Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041ce8f32ce552119e7b1d4237f62d551c007214b038e2e85e9201a6801f1604
+oid sha256:fe68f4577286b85cbc5c6a48af902103215e6d0a6d1406ab180a643234b19700
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eccf747ca8c8c8db9575b2956c6dd997a8eb4b5311ef905ec24ee3407e8cf61
+oid sha256:f0177ee53022f715e3a3e89ac556dbf20c1d9fd7f663800df2375e52c0556c37
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
+oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
+oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04347195476293564,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-6000",
-  "epoch": 2.9585798816568047,
+  "best_metric": 0.040071167051792145,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-8000",
+  "epoch": 3.9447731755424065,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,58 @@
       "eval_samples_per_second": 570.842,
       "eval_steps_per_second": 2.252,
       "step": 6000
+    },
+    {
+      "epoch": 3.2051282051282053,
+      "grad_norm": 0.47004055976867676,
+      "learning_rate": 1.935897435897436e-05,
+      "loss": 0.0409,
+      "step": 6500
+    },
+    {
+      "epoch": 3.4516765285996054,
+      "grad_norm": 0.3331545293331146,
+      "learning_rate": 1.930966469428008e-05,
+      "loss": 0.0395,
+      "step": 7000
+    },
+    {
+      "epoch": 3.4516765285996054,
+      "eval_accuracy": 0.9860283175305072,
+      "eval_f1": 0.5278735632183909,
+      "eval_loss": 0.041799116879701614,
+      "eval_precision": 0.7115558424790187,
+      "eval_recall": 0.4195660449181576,
+      "eval_runtime": 14.3982,
+      "eval_samples_per_second": 563.265,
+      "eval_steps_per_second": 2.223,
+      "step": 7000
+    },
+    {
+      "epoch": 3.698224852071006,
+      "grad_norm": 0.46907347440719604,
+      "learning_rate": 1.92603550295858e-05,
+      "loss": 0.0382,
+      "step": 7500
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "grad_norm": 0.3860171437263489,
+      "learning_rate": 1.921104536489152e-05,
+      "loss": 0.0384,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "eval_accuracy": 0.9865853140014457,
+      "eval_f1": 0.5588440922861804,
+      "eval_loss": 0.040071167051792145,
+      "eval_precision": 0.7205528846153846,
+      "eval_recall": 0.45641416063951273,
+      "eval_runtime": 14.3408,
+      "eval_samples_per_second": 565.521,
+      "eval_steps_per_second": 2.231,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -191,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 135256930917768.0,
+  "total_flos": 180338255777124.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null