Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8234dae96ba7260c611f7d9702611e59aeab592fd4574af1a5612a44d212b476
+oid sha256:14423a95c69ca92b5c42c52b231145f3606fcc0596cfcbd8c9ac28eca7d08217
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d607fab1f4688e5bec6ee2e6ac20d4ab1c590cd9491384d208084d34cac184b4
+oid sha256:1ebf8f9c1a5f4131340bda712dcbcf0877372297c7065ef54d3451de93a0ff3a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f714de4718c9f1d44807a05241d81ef45fb7284a03e54b16395bd62796dc0d80
+oid sha256:f4dc0d213e586bcd1df72750fb141783e5bfcc19f8684cdb03d84fb58c77cd64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa82bd145226380bce05f85478c748b91192c52d2324974f8354d5aa36dd6af
+oid sha256:91abd785f843b56723551602f2cdb78afbb89b1cb7bd96e4cdc2fd019d5d8e6d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.042106639593839645,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-6000",
-  "epoch": 0.7397361607693256,
+  "best_metric": 0.03985895588994026,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-7000",
+  "epoch": 0.8630255208975466,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,32 @@
       "eval_samples_per_second": 309.867,
       "eval_steps_per_second": 19.369,
       "step": 6000
+    },
+    {
+      "epoch": 0.8013808408334361,
+      "grad_norm": 0.3768202066421509,
+      "learning_rate": 1.839723831833313e-05,
+      "loss": 0.0443,
+      "step": 6500
+    },
+    {
+      "epoch": 0.8630255208975466,
+      "grad_norm": 0.4180874526500702,
+      "learning_rate": 1.827394895820491e-05,
+      "loss": 0.0427,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8630255208975466,
+      "eval_accuracy": 0.9864466731003873,
+      "eval_f1": 0.5342812621737437,
+      "eval_loss": 0.03985895588994026,
+      "eval_precision": 0.735684591658844,
+      "eval_recall": 0.41945102836608306,
+      "eval_runtime": 26.179,
+      "eval_samples_per_second": 309.828,
+      "eval_steps_per_second": 19.367,
+      "step": 7000
     }
   ],
   "logging_steps": 500,
@@ -170,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 135822863835864.0,
+  "total_flos": 158393844100440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null