Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6e68f6389b28bb492a3c8963aad257d3b2851f2e050a7e18c979282d758963
+oid sha256:fee2b31ed9bcba208a9c79ee3b40aa491d32a034da09678bdbc1e4b013eb4493
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e81e499be935a461206ef2e4f6a898598a9816e04baec1746f18da9784e6ed9
+oid sha256:3339164a0051af4d619463786dbb2c5468ff9acb343d82a01f625a04dadb257c
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a1c62fc8af3072edea6b86ce97b4405d8951256dbb71b2c3f38f30844dfa9b
+oid sha256:3423752383b460d81921e040320adc06ebc531dda60b0a8779f70aa3d3547d66
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f686dba8f33d080722b3e02cf97d226b14ea8782c87e439a492bfe4952d0f7fe
+oid sha256:6f2dfb71ca7e21eba0bfcf4443439b5f61c88455cedeb3b4671c00055ea293f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08827067911624908,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-1000",
-  "epoch": 0.12328936012822093,
+  "best_metric": 0.06931016594171524,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-2000",
+  "epoch": 0.24657872025644187,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33,6 +33,32 @@
       "eval_samples_per_second": 309.906,
       "eval_steps_per_second": 19.372,
       "step": 1000
+    },
+    {
+      "epoch": 0.1849340401923314,
+      "grad_norm": 0.32189494371414185,
+      "learning_rate": 1.9630131919615338e-05,
+      "loss": 0.0857,
+      "step": 1500
+    },
+    {
+      "epoch": 0.24657872025644187,
+      "grad_norm": 0.3812316358089447,
+      "learning_rate": 1.9506842559487118e-05,
+      "loss": 0.0762,
+      "step": 2000
+    },
+    {
+      "epoch": 0.24657872025644187,
+      "eval_accuracy": 0.9814654995273908,
+      "eval_f1": 0.003808363165511463,
+      "eval_loss": 0.06931016594171524,
+      "eval_precision": 0.5,
+      "eval_recall": 0.0019114611208808012,
+      "eval_runtime": 26.3139,
+      "eval_samples_per_second": 308.24,
+      "eval_steps_per_second": 19.267,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -40,7 +66,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 22556469164112.0,
+  "total_flos": 45362736557640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null