Training in progress, step 27000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbd63eda678f66ec580647b07be68c8743cd98cdf0b387eabede8ede6bcae6e
+oid sha256:7245803078fac2f6255059cb485ab88160cd760360b664789085d780d2500207
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08283207145443799a64119692d2ee9ee3eea4d943297e0d512b9da504c5ef93
+oid sha256:32e26a150bf4dd6f1ce2b2121ef1b2bd1b961eec79f861a295ea1c13e225ce5e
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793caa5e4418f4422d5d92252c23e8874e978cd59b9e9a633c26689ccb78fa7d
+oid sha256:11a441c71135cb22b0428492e00c565a64170f2a3da561a8d3a1b52db0b9efbc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af05cf80d8d6f86618fa017634a924537705f0ef8cc7edcf2a808680566ba4d
+oid sha256:28b921d2b6bf7a59d1fc691704cd7a4e3a1229a1cb800d6477437d3eb81e3bf9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.030400587245821953,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-25000",
-  "epoch": 3.2055233633337443,
+  "best_metric": 0.030225617811083794,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-27000",
+  "epoch": 3.328812723461965,
   "eval_steps": 1000,
-  "global_step": 26000,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -683,6 +683,32 @@
       "eval_samples_per_second": 296.421,
       "eval_steps_per_second": 18.529,
       "step": 26000
+    },
+    {
+      "epoch": 3.267168043397855,
+      "grad_norm": 0.24132761359214783,
+      "learning_rate": 1.3465663913204292e-05,
+      "loss": 0.0271,
+      "step": 26500
+    },
+    {
+      "epoch": 3.328812723461965,
+      "grad_norm": 0.40002453327178955,
+      "learning_rate": 1.334237455307607e-05,
+      "loss": 0.0273,
+      "step": 27000
+    },
+    {
+      "epoch": 3.328812723461965,
+      "eval_accuracy": 0.9894750565784793,
+      "eval_f1": 0.678136511375948,
+      "eval_loss": 0.030225617811083794,
+      "eval_precision": 0.7827130852340937,
+      "eval_recall": 0.5982108723908556,
+      "eval_runtime": 26.2863,
+      "eval_samples_per_second": 308.564,
+      "eval_steps_per_second": 19.288,
+      "step": 27000
     }
   ],
   "logging_steps": 500,
@@ -690,7 +716,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 588002747140980.0,
+  "total_flos": 610656647979636.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null