Training in progress, step 195, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c8a9f00d293dd253e12e2902978c87a7b1732187c713f7dcc56dab3f31196
+oid sha256:1e414d493c7b174cfc9f15e8c8f498a62290ef39418bff71646044ba53766d2f
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4075100b03b5aee441579d318bde3f874036f3f3703250b3166ed2a132b016a0
+oid sha256:746384d1c74a736559be2e4296fa1ef73756a741e53afa3adbe66178b2abe282
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6b8abea532445f7a2b8197f8311b5a4d582f8239dfa11c211ca7d24d646650
+oid sha256:333f2a71b3e34575844f8fd8a45254433fb8a5c1731e62ba395b530a464ea2d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b289b438571df9d34409287e67864402aaad98d9ecdf87ccd44b9abb7f5b6982
+oid sha256:a35430a05f2b9748f37dd11667a782564c85a35d840d60cbaddfa2c905ab7c0a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09291521486643438,
+  "epoch": 0.0953603520997616,
   "eval_steps": 34,
-  "global_step": 190,
+  "global_step": 195,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1385,6 +1385,41 @@
       "learning_rate": 1.7026900316098215e-06,
       "loss": 0.9855,
       "step": 190
+    },
+    {
+      "epoch": 0.09340424231309982,
+      "grad_norm": 1.6108776330947876,
+      "learning_rate": 1.3799252646597426e-06,
+      "loss": 1.2474,
+      "step": 191
+    },
+    {
+      "epoch": 0.09389326975976527,
+      "grad_norm": 1.4905693531036377,
+      "learning_rate": 1.0908391628854041e-06,
+      "loss": 1.0982,
+      "step": 192
+    },
+    {
+      "epoch": 0.09438229720643071,
+      "grad_norm": 1.3788636922836304,
+      "learning_rate": 8.355304489257254e-07,
+      "loss": 1.0791,
+      "step": 193
+    },
+    {
+      "epoch": 0.09487132465309615,
+      "grad_norm": 1.8257007598876953,
+      "learning_rate": 6.140863104726391e-07,
+      "loss": 1.1666,
+      "step": 194
+    },
+    {
+      "epoch": 0.0953603520997616,
+      "grad_norm": 1.4958456754684448,
+      "learning_rate": 4.2658237049655323e-07,
+      "loss": 0.9653,
+      "step": 195
     }
   ],
   "logging_steps": 1,
@@ -1404,7 +1439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0968875503976448e+17,
+  "total_flos": 1.1257530122502144e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null