Training in progress, step 29000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62738e68c380b84e7ba5e70ed74beaef6dca37767638644ad9080404c2bc289d
+oid sha256:c3d3a07ae6da47a6ffe951aea757172b91a104ade84e1133f83bdc65dbf0fced
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc2b2d9610345b393e6a11d4aa099c4db304e875ebd163d9077cf1d6e12b09e
+oid sha256:84045260341781fd5db950741d3fad85d3e3ffa7a7b222322201c5e8b6f847ce
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b9d03691297dc71e66ee41b307397d343b7d27a3f7ccd654ec08e89e0e9ad3
+oid sha256:4e73cb909220f314d8bb2ce3c6b11d2d3d5ceafeda564a5681c9a84b2f38e70b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b205b52a82ca38a3bbc35d27e64c93a0ac87167c9e077557ca8c95371c1062
+oid sha256:c76e3ea474774b61d4cea19e7b0ce1e01ae99b8e67a194b3fa352d29ccf26585
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.029832862317562103,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-28000",
-  "epoch": 3.4521020835901863,
+  "best_metric": 0.029792238026857376,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-29000",
+  "epoch": 3.575391443718407,
   "eval_steps": 1000,
-  "global_step": 28000,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -735,6 +735,32 @@
       "eval_samples_per_second": 284.968,
       "eval_steps_per_second": 17.813,
       "step": 28000
+    },
+    {
+      "epoch": 3.5137467636542965,
+      "grad_norm": 0.2937909960746765,
+      "learning_rate": 1.2972506472691408e-05,
+      "loss": 0.0269,
+      "step": 28500
+    },
+    {
+      "epoch": 3.575391443718407,
+      "grad_norm": 0.46021705865859985,
+      "learning_rate": 1.2849217112563186e-05,
+      "loss": 0.0272,
+      "step": 29000
+    },
+    {
+      "epoch": 3.575391443718407,
+      "eval_accuracy": 0.9895558323661495,
+      "eval_f1": 0.6867029416765856,
+      "eval_loss": 0.029792238026857376,
+      "eval_precision": 0.7732886548587841,
+      "eval_recall": 0.6175548589341693,
+      "eval_runtime": 26.2698,
+      "eval_samples_per_second": 308.757,
+      "eval_steps_per_second": 19.3,
+      "step": 29000
     }
   ],
   "logging_steps": 500,
@@ -742,7 +768,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 633129160062492.0,
+  "total_flos": 655800681523140.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null