Training in progress, step 2200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd05797eba4af2ca90d5c8aedc8a2a141b146602a03127e89e52aeaa78c51cb0
+oid sha256:1b672b5cdfd1f8862685ea34563e2c8e28e69748fe9718cf421bba7dfab2006c
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5505d7094552ed7661bfc40965c065158aa0046fb8d6f07d161f457d37e1da5f
+oid sha256:260d8bec545542491a26819f31102a5e9700298d557614b9b96e6fe9e6ee6451
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d51837dd781f74c987a30a788fb34245746bf69bd7d3e79d3c65a22612eb23
+oid sha256:d3a8e3d7dc555cfd33954afbf3db56bb6f83c1bb4e5cfd281fce73c4efbf5429
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfd5e7fe0683153dd34505da9c613acbbf24ffe8ad301d2cfe6618d63d98896
+oid sha256:ef340a6411b8b518408fb09d160dd4f0e5ee5f7993bb698e2f1a2e34fceebc38
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc574ffdad315f35625e325f3592a5576c7dfb0a7edc69111f4fc7430d5f8bd
+oid sha256:ed0f6b270edd75f8ad03a0a501c63fc180ed748c6bbf472a303f1bd0c278a32e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207a31c0d5216576c258e1e019adc0b0471874547e0afd1e435ea0357317731f
+oid sha256:40348d850ac58ccc5115d7000f52e5cadd7b36ee5e2c20f7f67b47d1868058ef
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f7b847089c23254653d5114a76b90d4e846cc6929c539b8969df05d9501e6f
+oid sha256:0163aa20d0187419bf300d2a367c9e4f82a09b492cfb237f304e3a6bfac7210e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8368203639984131,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2100",
-  "epoch": 2.8112449799196786,
+  "epoch": 2.9451137884872827,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,21 @@
       "eval_samples_per_second": 893.931,
       "eval_steps_per_second": 3.612,
       "step": 2100
+    },
+    {
+      "epoch": 2.9451137884872827,
+      "grad_norm": 0.1776580661535263,
+      "learning_rate": 0.0007054886211512718,
+      "loss": 0.8327,
+      "step": 2200
+    },
+    {
+      "epoch": 2.9451137884872827,
+      "eval_loss": 0.8410006165504456,
+      "eval_runtime": 6.4205,
+      "eval_samples_per_second": 886.529,
+      "eval_steps_per_second": 3.582,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -336,7 +351,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -350,7 +365,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.6255768608768e+16,
+  "total_flos": 7.9886995685376e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null