Training in progress, step 102, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b03ad288e9be268229d4c9b8350b53a0832256682c787acaf0d0153bef542a
+oid sha256:fbbf1eca6e8a077aad44f0eea548900906563fba91ae629ff999cfbb84d12183
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b33cb1418e7c3b78e10095e9e9845586d0cec7958bc2a6c4d162562a3e217d0
+oid sha256:01c50059bf06051c0e59a9446ee43b11917461b9915373cdac8ef7e15a1c3f0d
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f03bc1423c34b94dc31b9df725b107e8c7094161c242c029296a4dd797e9612
+oid sha256:455d3b76f5d818e204f559cce8a72f513e0e5623eb82e10af57277665f41a7cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57465ffa9dc280f2ea6034fe61064b0208bf36c7b5f569218c0e1296778ee099
+oid sha256:baea37709b071cdabc5712824dc3f783ecd30d18a1e0d85c4d56cfebfa22b7e0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019334660221779928,
+  "epoch": 0.02900199033266989,
   "eval_steps": 34,
-  "global_step": 68,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -185,6 +185,98 @@
       "eval_samples_per_second": 35.237,
       "eval_steps_per_second": 4.408,
       "step": 68
+    },
+    {
+      "epoch": 0.019618993460335514,
+      "grad_norm": 0.16994404792785645,
+      "learning_rate": 4.7229269307953235e-05,
+      "loss": 0.9841,
+      "step": 69
+    },
+    {
+      "epoch": 0.020471993176002276,
+      "grad_norm": 0.17181497812271118,
+      "learning_rate": 4.694636022946012e-05,
+      "loss": 0.9944,
+      "step": 72
+    },
+    {
+      "epoch": 0.021324992891669035,
+      "grad_norm": 0.21411621570587158,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 1.0013,
+      "step": 75
+    },
+    {
+      "epoch": 0.022177992607335797,
+      "grad_norm": 0.19594340026378632,
+      "learning_rate": 4.6342266598556814e-05,
+      "loss": 0.9969,
+      "step": 78
+    },
+    {
+      "epoch": 0.02303099232300256,
+      "grad_norm": 0.2057276964187622,
+      "learning_rate": 4.6021434819815555e-05,
+      "loss": 0.9808,
+      "step": 81
+    },
+    {
+      "epoch": 0.02388399203866932,
+      "grad_norm": 0.21778051555156708,
+      "learning_rate": 4.568832711511125e-05,
+      "loss": 0.9456,
+      "step": 84
+    },
+    {
+      "epoch": 0.024736991754336083,
+      "grad_norm": 0.21349306404590607,
+      "learning_rate": 4.534313800996299e-05,
+      "loss": 0.953,
+      "step": 87
+    },
+    {
+      "epoch": 0.02558999147000284,
+      "grad_norm": 0.21818219125270844,
+      "learning_rate": 4.498606908508754e-05,
+      "loss": 0.9133,
+      "step": 90
+    },
+    {
+      "epoch": 0.026442991185669604,
+      "grad_norm": 0.2510223388671875,
+      "learning_rate": 4.46173288586818e-05,
+      "loss": 0.9125,
+      "step": 93
+    },
+    {
+      "epoch": 0.027295990901336366,
+      "grad_norm": 0.24031595885753632,
+      "learning_rate": 4.4237132664654154e-05,
+      "loss": 0.8784,
+      "step": 96
+    },
+    {
+      "epoch": 0.028148990617003128,
+      "grad_norm": 0.2543729543685913,
+      "learning_rate": 4.384570252687542e-05,
+      "loss": 0.8984,
+      "step": 99
+    },
+    {
+      "epoch": 0.02900199033266989,
+      "grad_norm": 0.27020716667175293,
+      "learning_rate": 4.344326702952326e-05,
+      "loss": 0.8719,
+      "step": 102
+    },
+    {
+      "epoch": 0.02900199033266989,
+      "eval_loss": 0.8574855923652649,
+      "eval_runtime": 168.0651,
+      "eval_samples_per_second": 35.248,
+      "eval_steps_per_second": 4.409,
+      "step": 102
     }
   ],
   "logging_steps": 3,
@@ -204,7 +296,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1776001197408256e+16,
+  "total_flos": 3.2664001796112384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null