Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b4a4c2155d4aa5d9ba3242e977b2dba6c5db7e9966a368227fd5382033a9d2
+oid sha256:9fd990d11bd5d66d6bed13f185883ea4cb7944e28eba186eb6558a9ccdcdbc2e
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99733c997fc7435948570b4de5efe8122bb8d127b7a18fef6a258586e08c0aef
+oid sha256:e1e92f6aa1461f021602ec4129ab6fa7dbab49bf5e6d579fc44c475447dbbd9c
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f04f6fd7c65d03db1dadb8f38687e3b2d58ce7526cb15c9a8c8b748a722949
+oid sha256:3e0f56ea2258aa848a268b65b4eb9157d222d715d9d9a7cc13ef82fd5f1faa73
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0edea2ed5e3ece25dc521aa3671e1ca478b0465607eea7f15adda71ddd55af89
+oid sha256:8c5ef62e5944f7a0f68155eb1714c52ea2903c9c361562828b854d1e450461a1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b9057f14bf3373d9e1f241ad9da2d6855725376530c8d981ecc5264012c16e5
+oid sha256:c4fcbe30b6934f80a241180dfc415b0f92927e3c28b8b87796f9a64e696582ef
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c89da50d878de65c791945958d2ad63fbb056fd379f71d2ad048791404f48f
+oid sha256:76a7b9b24e27099b1ee0ad93277549a53e07025af6930aa984b8a7e95784117c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fefc6f5e9bfe1c9e70e43ba61c03a371abcf2583878488a0cf8b57511098aefb
+oid sha256:9aca3b4e41519cad54d0814687cff94c8c96d678dfab879b406e03675dbb33ee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7487396597862244,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6500",
-  "epoch": 9.236947791164658,
+  "epoch": 9.370816599732262,
   "eval_steps": 100,
-  "global_step": 6900,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1042,6 +1042,21 @@
       "eval_samples_per_second": 893.836,
       "eval_steps_per_second": 3.612,
       "step": 6900
+    },
+    {
+      "epoch": 9.370816599732262,
+      "grad_norm": 0.2047683447599411,
+      "learning_rate": 6.291834002677377e-05,
+      "loss": 0.6625,
+      "step": 7000
+    },
+    {
+      "epoch": 9.370816599732262,
+      "eval_loss": 0.7502346038818359,
+      "eval_runtime": 6.3912,
+      "eval_samples_per_second": 890.597,
+      "eval_steps_per_second": 3.599,
+      "step": 7000
     }
   ],
   "logging_steps": 100,
@@ -1056,7 +1071,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 4
+        "early_stopping_patience_counter": 5
       }
     },
     "TrainerControl": {
@@ -1065,12 +1080,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.50554668285952e+17,
+  "total_flos": 2.5418589536256e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null