Training in progress, step 3400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fcc6b68ed6c8fcec7935714d880896ac1f50e26c53db7f0662d98ab1a15414
+oid sha256:fa079d8f5f78ad05341ea236d2ade00e651277862b68a4130ace8f1920e4fc26
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6146b500d61dcfd9fb8f6f470d354ea82c8673e39cf6c885f67eebe284bdc832
+oid sha256:507a453e50f7a1b01e314911b48daf7d2393ad033c1524e967270d46aa02b89b
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c9bcd7d5c7db6d39407cf0f484e960bc685e2e96251815b42ccafca7685683
+oid sha256:83839fd075ba66694d3c368de69d75c341a9c5fab798f9cc50c55f617f5662ea
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be59fda547433051d1e3429d31d948c03fb4fc94f4aa092a8ba1a6c18f620262
+oid sha256:653813692be3fe76058a72494d47dfbd3b6bbfee96ad09970fa4673fd2ea20e7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d90284b24f335c55911eb7de6e1b04f64d7916ffd27324cbd36e8c39ff5f39
+oid sha256:6441076c1cbb565e8a73d1aab0642efd925e6b62088853107fb5868252f66a6f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793dfcb846de77f43d414bbe711491e2af32eca9823a49b468c31c54598cb459
+oid sha256:587dbaeb0068045023e24668350e32134b72575f93a986040a0358feb0532d23
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7623b48a4372484f57d0d82402f5c3c0b0e58b745867e2e8f7526e0f0890c47
+oid sha256:efdc531e420599f96dd87d66bd6a5df7ddb29f4c8764fef359b2917a85fb4260
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.805473268032074,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3200",
-  "epoch": 4.417670682730924,
+  "epoch": 4.551539491298527,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -502,6 +502,21 @@
       "eval_samples_per_second": 892.112,
       "eval_steps_per_second": 3.605,
       "step": 3300
+    },
+    {
+      "epoch": 4.551539491298527,
+      "grad_norm": 0.18258976936340332,
+      "learning_rate": 0.0005448460508701473,
+      "loss": 0.7677,
+      "step": 3400
+    },
+    {
+      "epoch": 4.551539491298527,
+      "eval_loss": 0.8068288564682007,
+      "eval_runtime": 6.3962,
+      "eval_samples_per_second": 889.896,
+      "eval_steps_per_second": 3.596,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
@@ -516,7 +531,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -530,7 +545,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.19830493528064e+17,
+  "total_flos": 1.23461720604672e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null