Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196dba7b25c0a4c68d7a023c577d7e08c52e76d0408d8bc30c27ca039dbe9a92
+oid sha256:a8397db461e41b61712c457016b351f7f6dc554101c570e4a6daff1bf4160f00
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c232c70d72ff63954a64510b19045d431ee3cf56e8201d12f051c97760d891
+oid sha256:d3874c420fe9a2f73893b67a2dea07956637705f44be263169a4a4590aba7ffa
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c9aaea8c26c5e4232cacfa8dd7d43278b636bf8b016e620006628dcd43298e
+oid sha256:529b103d77a0239f5cc9fdc12d2f27ed56abb5aedd679ea0594afff05c3a18f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6560861164780567,
+  "epoch": 1.9321004692243997,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,41 @@
       "learning_rate": 8.45734287123433e-05,
       "loss": 0.279,
       "step": 3000
+    },
+    {
+      "epoch": 1.7112889870273253,
+      "grad_norm": 1.4846047163009644,
+      "learning_rate": 8.315557797577755e-05,
+      "loss": 0.2788,
+      "step": 3100
+    },
+    {
+      "epoch": 1.766491857576594,
+      "grad_norm": 1.2695362567901611,
+      "learning_rate": 8.168845595033201e-05,
+      "loss": 0.2764,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8216947281258626,
+      "grad_norm": 1.3499970436096191,
+      "learning_rate": 8.017424287226106e-05,
+      "loss": 0.2576,
+      "step": 3300
+    },
+    {
+      "epoch": 1.876897598675131,
+      "grad_norm": 1.3490862846374512,
+      "learning_rate": 7.861518895810596e-05,
+      "loss": 0.2529,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9321004692243997,
+      "grad_norm": 1.3637194633483887,
+      "learning_rate": 7.701361106073043e-05,
+      "loss": 0.247,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
@@ -236,7 +271,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5884360163671409e+18,
+  "total_flos": 1.8555493591209738e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null