Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:addd3dd183f9c0fb2f62b3ff32005cb369d656dac8b5af5b044a7fce8f21a53f
+oid sha256:60d80833c27cee255799a3bfbda672d7114700cf2a4ca494036a68c03d65f71a
 size 41977360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d1503ba5046d07c21f93b4575d1b083dbc181a049aa2f247b683f047bd09e7a
+oid sha256:ff91055c1d115ea31ce5e367e6b60d51fcc58fd188c250c59669def6ed92fdf7
 size 84100858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec629a82fc6a705e145bf37ce628a81a3dd7365c4e459a322e17229e377107e
+oid sha256:fb3a36c4212e103c674b3f32de687c7d3da32dcbbb2bf6a69db439d5bbf72e15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718aa1d234ba2748901ce4d93b9b9f5911dad7fc2a60aef63bb9baa629751755
+oid sha256:33c8659615615a93a70aac05e323342ecdd678d5af9aa183dc0739a5db1bba97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7326057553291321,
-  "best_model_checkpoint": "./results/phi2-mentalchat16k/checkpoint-1800",
-  "epoch": 2.6925953627524306,
+  "best_metric": 0.7297702431678772,
+  "best_model_checkpoint": "./results/phi2-mentalchat16k/checkpoint-2000",
+  "epoch": 2.9917726252804786,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -410,6 +410,50 @@
       "eval_samples_per_second": 12.168,
       "eval_steps_per_second": 3.042,
       "step": 1800
+    },
+    {
+      "epoch": 2.767389678384443,
+      "grad_norm": 0.30385613441467285,
+      "learning_rate": 4.569041677996858e-05,
+      "loss": 0.7131,
+      "step": 1850
+    },
+    {
+      "epoch": 2.842183994016455,
+      "grad_norm": 0.344064325094223,
+      "learning_rate": 4.0702796629261964e-05,
+      "loss": 0.6994,
+      "step": 1900
+    },
+    {
+      "epoch": 2.842183994016455,
+      "eval_loss": 0.7319425344467163,
+      "eval_runtime": 38.8045,
+      "eval_samples_per_second": 12.164,
+      "eval_steps_per_second": 3.041,
+      "step": 1900
+    },
+    {
+      "epoch": 2.9169783096484667,
+      "grad_norm": 0.3289170563220978,
+      "learning_rate": 3.593305083535229e-05,
+      "loss": 0.7064,
+      "step": 1950
+    },
+    {
+      "epoch": 2.9917726252804786,
+      "grad_norm": 0.32823771238327026,
+      "learning_rate": 3.139870476601171e-05,
+      "loss": 0.6995,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9917726252804786,
+      "eval_loss": 0.7297702431678772,
+      "eval_runtime": 38.8084,
+      "eval_samples_per_second": 12.162,
+      "eval_steps_per_second": 3.041,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -438,7 +482,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.097538439389696e+17,
+  "total_flos": 1.219471678929408e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null