Training in progress, step 36000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8346908bf33687376184a75bfa80d3fd1f182516ba546d99d10270d43f363880
+oid sha256:9245d84373d3b12c27df7cecfd5cb67f503038217a09a8fa66c6ed11fabdb66d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b1c6f2850c1e00fceac60d726fdc10fbc6ec5c53769c1b8c10d41336136e2d
+oid sha256:f393e50657c26885a52a8001da713333d43f6c421fad3acc87275790b0eede21
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44cdbc3cbc2fbec16032486dcd5ac6cde146de3cbbd02f673160412d3f17fbdf
+oid sha256:b686a640da84061f259c5a5a5135b005a1c3602970c796a5b2db1de5bbc4c327
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092713bf5ba390f71c98aec74472365921cd4ea46843b398ad777a61cf2e4830
+oid sha256:913eadf36f83dad6af3b7da8337c81eb368b5e4165fc481d8542ba2714a66944
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.029198406264185905,
   "best_model_checkpoint": "doc-topic-model/checkpoint-33000",
-  "epoch": 4.315127604487733,
+  "epoch": 4.4384169646159535,
   "eval_steps": 1000,
-  "global_step": 35000,
+  "global_step": 36000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -917,6 +917,32 @@
       "eval_samples_per_second": 289.801,
       "eval_steps_per_second": 18.115,
       "step": 35000
+    },
+    {
+      "epoch": 4.376772284551843,
+      "grad_norm": 0.44469302892684937,
+      "learning_rate": 1.1246455430896314e-05,
+      "loss": 0.025,
+      "step": 35500
+    },
+    {
+      "epoch": 4.4384169646159535,
+      "grad_norm": 0.6926087737083435,
+      "learning_rate": 1.1123166070768094e-05,
+      "loss": 0.0241,
+      "step": 36000
+    },
+    {
+      "epoch": 4.4384169646159535,
+      "eval_accuracy": 0.989632356796574,
+      "eval_f1": 0.6952174637560407,
+      "eval_loss": 0.02927555702626705,
+      "eval_precision": 0.7637528604118993,
+      "eval_recall": 0.6379692637051763,
+      "eval_runtime": 26.5512,
+      "eval_samples_per_second": 305.485,
+      "eval_steps_per_second": 19.095,
+      "step": 36000
     }
   ],
   "logging_steps": 500,
@@ -924,7 +950,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 791632873923588.0,
+  "total_flos": 814212146245572.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null