Training in progress, step 8800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f6a115eb1a9c4a49e168f1bb3857564f38d4d9bc3ea0efe40b49efcf6b08f4
+oid sha256:f4acf6dde0a2feddc6fd239a6dd1f2386a1d1183b31361187de4d96ada1700c4
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c1b08f11f195ad4c5b17de831e8e1b4f539b2eb09209e52bc321acf39f4cce
+oid sha256:8b0248bc44eb9451dcde4a074fcc8492267618109d413fb6b57eb77d1a89c015
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154c6473a996aa5f5c1ce0512e3b88de25acb1a3c6cc4e05d1741ffd47af728e
+oid sha256:9c09f6512ffeeb2bf4558b0bf61454499dc0b26ef6c496c7d732c475bb5bbb20
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fe8fa48618c088835b11de6c48fcc323c2cbbb03b64c3e65eaf48a82f43ade7
+oid sha256:9c6db6ffd06c80cdcf75f36f88ac9398d22db0dc867b0e1529e8a83cac1c9f35
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0486035346984863,
   "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-8700",
-  "epoch": 2.525399129172714,
+  "epoch": 2.5544267053701017,
   "eval_steps": 100,
-  "global_step": 8700,
+  "global_step": 8800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1312,6 +1312,21 @@
       "eval_samples_per_second": 213.062,
       "eval_steps_per_second": 3.329,
       "step": 8700
+    },
+    {
+      "epoch": 2.5544267053701017,
+      "grad_norm": 1.2411503791809082,
+      "learning_rate": 7.445573294629898e-05,
+      "loss": 2.0016,
+      "step": 8800
+    },
+    {
+      "epoch": 2.5544267053701017,
+      "eval_loss": 1.0516774654388428,
+      "eval_runtime": 213.2425,
+      "eval_samples_per_second": 213.367,
+      "eval_steps_per_second": 3.334,
+      "step": 8800
     }
   ],
   "logging_steps": 100,
@@ -1326,7 +1341,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1340,7 +1355,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.703137722820198e+16,
+  "total_flos": 8.803176483599155e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null