Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587b463eff4fb70a2a1f6e50180e073f772db790d53aabe76c5367e410d330f4
+oid sha256:7bfd067bc61e6bfcc59e3c54cec1c0021060e09321f234f56691f2aa3478b074
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a484a9a006360ee96289080be4d9d9487eaa82dbc55607e7559d36071f6f073
+oid sha256:0bb831687d2acfe6bf1e666a18d84fc971aa14a65e6c52db2330c0ec58eb8e40
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a5b7fde4c37eeccbe4aca8abd49518b2e855ca1720563c5af4866d40338cb0
+oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4834ce2586dc426079f90c930b0e0d6ec21ad9d8a256946c64bb3fc73152baa
+oid sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04979131370782852,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-4000",
-  "epoch": 1.972386587771203,
+  "best_metric": 0.04605511203408241,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-5000",
+  "epoch": 2.465483234714004,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,32 @@
       "eval_samples_per_second": 556.302,
       "eval_steps_per_second": 2.195,
       "step": 4000
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.3279891312122345,
+      "learning_rate": 1.9556213017751483e-05,
+      "loss": 0.0488,
+      "step": 4500
+    },
+    {
+      "epoch": 2.465483234714004,
+      "grad_norm": 0.4424910843372345,
+      "learning_rate": 1.95069033530572e-05,
+      "loss": 0.048,
+      "step": 5000
+    },
+    {
+      "epoch": 2.465483234714004,
+      "eval_accuracy": 0.985223294641212,
+      "eval_f1": 0.4251213056903397,
+      "eval_loss": 0.04605511203408241,
+      "eval_precision": 0.7708458308338332,
+      "eval_recall": 0.29349067377236393,
+      "eval_runtime": 14.4651,
+      "eval_samples_per_second": 560.659,
+      "eval_steps_per_second": 2.212,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 90534755794896.0,
+  "total_flos": 113147714600100.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null