Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14423a95c69ca92b5c42c52b231145f3606fcc0596cfcbd8c9ac28eca7d08217
+oid sha256:ca3d01ccbc2f46468952e0767a827e92c923d0fe50acfbf704b2386092cccacb
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebf8f9c1a5f4131340bda712dcbcf0877372297c7065ef54d3451de93a0ff3a
+oid sha256:33811a66ae2f539db3741cebc74612b4148ddad8e6219231260bf9b7d0bd3be4
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4dc0d213e586bcd1df72750fb141783e5bfcc19f8684cdb03d84fb58c77cd64
+oid sha256:aa7fcb3233d0cc25d1a48ce8cd416cdb8e7197f92de2264ae7016915d03ce48d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91abd785f843b56723551602f2cdb78afbb89b1cb7bd96e4cdc2fd019d5d8e6d
+oid sha256:e039ca70063df243e36a1f08dbf7d4436dc130b61c968cb193766016893f85f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03985895588994026,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-7000",
-  "epoch": 0.8630255208975466,
+  "best_metric": 0.037820931524038315,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-8000",
+  "epoch": 0.9863148810257675,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,32 @@
       "eval_samples_per_second": 309.828,
       "eval_steps_per_second": 19.367,
       "step": 7000
+    },
+    {
+      "epoch": 0.924670200961657,
+      "grad_norm": 0.3766914904117584,
+      "learning_rate": 1.8150659598076686e-05,
+      "loss": 0.0426,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9863148810257675,
+      "grad_norm": 0.3016286790370941,
+      "learning_rate": 1.8027370237948466e-05,
+      "loss": 0.0415,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9863148810257675,
+      "eval_accuracy": 0.9869695900416208,
+      "eval_f1": 0.560279278848453,
+      "eval_loss": 0.037820931524038315,
+      "eval_precision": 0.7479570990806946,
+      "eval_recall": 0.44789356984478934,
+      "eval_runtime": 26.4209,
+      "eval_samples_per_second": 306.992,
+      "eval_steps_per_second": 19.189,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -196,7 +222,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 158393844100440.0,
+  "total_flos": 180973116422424.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null