Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d80833c27cee255799a3bfbda672d7114700cf2a4ca494036a68c03d65f71a
+oid sha256:01d3c25fe15711de727142e72fcf18b1562f70ba4803b2ccb81aa11f5be7f0b6
 size 41977360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff91055c1d115ea31ce5e367e6b60d51fcc58fd188c250c59669def6ed92fdf7
+oid sha256:1d9ffc1c556923224e5accb81e675f29bc7461c6ef6704644fe820ff7da2d25a
 size 84100858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3a36c4212e103c674b3f32de687c7d3da32dcbbb2bf6a69db439d5bbf72e15
+oid sha256:4a00c887d1f42518acb45d72e988d69cde39eeaca6011972cd0e04b64ce69f72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c8659615615a93a70aac05e323342ecdd678d5af9aa183dc0739a5db1bba97
+oid sha256:d6dee65d23c30e8b90e557d338adbbb6ac407846ac98bf5125837e5e2dee92dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7297702431678772,
   "best_model_checkpoint": "./results/phi2-mentalchat16k/checkpoint-2000",
-  "epoch": 2.9917726252804786,
+  "epoch": 3.2909498878085266,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -454,6 +454,50 @@
       "eval_samples_per_second": 12.162,
       "eval_steps_per_second": 3.041,
       "step": 2000
+    },
+    {
+      "epoch": 3.0665669409124905,
+      "grad_norm": 0.31735172867774963,
+      "learning_rate": 2.7116418865193638e-05,
+      "loss": 0.6928,
+      "step": 2050
+    },
+    {
+      "epoch": 3.141361256544503,
+      "grad_norm": 0.36334428191185,
+      "learning_rate": 2.310192743794496e-05,
+      "loss": 0.6887,
+      "step": 2100
+    },
+    {
+      "epoch": 3.141361256544503,
+      "eval_loss": 0.7313625812530518,
+      "eval_runtime": 38.8213,
+      "eval_samples_per_second": 12.158,
+      "eval_steps_per_second": 3.04,
+      "step": 2100
+    },
+    {
+      "epoch": 3.2161555721765147,
+      "grad_norm": 0.3707718849182129,
+      "learning_rate": 1.9369980838209156e-05,
+      "loss": 0.6852,
+      "step": 2150
+    },
+    {
+      "epoch": 3.2909498878085266,
+      "grad_norm": 0.28901323676109314,
+      "learning_rate": 1.5934291271938596e-05,
+      "loss": 0.6712,
+      "step": 2200
+    },
+    {
+      "epoch": 3.2909498878085266,
+      "eval_loss": 0.7308326363563538,
+      "eval_runtime": 154.853,
+      "eval_samples_per_second": 3.048,
+      "eval_steps_per_second": 0.762,
+      "step": 2200
     }
   ],
   "logging_steps": 50,
@@ -468,7 +512,7 @@
         "early_stopping_threshold": 0.001
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -482,7 +526,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.219471678929408e+17,
+  "total_flos": 1.341425978522112e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null