Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:259d5dbd58ddb936ce7b5dbc79e8f28d6862e2e6fb252ba87080dd57d1cfe74d
+oid sha256:e72144d54bcc5be126ed76a60d0546279dee7f1a463d94e91f15bf80a5d86ec5
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d590eb67d97bb6c33f59de5c7c6e35239e0a57a8f95e409c936c7324b3a516f1
+oid sha256:ba57df416a78aadf086b9109b9f1564080f49bfa03a033040dba3a5234da3ab0
 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:c57b43b54c171b469f2109727ed655fc17fadbe3181e8c53e731dcc4f4e6bbd9
+oid sha256:ac39890beed6f47b99e7a6478c8d7f5d405911830cdb68c8f08f50e9a97932b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.049183741211891174,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-4000",
-  "epoch": 1.9714144898965007,
+  "best_metric": 0.045466337352991104,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-5000",
+  "epoch": 2.464268112370626,
   "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": 561.657,
       "eval_steps_per_second": 2.216,
       "step": 4000
+    },
+    {
+      "epoch": 2.2178413011335634,
+      "grad_norm": 0.4629921317100525,
+      "learning_rate": 1.955643173977329e-05,
+      "loss": 0.0479,
+      "step": 4500
+    },
+    {
+      "epoch": 2.464268112370626,
+      "grad_norm": 0.38679325580596924,
+      "learning_rate": 1.9507146377525875e-05,
+      "loss": 0.0473,
+      "step": 5000
+    },
+    {
+      "epoch": 2.464268112370626,
+      "eval_accuracy": 0.9854925804668566,
+      "eval_f1": 0.46681946036045424,
+      "eval_loss": 0.045466337352991104,
+      "eval_precision": 0.7406611570247934,
+      "eval_recall": 0.3408122908427137,
+      "eval_runtime": 14.1723,
+      "eval_samples_per_second": 572.243,
+      "eval_steps_per_second": 2.258,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 90673906883274.0,
+  "total_flos": 113366676741030.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null