Training in progress, step 1260, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4989f417f8af82aa5afd207ae1fd0befd4ae0dcdae5fdc748922cf8c530c7b97
+oid sha256:c6083d1472c6086310a747e55e3c219fd918f02590a78870e05c736cd45dbab7
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90bdbd8e9dba7260bfc44bfde0f43461ac775cf18170c0d1133ac88052f92e9
+oid sha256:381cacd46391e3f555d4e12d200333abae360d4bdef760f00cdb360a10db7906
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c48f3975b279f6efbdc2f7b3c963816b9fdd9626320f2bf9378c327c8e958c2
+oid sha256:fca463d79bf4813a9d6530d90204c4d73a7f2230eb606726b7385a62bc76294f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e5e3b3844635e28b48697b64695f6ae48a5abd3795536da24be2a1a747340e
+oid sha256:53516e58e5e8a23d810a2b934d82c13e25c739e42ae684ed7376620ab310e104
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.44364937388193204,
+  "epoch": 0.45080500894454384,
   "eval_steps": 500,
-  "global_step": 1240,
+  "global_step": 1260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -999,14 +999,30 @@
       "loss": 0.4028,
       "num_input_tokens_seen": 835022,
       "step": 1240
+    },
+    {
+      "epoch": 0.4472271914132379,
+      "grad_norm": 0.3959554135799408,
+      "learning_rate": 0.00011055456171735241,
+      "loss": 0.402,
+      "num_input_tokens_seen": 841676,
+      "step": 1250
+    },
+    {
+      "epoch": 0.45080500894454384,
+      "grad_norm": 0.4300963580608368,
+      "learning_rate": 0.00010983899821109125,
+      "loss": 0.4169,
+      "num_input_tokens_seen": 848238,
+      "step": 1260
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 835022,
+  "num_input_tokens_seen": 848238,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.8776695989989376e+16,
+  "total_flos": 1.9073877159112704e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null