Training in progress, step 8900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4acf6dde0a2feddc6fd239a6dd1f2386a1d1183b31361187de4d96ada1700c4
+oid sha256:4792b6295769671ef028bc072477a4dc6b2cdad04d8241af13a27bd5bc283018
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0248bc44eb9451dcde4a074fcc8492267618109d413fb6b57eb77d1a89c015
+oid sha256:f0809bfda509f79842fa22ff4a74001a45f4de3e95e2aa0f32fada66c76f6bf1
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c09f6512ffeeb2bf4558b0bf61454499dc0b26ef6c496c7d732c475bb5bbb20
+oid sha256:e29647aaac7584d5c979f85f161bf7892d8e311714c56e2e611ee2a08b9475e5
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6db6ffd06c80cdcf75f36f88ac9398d22db0dc867b0e1529e8a83cac1c9f35
+oid sha256:5603f8c0ec715faa1d0b7e7b75e57ca14609131762cc7b196cf6563d0272d241
 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": 2.5544267053701017,
+  "best_metric": 1.0438764095306396,
+  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-8900",
+  "epoch": 2.583454281567489,
   "eval_steps": 100,
-  "global_step": 8800,
+  "global_step": 8900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1327,6 +1327,21 @@
       "eval_samples_per_second": 213.367,
       "eval_steps_per_second": 3.334,
       "step": 8800
+    },
+    {
+      "epoch": 2.583454281567489,
+      "grad_norm": 1.2166720628738403,
+      "learning_rate": 7.416545718432511e-05,
+      "loss": 1.9761,
+      "step": 8900
+    },
+    {
+      "epoch": 2.583454281567489,
+      "eval_loss": 1.0438764095306396,
+      "eval_runtime": 213.2447,
+      "eval_samples_per_second": 213.365,
+      "eval_steps_per_second": 3.334,
+      "step": 8900
     }
   ],
   "logging_steps": 100,
@@ -1341,7 +1356,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -1355,7 +1370,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.803176483599155e+16,
+  "total_flos": 8.903215244378112e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null