Training in progress, step 26000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1bde5b6be4d22f988eda04d97f0607bf649798d2d3c0acfccc8df640690b06
+oid sha256:3cbd63eda678f66ec580647b07be68c8743cd98cdf0b387eabede8ede6bcae6e
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116c2ffba27b86eabecc66bf3cabfb8174905826dd09a796a36cd692e4dfd260
+oid sha256:08283207145443799a64119692d2ee9ee3eea4d943297e0d512b9da504c5ef93
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a5269f91fcc98a58427f6cc2fdaa68df40a7721de49cb312375e263409c13b
+oid sha256:793caa5e4418f4422d5d92252c23e8874e978cd59b9e9a633c26689ccb78fa7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6ce615a698f7568cacdf7c4a6bc20daf8e2bb504b05428ec3aba86d5638ee07
+oid sha256:9af05cf80d8d6f86618fa017634a924537705f0ef8cc7edcf2a808680566ba4d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.030400587245821953,
   "best_model_checkpoint": "doc-topic-model/checkpoint-25000",
-  "epoch": 3.0822340032055235,
+  "epoch": 3.2055233633337443,
   "eval_steps": 1000,
-  "global_step": 25000,
+  "global_step": 26000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -657,6 +657,32 @@
       "eval_samples_per_second": 309.458,
       "eval_steps_per_second": 19.344,
       "step": 25000
+    },
+    {
+      "epoch": 3.1438786832696337,
+      "grad_norm": 0.539164125919342,
+      "learning_rate": 1.3712242633460732e-05,
+      "loss": 0.0272,
+      "step": 25500
+    },
+    {
+      "epoch": 3.2055233633337443,
+      "grad_norm": 0.36777427792549133,
+      "learning_rate": 1.3588953273332512e-05,
+      "loss": 0.0275,
+      "step": 26000
+    },
+    {
+      "epoch": 3.2055233633337443,
+      "eval_accuracy": 0.9893092536458932,
+      "eval_f1": 0.6747995516854902,
+      "eval_loss": 0.03040589578449726,
+      "eval_precision": 0.7734954046842574,
+      "eval_recall": 0.5984402477253613,
+      "eval_runtime": 27.3631,
+      "eval_samples_per_second": 296.421,
+      "eval_steps_per_second": 18.529,
+      "step": 26000
     }
   ],
   "logging_steps": 500,
@@ -664,7 +690,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 565404817689828.0,
+  "total_flos": 588002747140980.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null