    },
+    {
+      "epoch": 18.0,
+      "eval_f1": 0.7944218814891261,
+      "eval_loss": 0.5516819953918457,
+      "eval_runtime": 0.1027,
+      "eval_samples_per_second": 2122.343,
+      "eval_steps_per_second": 38.942,
+      "step": 432
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 3.674745559692383,
+      "learning_rate": 5.208333333333334e-07,
+      "loss": 0.162,
+      "step": 456
+    },
+    {
+      "epoch": 19.0,
+      "eval_f1": 0.7746872341905638,
+      "eval_loss": 0.5430514216423035,
+      "eval_runtime": 0.1022,
+      "eval_samples_per_second": 2133.699,
+      "eval_steps_per_second": 39.15,
+      "step": 456
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 3.700077772140503,
+      "learning_rate": 2.0833333333333335e-08,
+      "loss": 0.1604,
+      "step": 480
+    },
+    {
+      "epoch": 20.0,
+      "eval_f1": 0.7909264379084623,
+      "eval_loss": 0.5474005937576294,
+      "eval_runtime": 0.1057,
+      "eval_samples_per_second": 2063.283,
+      "eval_steps_per_second": 37.858,
+      "step": 480
     }
   ],
   "logging_steps": 500,
@@ -277,12 +341,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 598932949836120.0,
+  "total_flos": 749054183774760.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null