Training in progress, step 100, checkpoint

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca14abc2231924cd6f53b4a1029a4db1b0e36b9bffb54cd66d4b80c435a97e2
-size 4747538
+oid sha256:7d4db39d5938238acd56dde9187a5e93434a86acab863d24bd3ecad16485eb70
+size 997351674

checkpoint-100/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc52dc4cca2eddcf0a58171fa91263a8b35d1dca5b277cef6b03ac7f02c0c38
+oid sha256:1ac491627d7b469328f54e32f7f1f9e2b671c5716f6b5a2408b041d27185e33b
 size 498661166

checkpoint-100/tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 1,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

checkpoint-100/trainer_state.json

@@ -11,13 +11,13 @@
     {
       "epoch": 0.05,
       "learning_rate": 0.0004995563442768412,
-      "loss": 1.2913,
+      "loss": 1.3139,
       "step": 10
     },
     {
       "epoch": 0.11,
       "learning_rate": 0.0004986690328305235,
-      "loss": 1.1578,
+      "loss": 1.2812,
       "step": 20
     },
     {
@@ -25,24 +25,24 @@
       "eval_accuracy": 0.7386666666666667,
       "eval_combined_score": 0.6626504648943422,
       "eval_f1": 0.6276400817995911,
-      "eval_loss": 0.7813256978988647,
+      "eval_loss": 0.8499402403831482,
       "eval_precision": 0.5456284444444445,
       "eval_recall": 0.7386666666666667,
-      "eval_runtime": 5.7155,
-      "eval_samples_per_second": 262.444,
-      "eval_steps_per_second": 8.223,
+      "eval_runtime": 125.9807,
+      "eval_samples_per_second": 11.907,
+      "eval_steps_per_second": 0.373,
       "step": 20
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0004977817213842058,
-      "loss": 0.8742,
+      "loss": 0.832,
       "step": 30
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0004968944099378882,
-      "loss": 0.7537,
+      "loss": 0.8156,
       "step": 40
     },
     {
@@ -50,24 +50,24 @@
       "eval_accuracy": 0.7386666666666667,
       "eval_combined_score": 0.6626504648943422,
       "eval_f1": 0.6276400817995911,
-      "eval_loss": 0.792127251625061,
+      "eval_loss": 0.8848057985305786,
       "eval_precision": 0.5456284444444445,
       "eval_recall": 0.7386666666666667,
-      "eval_runtime": 5.6846,
-      "eval_samples_per_second": 263.869,
-      "eval_steps_per_second": 8.268,
+      "eval_runtime": 46.3365,
+      "eval_samples_per_second": 32.372,
+      "eval_steps_per_second": 1.014,
       "step": 40
     },
     {
       "epoch": 0.27,
       "learning_rate": 0.0004960070984915705,
-      "loss": 0.8076,
+      "loss": 0.7475,
       "step": 50
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0004951197870452529,
-      "loss": 0.7436,
+      "loss": 0.7478,
       "step": 60
     },
     {
@@ -75,24 +75,24 @@
       "eval_accuracy": 0.7386666666666667,
       "eval_combined_score": 0.6626504648943422,
       "eval_f1": 0.6276400817995911,
-      "eval_loss": 0.7419535517692566,
+      "eval_loss": 0.7691774964332581,
       "eval_precision": 0.5456284444444445,
       "eval_recall": 0.7386666666666667,
-      "eval_runtime": 5.7977,
-      "eval_samples_per_second": 258.725,
-      "eval_steps_per_second": 8.107,
+      "eval_runtime": 6.0551,
+      "eval_samples_per_second": 247.726,
+      "eval_steps_per_second": 7.762,
       "step": 60
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0004942324755989353,
-      "loss": 0.7465,
+      "loss": 0.7663,
       "step": 70
     },
     {
       "epoch": 0.43,
       "learning_rate": 0.0004933451641526176,
-      "loss": 0.6516,
+      "loss": 0.6034,
       "step": 80
     },
     {
@@ -100,24 +100,24 @@
       "eval_accuracy": 0.7386666666666667,
       "eval_combined_score": 0.6626504648943422,
       "eval_f1": 0.6276400817995911,
-      "eval_loss": 0.7484750747680664,
+      "eval_loss": 0.7553095817565918,
       "eval_precision": 0.5456284444444445,
       "eval_recall": 0.7386666666666667,
-      "eval_runtime": 5.7051,
-      "eval_samples_per_second": 262.923,
-      "eval_steps_per_second": 8.238,
+      "eval_runtime": 6.025,
+      "eval_samples_per_second": 248.962,
+      "eval_steps_per_second": 7.801,
       "step": 80
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0004924578527063,
-      "loss": 0.9634,
+      "loss": 0.9511,
       "step": 90
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0004915705412599822,
-      "loss": 0.8011,
+      "loss": 0.7548,
       "step": 100
     },
     {
@@ -125,12 +125,12 @@
       "eval_accuracy": 0.7386666666666667,
       "eval_combined_score": 0.6626504648943422,
       "eval_f1": 0.6276400817995911,
-      "eval_loss": 0.7428026795387268,
+      "eval_loss": 0.7768574357032776,
       "eval_precision": 0.5456284444444445,
       "eval_recall": 0.7386666666666667,
-      "eval_runtime": 5.7042,
-      "eval_samples_per_second": 262.962,
-      "eval_steps_per_second": 8.239,
+      "eval_runtime": 5.9796,
+      "eval_samples_per_second": 250.851,
+      "eval_steps_per_second": 7.86,
       "step": 100
     }
   ],

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f7cf02005ce236de7bb1fda33a06f2c3053bafb778c1f449d2ec5279f3a3ec
+oid sha256:5774ca6e2ea30af0574f0df2eee8b6bf7c47cb150d6cc3a84e7f1fdeba63d725
 size 4472