Training in progress, step 6200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c34ba597a5c81ced1d39b217a0c23c258e10ff6753c4df538802d18ce5e628
+oid sha256:ee3ae07dfc8047815d8a6c8fa296734722fa59b3cbce8564d1323ef267909af0
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f899c00d47f39bb7388c3f058992fd87e8876c1cc3304647873a123f22ed96
+oid sha256:be98d39cce9ff88fbe1cc2efa6e12295da3d7e52cc13c66ab55863018e19714d
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:373381e1af0a7bd8f556a1461be5145a00f7ca5c3f9b98fdd6aa1a1866e01871
+oid sha256:dc2062bc89d104244d565459987ebb4830d60b8bf5adf124b5e56de8734d6115
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8054d9536c9328179ffe89e113671755f845d619eca4ba0428dce64587ae20ff
+oid sha256:623bc2e65ccbc34780c1af24f2c57017f114efdf168ac15aa697d79d87303903
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3efc810bd5e02520ea4047772206af56b66c4663e317c3c18bbf1aacf3ccf3
+oid sha256:5706071c9ad96057c6c418b387e13aee2d821fd2f5f783d719b2e5373d3c6eba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80455bdd5f9d0849480e1ae2cd0f431ae5c19bbf0c5a630d843b2e838f480ce1
+oid sha256:5e50793c876edc70655416f85d3d91575396243d66a94e5c6919e4c64b70e3fe
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bba307a2dbb51e1fe4a814ce6fd6fcd90ba49bffaa9b023d0750076d62c718
+oid sha256:2a52d27fb81146a519532f9a867778c1f05661217a09bb1e7108e29e88e3a990
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7580859661102295,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6000",
-  "epoch": 8.165997322623829,
+  "best_metric": 0.757574200630188,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6200",
+  "epoch": 8.299866131191433,
   "eval_steps": 100,
-  "global_step": 6100,
+  "global_step": 6200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -922,6 +922,21 @@
       "eval_samples_per_second": 884.859,
       "eval_steps_per_second": 3.576,
       "step": 6100
+    },
+    {
+      "epoch": 8.299866131191433,
+      "grad_norm": 0.19806508719921112,
+      "learning_rate": 0.00017001338688085678,
+      "loss": 0.6774,
+      "step": 6200
+    },
+    {
+      "epoch": 8.299866131191433,
+      "eval_loss": 0.757574200630188,
+      "eval_runtime": 6.4053,
+      "eval_samples_per_second": 888.642,
+      "eval_steps_per_second": 3.591,
+      "step": 6200
     }
   ],
   "logging_steps": 100,
@@ -936,7 +951,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -950,7 +965,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.21504851673088e+17,
+  "total_flos": 2.25136078749696e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null