Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e99af771f7ef26c99b07932ae7bad8731c64be962b95861259ce6409960b99
+oid sha256:a92cfb1160468733e69a0c34e371d4d3fe7d602cbade9375de357250e66b2aca
 size 669476892

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1471d9b27dcd680de756171c43339e539fee09e8875dd913867a4873fe2490c
+oid sha256:89317d47ef01d7a40d316547cd08674ecc2fea0bf612136ff703ca765687b396
 size 1339074810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8f0ff43c2a1c4af634cdc1b8efd795673b994980808368515d76c66ec6805a
+oid sha256:d94c235e5dad9735892046c73c0e023adaadeb5618da38fc66eed3a6687af253
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909c45ebec99a47223b2a7186dc20cd087cc5d42c245e978a422831dce142ba9
+oid sha256:f462141317f5e0cfce220bdcec1f89eae028698a4bd4b653716c37fdf09a3f67
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.40313778990450205,
-  "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-122",
-  "epoch": 7.96734693877551,
+  "best_metric": 0.40586630286493863,
+  "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-137",
+  "epoch": 8.946938775510205,
   "eval_steps": 500,
-  "global_step": 122,
+  "global_step": 137,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,15 @@
       "eval_samples_per_second": 62.423,
       "eval_steps_per_second": 2.64,
       "step": 122
+    },
+    {
+      "epoch": 8.946938775510205,
+      "eval_accuracy": 0.40586630286493863,
+      "eval_loss": 1.670142650604248,
+      "eval_runtime": 23.4792,
+      "eval_samples_per_second": 62.438,
+      "eval_steps_per_second": 2.641,
+      "step": 137
     }
   ],
   "logging_steps": 500,
@@ -98,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.233542150995968e+16,
+  "total_flos": 1.387734919870464e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null