Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -13,15 +13,17 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "Safe Email",
-    "1": "Phishing Email"
+    "0": "No Fit",
+    "1": "Potential Fit",
+    "2": "Good Fit"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "is_decoder": false,
   "label2id": {
-    "Phishing Email": 1,
-    "Safe Email": 0
+    "0": "No Fit",
+    "1": "Potential Fit",
+    "2": "Good Fit"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b66535ff6415d2c31921f3fe356b0fac561719725dcb426dd1c3a9773e770c5
-size 437958624
+oid sha256:fcc41825dd4e2dda5ab59a18fb15d2bc6d7ebc016b0d6aad6f14401fee55dc77
+size 437961700

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45e4c9cef7b3d793962401a30cc5375b49e5f6fa7d66e64cc389d199fe8102b
-size 4741923
+oid sha256:1a4aba44d4545ce5bc2feb3d532db36ad6fd06c32b17949196f677fd6387137f
+size 4748067

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2e8413b53592d1e0dd4c602cd67bd1e7cb9a9ee96e69486272827e44496b7a
+oid sha256:73adb01bcea0cecd8da970a42e3125d42bd82dec94c1b2c5a1cf209bdb4e6dbe
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd34198e30d2e33cdb497643e8b4ce22778c6cc08096a422300c51708bdf5a02
+oid sha256:0861073ade655d14fb72097d362c2e813ed5d5faa50345ce5bc8f77fc935cfd8
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695b5daec62904ea9fe48fd42c554ece0bc33b8a351b379641efd77afed9c35f
+oid sha256:fc113105be61c25bb07c129ade488bf1ad8df712e596a6c750dd2672b51f8951
 size 1465

last-checkpoint/trainer_state.json

@@ -1,162 +1,27 @@
 {
-  "best_global_step": 4670,
-  "best_metric": 0.45520129799842834,
-  "best_model_checkpoint": "./bert-email/checkpoint-4670",
-  "epoch": 10.0,
+  "best_global_step": 196,
+  "best_metric": 2.137895345687866,
+  "best_model_checkpoint": "./bert-resume/checkpoint-196",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 4670,
+  "global_step": 196,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.9388861656188965,
-      "eval_runtime": 66.9874,
-      "eval_samples_per_second": 55.682,
-      "eval_steps_per_second": 1.747,
-      "step": 467
-    },
-    {
-      "epoch": 1.0706638115631693,
-      "grad_norm": 3.0445573329925537,
-      "learning_rate": 7.862955032119916e-06,
-      "loss": 1.1060218505859376,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.7270694971084595,
-      "eval_runtime": 66.8664,
-      "eval_samples_per_second": 55.783,
-      "eval_steps_per_second": 1.75,
-      "step": 934
-    },
-    {
-      "epoch": 2.1413276231263385,
-      "grad_norm": 5.564135551452637,
-      "learning_rate": 5.721627408993576e-06,
-      "loss": 0.8154515380859375,
-      "step": 1000
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 0.6182085871696472,
-      "eval_runtime": 66.9212,
-      "eval_samples_per_second": 55.737,
-      "eval_steps_per_second": 1.748,
-      "step": 1401
-    },
-    {
-      "epoch": 3.2119914346895073,
-      "grad_norm": 2.9384329319000244,
-      "learning_rate": 3.580299785867238e-06,
-      "loss": 0.6724396362304688,
-      "step": 1500
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.5720958113670349,
-      "eval_runtime": 66.8887,
-      "eval_samples_per_second": 55.764,
-      "eval_steps_per_second": 1.749,
-      "step": 1868
-    },
-    {
-      "epoch": 4.282655246252677,
-      "grad_norm": 1.6766972541809082,
-      "learning_rate": 1.4389721627408994e-06,
-      "loss": 0.6073400268554687,
-      "step": 2000
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": 0.5627617239952087,
-      "eval_runtime": 66.8913,
-      "eval_samples_per_second": 55.762,
-      "eval_steps_per_second": 1.749,
-      "step": 2335
-    },
-    {
-      "epoch": 5.353319057815845,
-      "grad_norm": 1.2230651378631592,
-      "learning_rate": 4.648822269807281e-06,
-      "loss": 0.5784992564808239,
-      "step": 2500
-    },
-    {
-      "epoch": 6.0,
-      "eval_loss": 0.5057228207588196,
-      "eval_runtime": 66.8732,
-      "eval_samples_per_second": 55.777,
-      "eval_steps_per_second": 1.75,
-      "step": 2802
-    },
-    {
-      "epoch": 6.423982869379015,
-      "grad_norm": 1.8150324821472168,
-      "learning_rate": 3.5781584582441113e-06,
-      "loss": 0.54178466796875,
-      "step": 3000
-    },
-    {
-      "epoch": 7.0,
-      "eval_loss": 0.4829275608062744,
-      "eval_runtime": 66.8232,
-      "eval_samples_per_second": 55.819,
-      "eval_steps_per_second": 1.751,
-      "step": 3269
-    },
-    {
-      "epoch": 7.494646680942184,
-      "grad_norm": 1.125893235206604,
-      "learning_rate": 2.5074946466809425e-06,
-      "loss": 0.5138602294921875,
-      "step": 3500
-    },
-    {
-      "epoch": 8.0,
-      "eval_loss": 0.46736541390419006,
-      "eval_runtime": 66.835,
-      "eval_samples_per_second": 55.809,
-      "eval_steps_per_second": 1.751,
-      "step": 3736
-    },
-    {
-      "epoch": 8.565310492505354,
-      "grad_norm": 1.139656662940979,
-      "learning_rate": 1.4368308351177733e-06,
-      "loss": 0.48643429565429686,
-      "step": 4000
-    },
-    {
-      "epoch": 9.0,
-      "eval_loss": 0.4572421610355377,
-      "eval_runtime": 66.7921,
-      "eval_samples_per_second": 55.845,
-      "eval_steps_per_second": 1.752,
-      "step": 4203
-    },
-    {
-      "epoch": 9.635974304068522,
-      "grad_norm": 1.6265816688537598,
-      "learning_rate": 3.661670235546039e-07,
-      "loss": 0.4844812927246094,
-      "step": 4500
-    },
-    {
-      "epoch": 10.0,
-      "eval_loss": 0.45520129799842834,
-      "eval_runtime": 66.8894,
-      "eval_samples_per_second": 55.764,
-      "eval_steps_per_second": 1.749,
-      "step": 4670
+      "eval_loss": 2.137895345687866,
+      "eval_runtime": 30.7966,
+      "eval_samples_per_second": 57.117,
+      "eval_steps_per_second": 1.786,
+      "step": 196
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4670,
+  "max_steps": 1568,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 8,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -165,12 +30,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.947507785777152e+16,
+  "total_flos": 1642090840040448.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e4ddd5ae672fe01abbc5d9c911cbb2a3272aa3019c09d3f6c0be52a5687dd28
+oid sha256:5b89ecfe7b715ea3f4f7f68441cad26801d1c51092cde3c13c8ced041b2a9b66
 size 5201