Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99ea8a951670df195f279acccd2d313b2dd58513793b2775f60a7410f38a8a5
+oid sha256:ec687cb4cf3c1a63b7c0cf984927892a5c40a9016826d6b333cda3c07f247c6d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a91f8cc1d7e3a8c2f5e5b6cd501624ceeba457fe1d55880ddea9c8fab1e60b
+oid sha256:fc99ad5a91c437864a61c3e9c4513dbab499871780ae574daccaf5b662db3387
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b696e420cb3a22c4263985de2c775e7feed84b140b3b4ea30f758865a3acf5
+oid sha256:93f0e9cc44a5d6ccaee93162e56f359da5c2b4c7afde86d9957879ed20b028a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a79d32d6e0fee32029e2310797f86c13defa1fcf2e3d24a796b9945791ee776
+oid sha256:8fc5202904cf5915604424b70e014b8084586938c2e29300d7ed606d964f0365
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0323067270219326,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-16000",
-  "epoch": 2.095919122179756,
+  "best_metric": 0.0319632813334465,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-18000",
+  "epoch": 2.2192084823079767,
   "eval_steps": 1000,
-  "global_step": 17000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -449,6 +449,32 @@
       "eval_samples_per_second": 299.979,
       "eval_steps_per_second": 18.751,
       "step": 17000
+    },
+    {
+      "epoch": 2.1575638022438666,
+      "grad_norm": 0.5995791554450989,
+      "learning_rate": 1.568487239551227e-05,
+      "loss": 0.0305,
+      "step": 17500
+    },
+    {
+      "epoch": 2.2192084823079767,
+      "grad_norm": 0.47302648425102234,
+      "learning_rate": 1.5561583035384046e-05,
+      "loss": 0.0308,
+      "step": 18000
+    },
+    {
+      "epoch": 2.2192084823079767,
+      "eval_accuracy": 0.9887707483947583,
+      "eval_f1": 0.6517841448409211,
+      "eval_loss": 0.0319632813334465,
+      "eval_precision": 0.766353208639041,
+      "eval_recall": 0.5670158268980809,
+      "eval_runtime": 26.7148,
+      "eval_samples_per_second": 303.615,
+      "eval_steps_per_second": 18.978,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
@@ -456,7 +482,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 384576294018456.0,
+  "total_flos": 407169040933728.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null