Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f89e9db5d95750cecfaa53b5d3dca05f5494600d9a038e7024b9513077c0d09d
+oid sha256:a5305db9dc3b35ada7e28de471d8a93c198fce0e6179c8f4843c1cad98f9ff05
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43ff5d20f9d462ed326803c9783439fe2343fe681ed65c375f83f7343047600
+oid sha256:cae873e04ea15e075c791a470276bf6aed8e32e21a540007436243d921549bbb
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70319a98fe46546d0ea83643bfec3abda12b773576a6b0aedf720557d6dc5c08
+oid sha256:6d088be71b0db07e8ca0115c931279967e5eb53f1c7bedd90a04ccd028d145ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0d23db6202d1dfbe74f3f933c1aa1ed74d84a406d2edf78292e88e0c12c973
+oid sha256:db4a9f0952f38c2a7352c6af4e8357c1d43055d3b068e5edda6136fb17f11371
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03410067781805992,
   "best_model_checkpoint": "doc-topic-model/checkpoint-12000",
-  "epoch": 1.4794723215386512,
+  "epoch": 1.6027616816668722,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,6 +319,32 @@
       "eval_samples_per_second": 303.351,
       "eval_steps_per_second": 18.962,
       "step": 12000
+    },
+    {
+      "epoch": 1.5411170016027618,
+      "grad_norm": 0.4056677222251892,
+      "learning_rate": 1.6917765996794478e-05,
+      "loss": 0.0358,
+      "step": 12500
+    },
+    {
+      "epoch": 1.6027616816668722,
+      "grad_norm": 0.4474567770957947,
+      "learning_rate": 1.6794476636666258e-05,
+      "loss": 0.0348,
+      "step": 13000
+    },
+    {
+      "epoch": 1.6027616816668722,
+      "eval_accuracy": 0.9879474022081549,
+      "eval_f1": 0.6121927864666454,
+      "eval_loss": 0.03413223475217819,
+      "eval_precision": 0.758359692724808,
+      "eval_recall": 0.5132655401789128,
+      "eval_runtime": 26.2727,
+      "eval_samples_per_second": 308.724,
+      "eval_steps_per_second": 19.298,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -326,7 +352,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 271445681786760.0,
+  "total_flos": 294192868271256.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null