Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888f30c08fc871ee89b2ed65aa59014c51e45b84bf83ac3179b9deb9ed86470e
+oid sha256:e99ea8a951670df195f279acccd2d313b2dd58513793b2775f60a7410f38a8a5
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:119d4d9a4c44dda0c9536517afae5273a65c3c1343185258bd68b1f9c6c0eca7
+oid sha256:e7a91f8cc1d7e3a8c2f5e5b6cd501624ceeba457fe1d55880ddea9c8fab1e60b
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:569537b3349a1263ef5364a44403c07c16a743e01891e82c4eec71160306f641
+oid sha256:60b696e420cb3a22c4263985de2c775e7feed84b140b3b4ea30f758865a3acf5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab36b245ea824451ef011c271839e80b2973196a36f183104d5550cef0ba7cb
+oid sha256:9a79d32d6e0fee32029e2310797f86c13defa1fcf2e3d24a796b9945791ee776
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0323067270219326,
   "best_model_checkpoint": "doc-topic-model/checkpoint-16000",
-  "epoch": 1.972629762051535,
+  "epoch": 2.095919122179756,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,6 +423,32 @@
       "eval_samples_per_second": 307.771,
       "eval_steps_per_second": 19.238,
       "step": 16000
+    },
+    {
+      "epoch": 2.0342744421156453,
+      "grad_norm": 0.4357479512691498,
+      "learning_rate": 1.593145111576871e-05,
+      "loss": 0.0322,
+      "step": 16500
+    },
+    {
+      "epoch": 2.095919122179756,
+      "grad_norm": 0.40149009227752686,
+      "learning_rate": 1.580816175564049e-05,
+      "loss": 0.0309,
+      "step": 17000
+    },
+    {
+      "epoch": 2.095919122179756,
+      "eval_accuracy": 0.9887041437979075,
+      "eval_f1": 0.6466285410293922,
+      "eval_loss": 0.03258202597498894,
+      "eval_precision": 0.7694661320953787,
+      "eval_recall": 0.5576114381833474,
+      "eval_runtime": 27.0385,
+      "eval_samples_per_second": 299.979,
+      "eval_steps_per_second": 18.751,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -430,7 +456,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 361961780452488.0,
+  "total_flos": 384576294018456.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null