Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715065202aecffcbafb8323a611ae9cbb04f68822e213a75eb819bbcf410e294
+oid sha256:4a3f2495790d9d44289a93b7b20ce1ffab8fa55eb1e2cfcbab6fcee33704b5eb
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ecb9542d4cc2a91269789aff2a462f7551a9f9f55f0a8e36de9a77bc8706f7
+oid sha256:8413ab76e5e1e1fe5f74863fe18a552d4660035148acf70bf16e60667aecbfa7
 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": 0.04674109071493149,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-5000",
-  "epoch": 2.465483234714004,
+  "best_metric": 0.042755745351314545,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/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": 564.763,
       "eval_steps_per_second": 2.228,
       "step": 5000
+    },
+    {
+      "epoch": 2.712031558185404,
+      "grad_norm": 0.36567422747612,
+      "learning_rate": 1.9457593688362923e-05,
+      "loss": 0.0449,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 0.4769591689109802,
+      "learning_rate": 1.940828402366864e-05,
+      "loss": 0.0433,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_accuracy": 0.9859475317828139,
+      "eval_f1": 0.484694142716075,
+      "eval_loss": 0.042755745351314545,
+      "eval_precision": 0.7564892926670993,
+      "eval_recall": 0.3565802554102623,
+      "eval_runtime": 14.1095,
+      "eval_samples_per_second": 574.791,
+      "eval_steps_per_second": 2.268,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -165,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 112700461753656.0,
+  "total_flos": 135256930917768.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null