Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41265f9920783a5a84cfe44c3bb367dfa635ab8d97bfec55cc560632190e590
+oid sha256:259d5dbd58ddb936ce7b5dbc79e8f28d6862e2e6fb252ba87080dd57d1cfe74d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e0267258c5346e8d50445e28f13662c5f37ac7095267ab854ceb9a7395e834
+oid sha256:d590eb67d97bb6c33f59de5c7c6e35239e0a57a8f95e409c936c7324b3a516f1
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64b28e054193eaeff0d625fef705a5122942e1a18af84585e7031e05f4d367e
+oid sha256:f8a5b7fde4c37eeccbe4aca8abd49518b2e855ca1720563c5af4866d40338cb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046f36a4f886839ef562bc29cbdb24226b9e49f224c3433541f83d2a6ddde8eb
+oid sha256:c57b43b54c171b469f2109727ed655fc17fadbe3181e8c53e731dcc4f4e6bbd9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.05670051649212837,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-3000",
-  "epoch": 1.4785608674223756,
+  "best_metric": 0.049183741211891174,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-4000",
+  "epoch": 1.9714144898965007,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,32 @@
       "eval_samples_per_second": 568.448,
       "eval_steps_per_second": 2.243,
       "step": 3000
+    },
+    {
+      "epoch": 1.724987678659438,
+      "grad_norm": 0.3530617356300354,
+      "learning_rate": 1.9655002464268113e-05,
+      "loss": 0.0565,
+      "step": 3500
+    },
+    {
+      "epoch": 1.9714144898965007,
+      "grad_norm": 0.3648615777492523,
+      "learning_rate": 1.96057171020207e-05,
+      "loss": 0.0535,
+      "step": 4000
+    },
+    {
+      "epoch": 1.9714144898965007,
+      "eval_accuracy": 0.9842510310812534,
+      "eval_f1": 0.33580394500896593,
+      "eval_loss": 0.049183741211891174,
+      "eval_precision": 0.7841987716359575,
+      "eval_recall": 0.21364466078491026,
+      "eval_runtime": 14.4394,
+      "eval_samples_per_second": 561.657,
+      "eval_steps_per_second": 2.216,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -113,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 68043845709666.0,
+  "total_flos": 90673906883274.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null