Training in progress, step 2560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f909b9fc067fab552364fb1de3f6e34dba04079b0b596520d0be14f0aea8874e
+oid sha256:99dae515fa23ad18fb5d804785a042044e88c12f664e33ed30799d995c9c0e2e
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef69499f4fb45b90f7ff201ee61e0a27e72a0d41576fc428f11b0b3210d7edf5
+oid sha256:3155003d2ea5cc790dee6fd194de467b7e81fb05ef1aa596c5a462da8a4bdbca
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7cbc060d6be543690e84079f5a0f9038405e71cf9fd3cec769843460f91c90a
+oid sha256:49541cd98b68651da591e11bb8ee1a4d2340295f0f1855a2571126b55e63a83c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4fa0a4cb65f7c841c287b50ca6fd51005d2271eb35681bcb90491c2c7baba1
+oid sha256:9b81f5081497282279ac6e33fa4ff19b1cd4357d0b584f715bb3836bdeb5ad85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9087656529516994,
+  "epoch": 0.9159212880143113,
   "eval_steps": 500,
-  "global_step": 2540,
+  "global_step": 2560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2039,14 +2039,30 @@
       "loss": 0.3874,
       "num_input_tokens_seen": 1720278,
       "step": 2540
+    },
+    {
+      "epoch": 0.9123434704830053,
+      "grad_norm": 0.23165664076805115,
+      "learning_rate": 1.7531305903398927e-05,
+      "loss": 0.4029,
+      "num_input_tokens_seen": 1729448,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9159212880143113,
+      "grad_norm": 0.41043820977211,
+      "learning_rate": 1.6815742397137747e-05,
+      "loss": 0.3661,
+      "num_input_tokens_seen": 1735842,
+      "step": 2560
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1720278,
+  "num_input_tokens_seen": 1735842,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.868297724403302e+16,
+  "total_flos": 3.903295664144794e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null