Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0198ee7059c347160690c553d247336d24eb495722d177cedb32f54c9e357a
+oid sha256:0b1bde5b6be4d22f988eda04d97f0607bf649798d2d3c0acfccc8df640690b06
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d143e47900c9b23372846634318a106311c5a735b9c0a978595ae5c988e8504
+oid sha256:116c2ffba27b86eabecc66bf3cabfb8174905826dd09a796a36cd692e4dfd260
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c47bc6814f3b2cc652539b879c8dd04a01b11a1d74628bcdc13005dca3efe8
+oid sha256:a8a5269f91fcc98a58427f6cc2fdaa68df40a7721de49cb312375e263409c13b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4979df536fde7ecfc0fbbf848b5153088756d28c508a484bc722499762180f
+oid sha256:b6ce615a698f7568cacdf7c4a6bc20daf8e2bb504b05428ec3aba86d5638ee07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.030529338866472244,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-23000",
-  "epoch": 2.9589446430773023,
+  "best_metric": 0.030400587245821953,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-25000",
+  "epoch": 3.0822340032055235,
   "eval_steps": 1000,
-  "global_step": 24000,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,6 +631,32 @@
       "eval_samples_per_second": 304.031,
       "eval_steps_per_second": 19.004,
       "step": 24000
+    },
+    {
+      "epoch": 3.020589323141413,
+      "grad_norm": 0.15014292299747467,
+      "learning_rate": 1.3958821353717176e-05,
+      "loss": 0.0282,
+      "step": 24500
+    },
+    {
+      "epoch": 3.0822340032055235,
+      "grad_norm": 0.36681485176086426,
+      "learning_rate": 1.3835531993588956e-05,
+      "loss": 0.0271,
+      "step": 25000
+    },
+    {
+      "epoch": 3.0822340032055235,
+      "eval_accuracy": 0.989312087884057,
+      "eval_f1": 0.6787904599659285,
+      "eval_loss": 0.030400587245821953,
+      "eval_precision": 0.7661763291991155,
+      "eval_recall": 0.6092973468919642,
+      "eval_runtime": 26.2103,
+      "eval_samples_per_second": 309.458,
+      "eval_steps_per_second": 19.344,
+      "step": 25000
     }
   ],
   "logging_steps": 500,
@@ -638,7 +664,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 542875815965880.0,
+  "total_flos": 565404817689828.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null