Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f74e82b4b53fcee32f5446bf0b5381ab072b7fe85388f33390750ead59cc4a
+oid sha256:8346908bf33687376184a75bfa80d3fd1f182516ba546d99d10270d43f363880
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6242dfd13e0ceb88ea3211d3cf85449e825b9b2d40156c3e62e9be2da7922ecb
+oid sha256:46b1c6f2850c1e00fceac60d726fdc10fbc6ec5c53769c1b8c10d41336136e2d
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6c045b436278549bdbc660efc96a3d35a76efb024c2b69675acaf5d2edb3b5
+oid sha256:44cdbc3cbc2fbec16032486dcd5ac6cde146de3cbbd02f673160412d3f17fbdf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abec6fd21b60e43c2541bef1c7779d397c66d374dbfc7c3e8dcafa185a2976b
+oid sha256:092713bf5ba390f71c98aec74472365921cd4ea46843b398ad777a61cf2e4830
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.029198406264185905,
   "best_model_checkpoint": "doc-topic-model/checkpoint-33000",
-  "epoch": 4.191838244359512,
+  "epoch": 4.315127604487733,
   "eval_steps": 1000,
-  "global_step": 34000,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -891,6 +891,32 @@
       "eval_samples_per_second": 307.637,
       "eval_steps_per_second": 19.23,
       "step": 34000
+    },
+    {
+      "epoch": 4.253482924423622,
+      "grad_norm": 0.42990005016326904,
+      "learning_rate": 1.1493034151152756e-05,
+      "loss": 0.0242,
+      "step": 34500
+    },
+    {
+      "epoch": 4.315127604487733,
+      "grad_norm": 0.4957457184791565,
+      "learning_rate": 1.1369744791024534e-05,
+      "loss": 0.024,
+      "step": 35000
+    },
+    {
+      "epoch": 4.315127604487733,
+      "eval_accuracy": 0.9897088812269984,
+      "eval_f1": 0.6963539053353404,
+      "eval_loss": 0.029602373018860817,
+      "eval_precision": 0.7683860847097905,
+      "eval_recall": 0.6366694701429773,
+      "eval_runtime": 27.9882,
+      "eval_samples_per_second": 289.801,
+      "eval_steps_per_second": 18.115,
+      "step": 35000
     }
   ],
   "logging_steps": 500,
@@ -898,7 +924,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 768934403276364.0,
+  "total_flos": 791632873923588.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null