Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd55083b4091559ebf65192c407ebceaf4d21bf739682d6114ccc3dbf70a00a3
+oid sha256:103d975bd8ddb9cf239064412e2cc76404ce1f648701fdb8ec7912d9266b990e
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271672373ed49cdd7feb8ecbcc127f67a549a72a4528028c2ad80ee8ed1352d0
+oid sha256:b4869263614539762c094ca057e0e9f69d99ec276193337cc0e640386ce46f24
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea0571e03c42072c2619a6841806791c3454e943bf747e8a4e1158abf717848
+oid sha256:bc9120ba08562e298368a02d3bb5097b22537f427b96b3a071e6c5a8b4dba68e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005195633022337012,
+  "epoch": 0.006061571859393182,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 2.79,
       "eval_steps_per_second": 1.395,
       "step": 54
+    },
+    {
+      "epoch": 0.005484279301355735,
+      "grad_norm": 21.539554595947266,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 6.7601,
+      "step": 57
+    },
+    {
+      "epoch": 0.0057729255803744585,
+      "grad_norm": 20.63874626159668,
+      "learning_rate": 0.0001,
+      "loss": 6.994,
+      "step": 60
+    },
+    {
+      "epoch": 0.006061571859393182,
+      "grad_norm": 16.417226791381836,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 5.5389,
+      "step": 63
+    },
+    {
+      "epoch": 0.006061571859393182,
+      "eval_loss": 0.17797139286994934,
+      "eval_runtime": 9174.8,
+      "eval_samples_per_second": 3.816,
+      "eval_steps_per_second": 1.908,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.839944410337116e+17,
+  "total_flos": 3.3132684787266355e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null