Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3186390ad438c7b0494839975b0c84b9377f4176e8af7e88f305ecb73994c4
+oid sha256:5ab54cdd6804c1f69dcbb1927b975d5309301ea7f09f14368ff5cb936f54fbbe
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2837b23275b182c3f3a9afc2f06ee97f7bfc3bcf6b533ea744dda23ad6eaaeb6
+oid sha256:f641ecb4950374542e19c7095a38f78489fe81cefbb63936c201a904573a2cdc
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
+oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
+oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04658225178718567,
-  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-5000",
-  "epoch": 2.465483234714004,
+  "best_metric": 0.044097188860177994,
+  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-6000",
+  "epoch": 2.9585798816568047,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,6 +137,32 @@
       "eval_samples_per_second": 560.288,
       "eval_steps_per_second": 2.21,
       "step": 5000
+    },
+    {
+      "epoch": 2.712031558185404,
+      "grad_norm": 0.42049625515937805,
+      "learning_rate": 1.9457593688362923e-05,
+      "loss": 0.0463,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 0.41673073172569275,
+      "learning_rate": 1.940828402366864e-05,
+      "loss": 0.0453,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_accuracy": 0.9859003075807098,
+      "eval_f1": 0.5020016012810248,
+      "eval_loss": 0.044097188860177994,
+      "eval_precision": 0.7244367417677643,
+      "eval_recall": 0.38407350689127107,
+      "eval_runtime": 14.4621,
+      "eval_samples_per_second": 560.982,
+      "eval_steps_per_second": 2.213,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -165,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 113179328068968.0,
+  "total_flos": 135803170199520.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null