Training in progress, step 5860, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a05d66290a553ce7e5848692f87b4d47dd70832cd730d3e060d68efb842c89b
+oid sha256:4ad91b707f2a94834727ceb71bd3a19c5ea0a8aadc4a8033e002e78433d6c063
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c55dfcbb3adece00c0495fe03185267c02807bfaa50cb1106c5f7e6137980a8d
+oid sha256:a4186aa74ed71d9daa7716797983f0781cfad89f6396a0de90be681c2d6683fd
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37eee1f275542e53d152c87d42b36d0933fa3b25d32e8265c1afb8163e08bdb
+oid sha256:d5f036b2ad95eeaf8bb887f1ebb8ed1a70d995e8fabc2814429a917b7a12f336
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ff425dd13fc2cddef013a46a6108a94fb4fb857872d9633c68069377e39e8a
+oid sha256:01e4cd9ba66911efce13a1a68979a2ddd0857e7ad459e78d4708175159b3713d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4672,
+  "epoch": 0.4688,
   "eval_steps": 500,
-  "global_step": 5840,
+  "global_step": 5860,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2051,6 +2051,13 @@
       "learning_rate": 2.4916033320336263e-05,
       "loss": 3.3979,
       "step": 5840
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 38.79692077636719,
+      "learning_rate": 2.487952958026282e-05,
+      "loss": 3.5581,
+      "step": 5860
     }
   ],
   "logging_steps": 20,
@@ -2058,7 +2065,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3829463670063104e+16,
+  "total_flos": 1.3871586461810688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null