Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee2b31ed9bcba208a9c79ee3b40aa491d32a034da09678bdbc1e4b013eb4493
+oid sha256:180c59532e67e2a42ff36f33e417d2684be2f4099397090c274a2291b88d4251
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3339164a0051af4d619463786dbb2c5468ff9acb343d82a01f625a04dadb257c
+oid sha256:da38f6314d96ba0c6df902c61eafa71a0bdf1d073b8b7027ae16768d28605572
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3423752383b460d81921e040320adc06ebc531dda60b0a8779f70aa3d3547d66
+oid sha256:2356e526daacaf3cddef386079df98ea0601ca2882bbb34b98fe16bdae5145ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2dfb71ca7e21eba0bfcf4443439b5f61c88455cedeb3b4671c00055ea293f8
+oid sha256:cd2c3e094b5ddaeb89ee4b7c0b707aa950f4b94460991a5994dffa66d0682ac2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.06931016594171524,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-2000",
-  "epoch": 0.24657872025644187,
+  "best_metric": 0.057068832218647,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-3000",
+  "epoch": 0.3698680803846628,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,32 @@
       "eval_samples_per_second": 308.24,
       "eval_steps_per_second": 19.267,
       "step": 2000
+    },
+    {
+      "epoch": 0.30822340032055234,
+      "grad_norm": 0.37316232919692993,
+      "learning_rate": 1.9383553199358898e-05,
+      "loss": 0.0684,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3698680803846628,
+      "grad_norm": 0.38068899512290955,
+      "learning_rate": 1.9260263839230674e-05,
+      "loss": 0.0631,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3698680803846628,
+      "eval_accuracy": 0.9820110903739352,
+      "eval_f1": 0.07126134035703834,
+      "eval_loss": 0.057068832218647,
+      "eval_precision": 0.8268251273344652,
+      "eval_recall": 0.03723526263475801,
+      "eval_runtime": 27.0378,
+      "eval_samples_per_second": 299.987,
+      "eval_steps_per_second": 18.751,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -66,7 +92,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 45362736557640.0,
+  "total_flos": 67961702515968.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null