Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b0baeb960dd305488b4d620acbbe73944acf2f3aee6f39ab4f9f2ace9146da
+oid sha256:a3da96280e1331c1a0b3fdbb63178b204c63147570c36d2d8caa4e5aaf841261
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae5503ebaf112403941b4ddfc161ae2d74499963b425aa493869fdb99502c7b
+oid sha256:8190e7d36220b664948c8cf1a03bb28340c6615c9554514bbe827b6fc524675a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
+oid sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd937dc5ca4c62f5f5a023ee1555a7a5e140540c1dc517f73c54011163ae049e
+oid sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0379740335047245,
   "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-16000",
-  "epoch": 8.382642998027613,
+  "epoch": 8.875739644970414,
   "eval_steps": 1000,
-  "global_step": 17000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -449,6 +449,32 @@
       "eval_samples_per_second": 554.198,
       "eval_steps_per_second": 2.187,
       "step": 17000
+    },
+    {
+      "epoch": 8.629191321499015,
+      "grad_norm": 0.39663228392601013,
+      "learning_rate": 1.8274556213017754e-05,
+      "loss": 0.0215,
+      "step": 17500
+    },
+    {
+      "epoch": 8.875739644970414,
+      "grad_norm": 0.7587671279907227,
+      "learning_rate": 1.822524654832347e-05,
+      "loss": 0.0222,
+      "step": 18000
+    },
+    {
+      "epoch": 8.875739644970414,
+      "eval_accuracy": 0.9875816715563304,
+      "eval_f1": 0.6271172014639543,
+      "eval_loss": 0.03859669715166092,
+      "eval_precision": 0.7083253220534512,
+      "eval_recall": 0.5626145387904704,
+      "eval_runtime": 14.5227,
+      "eval_samples_per_second": 558.436,
+      "eval_steps_per_second": 2.203,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
@@ -477,7 +503,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 384458650453980.0,
+  "total_flos": 407138463972036.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null