Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e4734cbbe72f9e9bae98c394fc3d207a4fd1048611a77cfce5abf5553b06db
+oid sha256:b54ff74fab801349c682ac224c064c645c63499b7e32b1f9222373896cde4c1b
 size 50366280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22baff8ed7ca9cbeae04980dd00f21d06b23696536eb466e87398ce92d167ee
+oid sha256:f9fd949bbafd17e05a2918de74575e02e27d7c3e3224201eab8b7625a682939e
 size 51423589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81e990436bcd40e045db972dfd5d57a4c9c7a635f60b749fe3d5de220b821dd
+oid sha256:645b36e2bd97e938659ebdc42bca7dc703e4f3ef6ec907d98d2961f37b412eaa
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd65659e9d4065cb7ced7e5dc6a84ce910bd21d03812af593d819f8f600f4322
+oid sha256:57f5bbb5b4ba44d34a455960920ef8eaf75574205648b376b9b795cb9f0b32ae
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 25,
-  "best_metric": 1.4348562955856323,
-  "best_model_checkpoint": "./outputs/phi3-clause-lora-pushcheck/checkpoint-25",
-  "epoch": 0.13360053440213762,
+  "best_global_step": 30,
+  "best_metric": 1.3372900485992432,
+  "best_model_checkpoint": "./outputs/phi3-clause-lora-pushcheck/checkpoint-30",
+  "epoch": 0.16032064128256512,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -269,6 +269,67 @@
       "eval_samples_per_second": 6.603,
       "eval_steps_per_second": 0.825,
       "step": 25
+    },
+    {
+      "entropy": 0.5040823891758919,
+      "epoch": 0.13894455577822312,
+      "grad_norm": 2.546875,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 0.4367317259311676,
+      "mean_token_accuracy": 0.8917413204908371,
+      "num_tokens": 54550.0,
+      "step": 26
+    },
+    {
+      "entropy": 0.453246645629406,
+      "epoch": 0.14428857715430862,
+      "grad_norm": 2.015625,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 0.5294952392578125,
+      "mean_token_accuracy": 0.859589196741581,
+      "num_tokens": 56869.0,
+      "step": 27
+    },
+    {
+      "entropy": 0.5663181617856026,
+      "epoch": 0.14963259853039412,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 0.5441249012947083,
+      "mean_token_accuracy": 0.8913109004497528,
+      "num_tokens": 58736.0,
+      "step": 28
+    },
+    {
+      "entropy": 0.533376008272171,
+      "epoch": 0.15497661990647962,
+      "grad_norm": 2.4375,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 0.44721558690071106,
+      "mean_token_accuracy": 0.8709967359900475,
+      "num_tokens": 60653.0,
+      "step": 29
+    },
+    {
+      "entropy": 0.4581379536539316,
+      "epoch": 0.16032064128256512,
+      "grad_norm": 1.8515625,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 0.33484047651290894,
+      "mean_token_accuracy": 0.9065552577376366,
+      "num_tokens": 62630.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "eval_entropy": 0.7658527252701043,
+      "eval_loss": 1.3372900485992432,
+      "eval_mean_token_accuracy": 0.7872280500366189,
+      "eval_num_tokens": 62630.0,
+      "eval_runtime": 428.8036,
+      "eval_samples_per_second": 6.604,
+      "eval_steps_per_second": 0.826,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -283,12 +344,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1509696529403904.0,
+  "total_flos": 1803774565859328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null