Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95664b787851781d0c62edeefc3c53958be392ff262bb1aa5bab5c02faa99feb
+oid sha256:dc272e9a8e261ed2bdbeebd910f8b7fa802c0ab2771de97deb7426c0a34a46d4
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0ad4fadaa4dba4a1400074f46b7850ed6fab5bbfbe09f96d393f66b867fa21
+oid sha256:444082af6890f7fa4945fa47555e1290f6ca308e03915d60b4c7f291b3071486
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3992baeb5b4aeff64fbf88c36d791d5306c7958b8d54b6936d9563d4994bc181
+oid sha256:56f4ef3ec6475612038b659c4ace802fdab90a52ad47a95114fd963780c200ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8561ee0a37510aebbd3f443150e380bcaf6cbc3d5fe5502abdd174739a61c298
+oid sha256:d06f25b2e82d5726321480e2bb4450422006a39d571b32467918f1ed8e55e4db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04018256813287735,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-7000",
-  "epoch": 55.118110236220474,
+  "best_metric": 0.03934308886528015,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-8000",
+  "epoch": 62.99212598425197,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,32 @@
       "eval_samples_per_second": 575.762,
       "eval_steps_per_second": 2.272,
       "step": 7000
+    },
+    {
+      "epoch": 59.05511811023622,
+      "grad_norm": 0.12024829536676407,
+      "learning_rate": 3.1545275590551183e-06,
+      "loss": 0.0332,
+      "step": 7500
+    },
+    {
+      "epoch": 62.99212598425197,
+      "grad_norm": 0.12477916479110718,
+      "learning_rate": 3.0314960629921263e-06,
+      "loss": 0.0316,
+      "step": 8000
+    },
+    {
+      "epoch": 62.99212598425197,
+      "eval_accuracy": 0.9873237240812393,
+      "eval_f1": 0.5808023997000374,
+      "eval_loss": 0.03934308886528015,
+      "eval_precision": 0.7555176198024631,
+      "eval_recall": 0.47171678720974497,
+      "eval_runtime": 14.1551,
+      "eval_samples_per_second": 572.936,
+      "eval_steps_per_second": 2.261,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -208,7 +234,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3147116161527108.0,
+  "total_flos": 3596066806725396.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null