Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b04033f66e6da0e75294cfbc8045656a1041044177e0cc675bb3078d713e7c6
+oid sha256:b5c60f390a2a09c2d06f316d2eb971ceaae9536585000f507723f926c22f62c4
 size 437958624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe6c4cad29877ad55544b72d9cc0fdc397c3dd9324da51fd18b37f669a673c2
-size 4741923
+oid sha256:fbf2a19a8032edc40bb658d66547edff470d09254585ba9f3c328c5e1b984375
+size 113448011

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bcbaa2aabec41ab6ddbecc0bb29c7ea2c5176ca5f2b9b4caa2a00b191411de1
+oid sha256:2fb7e7f0e32311ea4a34bdd12b1dc8ec66d46164a59b314eea8415d8682591cf
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ea89449ac93a3391a38a417e2dd400eff8832c6d069777a257c68b16d10335
+oid sha256:8457a345e0d53a37b5f1ebb6db1120270f6a7f4b99a871d4acda8980a58382cc
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbd75b8ebb26bc9af4014ad504a07ec158976c6e00388b7f420c4414a2d5005
+oid sha256:3026a6862398ced41e03f502f101f7ea90db137e7358354f2ae702c428eaf49c
 size 1465

last-checkpoint/trainer_state.json

@@ -1,102 +1,28 @@
 {
-  "best_global_step": 3910,
-  "best_metric": 0.6816725730895996,
-  "best_model_checkpoint": "./bert-imdb-cp/checkpoint-3910",
-  "epoch": 5.0,
+  "best_global_step": 782,
+  "best_metric": 0.4083733856678009,
+  "best_model_checkpoint": "./bert-imdb-cp/checkpoint-782",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 3910,
+  "global_step": 782,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.639386189258312,
-      "grad_norm": 2.0524730682373047,
+      "grad_norm": 3.604527473449707,
       "learning_rate": 1.7447570332480818e-05,
-      "loss": 0.794633544921875,
+      "loss": 0.656656494140625,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.7082774043083191,
-      "eval_runtime": 417.8316,
-      "eval_samples_per_second": 59.833,
-      "eval_steps_per_second": 1.872,
+      "eval_loss": 0.4083733856678009,
+      "eval_runtime": 465.4628,
+      "eval_samples_per_second": 53.71,
+      "eval_steps_per_second": 1.68,
       "step": 782
-    },
-    {
-      "epoch": 1.278772378516624,
-      "grad_norm": 2.869081497192383,
-      "learning_rate": 1.489002557544757e-05,
-      "loss": 0.7621511840820312,
-      "step": 1000
-    },
-    {
-      "epoch": 1.918158567774936,
-      "grad_norm": 4.932098865509033,
-      "learning_rate": 1.2332480818414323e-05,
-      "loss": 0.7465299072265625,
-      "step": 1500
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.6928977966308594,
-      "eval_runtime": 418.4611,
-      "eval_samples_per_second": 59.743,
-      "eval_steps_per_second": 1.869,
-      "step": 1564
-    },
-    {
-      "epoch": 2.557544757033248,
-      "grad_norm": 3.311922311782837,
-      "learning_rate": 9.774936061381075e-06,
-      "loss": 0.753785888671875,
-      "step": 2000
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.6841378211975098,
-      "eval_runtime": 417.7404,
-      "eval_samples_per_second": 59.846,
-      "eval_steps_per_second": 1.872,
-      "step": 2346
-    },
-    {
-      "epoch": 3.1969309462915603,
-      "grad_norm": 3.621079683303833,
-      "learning_rate": 7.217391304347827e-06,
-      "loss": 0.735134765625,
-      "step": 2500
-    },
-    {
-      "epoch": 3.836317135549872,
-      "grad_norm": 3.455075979232788,
-      "learning_rate": 4.659846547314578e-06,
-      "loss": 0.7347869262695312,
-      "step": 3000
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.6839827299118042,
-      "eval_runtime": 417.6818,
-      "eval_samples_per_second": 59.854,
-      "eval_steps_per_second": 1.872,
-      "step": 3128
-    },
-    {
-      "epoch": 4.475703324808184,
-      "grad_norm": 1.4374239444732666,
-      "learning_rate": 2.10230179028133e-06,
-      "loss": 0.72141064453125,
-      "step": 3500
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 0.6816725730895996,
-      "eval_runtime": 417.8893,
-      "eval_samples_per_second": 59.824,
-      "eval_steps_per_second": 1.871,
-      "step": 3910
     }
   ],
   "logging_steps": 500,
@@ -111,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.287503158960144e+16,
+  "total_flos": 6575737273320960.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null