Training in progress, epoch 1, checkpoint

checkpoint-41/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd33ff53c0edd4d359980f27f4afa194ec5b807febef7f4cbaefde162b633c4b
+oid sha256:88c07cbc53c51f5c54df711ef5979bc1f3418049f6d85a04b3dbda81a97924a1
 size 592330980

checkpoint-41/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab3510262bc219de46e870072b2a617000c0c57c3d0baaaf87394856c91f5477
+oid sha256:607460e5b1146da32c681dd270585cfb7f0e8ea70592e43e5c102d6094ae78cc
 size 1014670074

checkpoint-41/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b75d0f85c6e5f43bda08f24453a869f5d0b5d0d33d936ef1b542f406f081347
+oid sha256:4a939982f711c8a91f0893b4f281f0db4fd89d7ca52de2aed82098ef9ff76ea2
 size 14244

checkpoint-41/trainer_state.json

@@ -14,60 +14,60 @@
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 339.0
+        "support": 271.0
       },
       "eval_B-MajorClaim": {
         "f1-score": 0.0,
         "precision": 0.0,
         "recall": 0.0,
-        "support": 160.0
+        "support": 139.0
       },
       "eval_B-Premise": {
-        "f1-score": 0.22426470588235295,
-        "precision": 0.8299319727891157,
-        "recall": 0.12964930924548354,
-        "support": 941.0
+        "f1-score": 0.22222222222222218,
+        "precision": 0.780952380952381,
+        "recall": 0.12954186413902052,
+        "support": 633.0
       },
       "eval_I-Claim": {
-        "f1-score": 0.38247663551401867,
-        "precision": 0.423873640600725,
-        "recall": 0.348446147296722,
-        "support": 4698.0
+        "f1-score": 0.3239807781739265,
+        "precision": 0.42653061224489797,
+        "recall": 0.26118470382404396,
+        "support": 4001.0
       },
       "eval_I-MajorClaim": {
-        "f1-score": 0.3634627625716104,
-        "precision": 0.5125673249551167,
-        "recall": 0.28155818540433925,
-        "support": 2028.0
+        "f1-score": 0.43526510480887787,
+        "precision": 0.5735174654752234,
+        "recall": 0.35072031793343267,
+        "support": 2013.0
       },
       "eval_I-Premise": {
-        "f1-score": 0.8298935191271198,
-        "precision": 0.8110747093209996,
-        "recall": 0.8496063521970257,
-        "support": 14861.0
+        "f1-score": 0.8370338686471983,
+        "precision": 0.7484180515958556,
+        "recall": 0.9494530698659139,
+        "support": 11336.0
       },
       "eval_O": {
-        "f1-score": 0.8121805609242796,
-        "precision": 0.7380952380952381,
-        "recall": 0.9027976701995608,
-        "support": 10473.0
+        "f1-score": 0.8603704893457543,
+        "precision": 0.8500846381718155,
+        "recall": 0.8709083026230219,
+        "support": 9226.0
       },
-      "eval_accuracy": 0.7286865671641791,
-      "eval_loss": 0.763540506362915,
+      "eval_accuracy": 0.7469857706651218,
+      "eval_loss": 0.6934069395065308,
       "eval_macro avg": {
-        "f1-score": 0.3731825977170545,
-        "precision": 0.47364898368017067,
-        "recall": 0.3588653806204473,
-        "support": 33500.0
+        "f1-score": 0.3826960661711399,
+        "precision": 0.48278616406288194,
+        "recall": 0.3659726083407761,
+        "support": 27619.0
       },
-      "eval_runtime": 1.4539,
-      "eval_samples_per_second": 55.714,
-      "eval_steps_per_second": 7.566,
+      "eval_runtime": 1.3993,
+      "eval_samples_per_second": 57.171,
+      "eval_steps_per_second": 7.146,
       "eval_weighted avg": {
-        "f1-score": 0.7040007584084623,
-        "precision": 0.7043362259324342,
-        "recall": 0.7286865671641791,
-        "support": 33500.0
+        "f1-score": 0.7147071394985115,
+        "precision": 0.7126373293529855,
+        "recall": 0.7469857706651218,
+        "support": 27619.0
       },
       "step": 41
     }
@@ -77,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 16,
   "save_steps": 500,
-  "total_flos": 143344257399000.0,
+  "total_flos": 143790812718000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-41/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:920ab155975bf66f694757fefb246b73b0d1489bdf4f03eda383fa028f5d083a
+oid sha256:ea7dd3e20b3e160af2247e96dc319ccd6cb101ae7dc47f0b44b05679d4ad74d7
 size 4664