Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2d0b116d8dee51ac7fb9419676c1c9cd9b91ebf2359117b4656e2ec557209f
+oid sha256:2bf890426e01c124441b5df69ee0d04c23c08bbb497f9dade4f9a2bfd07b060d
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c77e205a0b6da0ff6a113f4c1f94cb57eb5574483287819c4dcd1add6eadd42
+oid sha256:408a9970359416e60d28fafed8175037be96e51a0bad1d344baeb1cde658a113
 size 61232293

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62db0ba9861d9ab63380744e79a287faa461a1bf55700140a411fe1e976f1cd
+oid sha256:b429070a564985551cfca2e541b4c4fca20d998c67cc7cb6e2b59f638df425a3
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a724bf6710d3e8822e4a6d5d7af6c6dd7fc3675acae52e834bb4ca48401a5ba
+oid sha256:5cc298ce4e3144f9d66357bff950d24254c8f3ffbf9259e5a11fe99f4ee6dbf3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4,
+  "epoch": 2.56,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -323,6 +323,27 @@
       "learning_rate": 1.946420046645574e-05,
       "loss": 0.339,
       "step": 4500
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 0.24763137102127075,
+      "learning_rate": 1.625335454908574e-05,
+      "loss": 0.3467,
+      "step": 4600
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 0.24259154498577118,
+      "learning_rate": 1.3308374443593851e-05,
+      "loss": 0.34,
+      "step": 4700
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.4125021696090698,
+      "learning_rate": 1.0638609414329625e-05,
+      "loss": 0.2949,
+      "step": 4800
     }
   ],
   "logging_steps": 100,
@@ -342,7 +363,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.60361961409536e+17,
+  "total_flos": 4.913375708058624e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null