Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2337c930e5288017078419835a4c9b9706ad66b3b34977cc787152fe1ded7b
+oid sha256:fd3597182d719d91781498a2d657d7dcccfed6c4f6beb2ce4725ba6cd7ed6e9b
 size 2239622772

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f50495d912cdaddfcb82e677cc6e0d987ec2e02e77be13b3bcd2c8cba06979e
+oid sha256:f330e3fb5d84dc909f380910308bdcc94794f42795a76323440294ffb43dc5b8
 size 4479480977

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef7d497557c6acde0df57c8664dd739dd3dccf6a195816d7c89ef72a0524e04
+oid sha256:b771b35b521197254b82329f5cb616cd3abc4bc3db2753aeceb9799b9843f58e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f900f8e7ee0be53449615890cf1fad12ae456f7e5275907b8f6bf1d6c1480ab
+oid sha256:e6fb547027be1309700337f832e71ce88dcdac5f09ac4a912bfc57a4ed7da7ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7774524158125915,
   "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 995,
+  "global_step": 1194,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,22 @@
       "eval_samples_per_second": 12.186,
       "eval_steps_per_second": 6.093,
       "step": 995
+    },
+    {
+      "epoch": 5.025125628140704,
+      "grad_norm": 2496.794189453125,
+      "learning_rate": 4.974874371859297e-06,
+      "loss": 0.2005,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7642752562225475,
+      "eval_loss": 1.0910539627075195,
+      "eval_runtime": 111.8459,
+      "eval_samples_per_second": 12.213,
+      "eval_steps_per_second": 6.107,
+      "step": 1194
     }
   ],
   "logging_steps": 500,
@@ -78,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.47784427556048e+16,
+  "total_flos": 1.773413130672576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null