Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea6d447111a2ec8cd2317fa856caf6dd2ce70cc08dffaec690d421d24abd9f69
+oid sha256:b237893537fda4e4a94454052ef571287189b6a3a4fcfd591b04cf5224a008e5
 size 437958648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4167bc1e710d7dccff80b0c46ebfe6f40c46af346066de2c78a3a476b4ae5a4b
+oid sha256:5b5a38fcdff731d665d05997e361c69bb54d5086b988c150ade2ea80001f884c
 size 4741394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b86e157f86b466ae19e568a6360194077a6c859bad89453623425303da4937
+oid sha256:b3bf047f55dba59a50a635994a586d8ebb21180880beadb113000ddf89aa90f0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f8cd99175cf2f1e028a18a1ce679621f61ba504aa460cfcd83e0fc9f96eb8c
+oid sha256:0ce547e1d68585b25d05a5bec7c998637623fca10fb1992976ad7d664a792a22
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1d843eceb07cded9821c401bf7f9be101ad586a3ed822931c58813c3aff990f
+oid sha256:0e5f37a852c0ba1d6d735fab98ca6ba21037030dd87c3b32d0bd6558b6ce94ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 4689,
-  "best_metric": 0.2437499761581421,
-  "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-4689",
-  "epoch": 4.0,
+  "best_global_step": 7815,
+  "best_metric": 0.24368683993816376,
+  "best_model_checkpoint": "./bert-imdb-cp\\checkpoint-7815",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 6252,
+  "global_step": 7815,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -124,6 +124,35 @@
       "eval_samples_per_second": 92.125,
       "eval_steps_per_second": 5.76,
       "step": 6252
+    },
+    {
+      "epoch": 4.158669225847729,
+      "grad_norm": 1.3025797605514526,
+      "learning_rate": 1.6865003198976329e-06,
+      "loss": 0.2558,
+      "step": 6500
+    },
+    {
+      "epoch": 4.478566858605246,
+      "grad_norm": 1.6497241258621216,
+      "learning_rate": 1.0467050543825978e-06,
+      "loss": 0.2623,
+      "step": 7000
+    },
+    {
+      "epoch": 4.798464491362764,
+      "grad_norm": 1.4709057807922363,
+      "learning_rate": 4.0690978886756244e-07,
+      "loss": 0.2743,
+      "step": 7500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.24368683993816376,
+      "eval_runtime": 271.3467,
+      "eval_samples_per_second": 92.133,
+      "eval_steps_per_second": 5.76,
+      "step": 7815
     }
   ],
   "logging_steps": 500,
@@ -138,12 +167,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.603344526150064e+16,
+  "total_flos": 3.253872632752848e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null