Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6696d19dd1af5a4b5fe88fb64bbde2651a949b0a6a6c1dcf12734e21979d1f34
+oid sha256:ca9c059311090af74af91c0ae21a79827d1f5d3d2165f2f04f2aa1f3d40ea101
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca258020d8ee8dd24ca225723f357c7875efabaf0ff2b1cd7edf5145bac62883
+oid sha256:46fbd56a34f15ed260a7e70130c87d4f0448b308001bc4c1ba65921e287a285d
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4902fcfb33d73ecfa5cb7dbd3cfd13500058abf1d6eae05ae197780b6416694
+oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca0968ced7c542658d18cbe2b8492512ae721a8edd083db895fdfc19d743c20
+oid sha256:0c1f275ddac84bf2aaec319eef9d214f465f8e62ab95bb5bc139951b4d7d90e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04068835824728012,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-7000",
-  "epoch": 3.449975357318876,
+  "best_metric": 0.03988400474190712,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-8000",
+  "epoch": 3.9428289797930014,
   "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": 570.6,
       "eval_steps_per_second": 2.251,
       "step": 7000
+    },
+    {
+      "epoch": 3.696402168555939,
+      "grad_norm": 0.3296278417110443,
+      "learning_rate": 1.9260719566288815e-05,
+      "loss": 0.0379,
+      "step": 7500
+    },
+    {
+      "epoch": 3.9428289797930014,
+      "grad_norm": 0.22207264602184296,
+      "learning_rate": 1.92114342040414e-05,
+      "loss": 0.0376,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9428289797930014,
+      "eval_accuracy": 0.986619329053106,
+      "eval_f1": 0.563381584423993,
+      "eval_loss": 0.03988400474190712,
+      "eval_precision": 0.7187020648967551,
+      "eval_recall": 0.463264374809857,
+      "eval_runtime": 14.2691,
+      "eval_samples_per_second": 568.36,
+      "eval_steps_per_second": 2.243,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -217,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 158618507030838.0,
+  "total_flos": 181369839544038.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null