Training in progress, epoch 2, checkpoint

checkpoint-162/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fcdd8a6007a1be5c510663d9bfb96e3243904c78a656ccbcf28ba46ea72ab0a
+oid sha256:43c99e6a866cd6da18b8d9e9189c03d600a154fd5b5f19a93d91b0364eaa4952
 size 592324828

checkpoint-162/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220a80149fe4c069e67a4fc5b3210fedd75134cd8fb77d1f3a8ac23d3b9622bd
+oid sha256:50861c73a583a913a44587c4fa457f2a6245f0bd1f3fa030a197744b62add8d4
 size 1014657786

checkpoint-162/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6613e657dfa5c91f076329239ba74e9bccea696a05690b1f35a5faffc85df4aa
+oid sha256:88e210ec99a19f026e2def82a9c5587c47c7771d7dd08d2e2ba3261c169c79d9
 size 14244

checkpoint-162/trainer_state.json

@@ -11,90 +11,90 @@
     {
       "epoch": 1.0,
       "eval_Claim": {
-        "f1-score": 0.4888068880688806,
-        "precision": 0.6228840125391849,
-        "recall": 0.40222672064777326,
-        "support": 4940.0
+        "f1-score": 0.41092129347162903,
+        "precision": 0.5640703517587939,
+        "recall": 0.32317658349328215,
+        "support": 4168.0
       },
       "eval_MajorClaim": {
-        "f1-score": 0.7325278370054489,
-        "precision": 0.7604525332021643,
-        "recall": 0.706581352833638,
-        "support": 2188.0
+        "f1-score": 0.6523102655237298,
+        "precision": 0.5929304446978335,
+        "recall": 0.724907063197026,
+        "support": 2152.0
       },
       "eval_O": {
-        "f1-score": 0.8634848138844484,
-        "precision": 0.827613377692173,
-        "recall": 0.902606702950444,
-        "support": 10473.0
+        "f1-score": 0.8834432924913603,
+        "precision": 0.8545380875202593,
+        "recall": 0.9143724257533059,
+        "support": 9226.0
       },
       "eval_Premise": {
-        "f1-score": 0.8792819197655248,
-        "precision": 0.8543458914268763,
-        "recall": 0.9057173407132524,
-        "support": 15899.0
+        "f1-score": 0.8664166767469054,
+        "precision": 0.8441231929604023,
+        "recall": 0.8899196554294707,
+        "support": 12073.0
       },
-      "eval_accuracy": 0.8174925373134329,
-      "eval_loss": 0.49806877970695496,
+      "eval_accuracy": 0.7997031029363844,
+      "eval_loss": 0.5104541182518005,
       "eval_macro avg": {
-        "f1-score": 0.7410253646810757,
-        "precision": 0.7663239537150996,
-        "recall": 0.7292830292862769,
-        "support": 33500.0
+        "f1-score": 0.7032728820584061,
+        "precision": 0.7139155192343223,
+        "recall": 0.7130939319682712,
+        "support": 27619.0
       },
-      "eval_runtime": 4.9194,
-      "eval_samples_per_second": 16.465,
-      "eval_steps_per_second": 2.236,
+      "eval_runtime": 4.7759,
+      "eval_samples_per_second": 16.751,
+      "eval_steps_per_second": 2.094,
       "eval_weighted avg": {
-        "f1-score": 0.8071778099281224,
-        "precision": 0.80572410140167,
-        "recall": 0.8174925373134329,
-        "support": 33500.0
+        "f1-score": 0.7866826459135919,
+        "precision": 0.7857670171690952,
+        "recall": 0.7997031029363844,
+        "support": 27619.0
       },
       "step": 81
     },
     {
       "epoch": 2.0,
       "eval_Claim": {
-        "f1-score": 0.5993816254416962,
-        "precision": 0.6593780369290574,
-        "recall": 0.5493927125506073,
-        "support": 4940.0
+        "f1-score": 0.5200312174817897,
+        "precision": 0.5678977272727272,
+        "recall": 0.47960652591170827,
+        "support": 4168.0
       },
       "eval_MajorClaim": {
-        "f1-score": 0.8017817371937639,
-        "precision": 0.7197382769901853,
-        "recall": 0.9049360146252285,
-        "support": 2188.0
+        "f1-score": 0.7526302911671151,
+        "precision": 0.7948320413436692,
+        "recall": 0.7146840148698885,
+        "support": 2152.0
       },
       "eval_O": {
-        "f1-score": 0.9058997050147494,
-        "precision": 0.9337184554575859,
-        "recall": 0.8796906330564308,
-        "support": 10473.0
+        "f1-score": 0.9116096466629278,
+        "precision": 0.944560669456067,
+        "recall": 0.8808801213960546,
+        "support": 9226.0
       },
       "eval_Premise": {
-        "f1-score": 0.8854737486606459,
-        "precision": 0.862579028987236,
-        "recall": 0.9096169570413234,
-        "support": 15899.0
+        "f1-score": 0.8738735224125151,
+        "precision": 0.8259587020648967,
+        "recall": 0.9276898865236478,
+        "support": 12073.0
       },
-      "eval_accuracy": 0.8468358208955223,
-      "eval_loss": 0.4562840759754181,
+      "eval_accuracy": 0.8278359100619139,
+      "eval_loss": 0.44692954421043396,
       "eval_macro avg": {
-        "f1-score": 0.7981342040777137,
-        "precision": 0.7938534495910161,
-        "recall": 0.8109090793183975,
-        "support": 33500.0
+        "f1-score": 0.7645361694310869,
+        "precision": 0.7833122850343401,
+        "recall": 0.7507151371753248,
+        "support": 27619.0
       },
-      "eval_runtime": 4.904,
-      "eval_samples_per_second": 16.517,
-      "eval_steps_per_second": 2.243,
+      "eval_runtime": 4.7439,
+      "eval_samples_per_second": 16.864,
+      "eval_steps_per_second": 2.108,
       "eval_weighted avg": {
-        "f1-score": 0.8442053257085675,
-        "precision": 0.8455251408465503,
-        "recall": 0.8468358208955223,
-        "support": 33500.0
+        "f1-score": 0.8236335905447046,
+        "precision": 0.8242076985653165,
+        "recall": 0.8278359100619139,
+        "support": 27619.0
       },
       "step": 162
     }
@@ -104,7 +104,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 286684367734800.0,
+  "total_flos": 287577465453600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

checkpoint-162/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da575726aa6fb9f10d3d3191c16916e8d9dc133cfc573c1d27486b346adcb4eb
+oid sha256:1e651c478af6098730eda01c59bbe4834fbad7ed476e7ec6e4265141ee6647e9
 size 4856