Training in progress, step 21000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb8908b36d53267daa6b1c19c0f79889b634a80860d824372a3056b7d871286
+oid sha256:bc8d8ca9dce7d245120056bb7da047919672df31daef21ff9f779c4bb8748f19
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e28f021c73463e4442bd785612d072912429af19628c61b7f5b80b31f266ad2
+oid sha256:e9fe94f39831d020574c7f3fb491e79b550a3538949c892b212fcec33d591b11
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155ad12ff52df5f6bd601bf6db8835e792082e2ea71e126fb23e84367e27ff3c
+oid sha256:4a1de26c20e82e441893712f1b5b4dc9634b784afefb290ea79f2ec04450d39c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269db43e729ed0472aa01beafe0cac4ffe78f8c5279a6ce5b3a8d14f0a831d61
+oid sha256:38b019c379cd8b30080bc0a4d446967146c21b6a2da6f9b7f6bc2fe472aaa779
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03719973564147949,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-16000",
-  "epoch": 9.861932938856016,
+  "epoch": 10.355029585798816,
   "eval_steps": 1000,
-  "global_step": 20000,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -527,6 +527,32 @@
       "eval_samples_per_second": 563.339,
       "eval_steps_per_second": 2.222,
       "step": 20000
+    },
+    {
+      "epoch": 10.108481262327416,
+      "grad_norm": 0.18375088274478912,
+      "learning_rate": 1.7978796844181462e-05,
+      "loss": 0.0175,
+      "step": 20500
+    },
+    {
+      "epoch": 10.355029585798816,
+      "grad_norm": 0.13978295028209686,
+      "learning_rate": 1.7929487179487182e-05,
+      "loss": 0.0159,
+      "step": 21000
+    },
+    {
+      "epoch": 10.355029585798816,
+      "eval_accuracy": 0.9879291218436141,
+      "eval_f1": 0.641504670537743,
+      "eval_loss": 0.03958018124103546,
+      "eval_precision": 0.7120306370259667,
+      "eval_recall": 0.5836906584992343,
+      "eval_runtime": 14.3748,
+      "eval_samples_per_second": 564.392,
+      "eval_steps_per_second": 2.226,
+      "step": 21000
     }
   ],
   "logging_steps": 500,
@@ -550,12 +576,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 452312037970056.0,
+  "total_flos": 474932252325492.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null