Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9c059311090af74af91c0ae21a79827d1f5d3d2165f2f04f2aa1f3d40ea101
+oid sha256:6157b83d3ad04fbacce2164dc09995d5b7ec64a269194f09f28ec4576456b04a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fbd56a34f15ed260a7e70130c87d4f0448b308001bc4c1ba65921e287a285d
+oid sha256:779e39f46a015cc88c42b8580783cf0c7efbd1969b44e5eebd7272323cd66825
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
+oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1f275ddac84bf2aaec319eef9d214f465f8e62ab95bb5bc139951b4d7d90e2
+oid sha256:c1c594171daced1aeade37a70493521e5eab91ea5bc7c6a38065d07e548360fc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03988400474190712,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-8000",
-  "epoch": 3.9428289797930014,
+  "best_metric": 0.038919780403375626,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-9000",
+  "epoch": 4.435682602267127,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,6 +215,32 @@
       "eval_samples_per_second": 568.36,
       "eval_steps_per_second": 2.243,
       "step": 8000
+    },
+    {
+      "epoch": 4.189255791030064,
+      "grad_norm": 0.22761479020118713,
+      "learning_rate": 1.916214884179399e-05,
+      "loss": 0.034,
+      "step": 8500
+    },
+    {
+      "epoch": 4.435682602267127,
+      "grad_norm": 0.4061233699321747,
+      "learning_rate": 1.9112863479546578e-05,
+      "loss": 0.0339,
+      "step": 9000
+    },
+    {
+      "epoch": 4.435682602267127,
+      "eval_accuracy": 0.9869708179202631,
+      "eval_f1": 0.5653222374580359,
+      "eval_loss": 0.038919780403375626,
+      "eval_precision": 0.7471566054243219,
+      "eval_recall": 0.4546699117736538,
+      "eval_runtime": 14.2717,
+      "eval_samples_per_second": 568.258,
+      "eval_steps_per_second": 2.242,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -243,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 181369839544038.0,
+  "total_flos": 204191913672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null