Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63eb21b9e1cf0bf907284263d4a9338422b7e189e5c909d860a7e71d14a4c2ae
+oid sha256:c6f129518f061dfb2d30012ee249b910fe2448595d1cd6db3c6b9c197cebdc61
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a4128037147f3652b538c047a600b904144cfd95ce967abe8a3e0c26a0b50c
+oid sha256:0aa01671de9f9e7ea7498e79eb24b4eea4609e72a3b79a33573bd9681fa06142
 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": 0.04508376494050026,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-5000",
-  "epoch": 2.465483234714004,
+  "best_metric": 0.04229620099067688,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/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": 569.119,
       "eval_steps_per_second": 2.246,
       "step": 5000
+    },
+    {
+      "epoch": 2.712031558185404,
+      "grad_norm": 0.48908740282058716,
+      "learning_rate": 1.9457593688362923e-05,
+      "loss": 0.0453,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 0.3385593891143799,
+      "learning_rate": 1.940828402366864e-05,
+      "loss": 0.0441,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_accuracy": 0.9862465807786612,
+      "eval_f1": 0.5088571717785201,
+      "eval_loss": 0.04229620099067688,
+      "eval_precision": 0.7590215914238261,
+      "eval_recall": 0.3827179291968024,
+      "eval_runtime": 14.2621,
+      "eval_samples_per_second": 568.641,
+      "eval_steps_per_second": 2.244,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -165,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 112902580652976.0,
+  "total_flos": 135494291061072.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null