Training in progress, step 65, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c31cd0c71db08607f32996491b6438bb92e616866984646085e7d8af2abd1e1
+oid sha256:ee45b1cdd36db68e069c53deed747e5e3c9036e3d4c63ed4c4799a594eda0d55
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef66b44ddce7a3b65d72c15fad996a5a16867811836823139c8eb5e5ea890c7f
+oid sha256:d2668cd347986663a366567d5def91046d0f6ec5598af9e1847ba914d7328418
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2701e6433cbd351cde5d73f1b3cbd9cefb4bc8bfbd165ddcbca91b8495404c
+oid sha256:cd6c14874f8ead57c2fa8d8a60d83f94c33e974fd2075d5b17518426868d7142
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78248a64468e8e03af894427063f3f9a858b670b67d13949fb12f06211d294f4
+oid sha256:8977565a0b4b10da6945c32ba36caa3dc40fc9a4cdc4d66a537fb19aba96e0c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029341646799926645,
+  "epoch": 0.03178678403325386,
   "eval_steps": 34,
-  "global_step": 60,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -443,6 +443,41 @@
       "learning_rate": 0.00018502171357296144,
       "loss": 1.1566,
       "step": 60
+    },
+    {
+      "epoch": 0.02983067424659209,
+      "grad_norm": 1.1395761966705322,
+      "learning_rate": 0.00018403440716378928,
+      "loss": 0.9825,
+      "step": 61
+    },
+    {
+      "epoch": 0.030319701693257536,
+      "grad_norm": 1.1984392404556274,
+      "learning_rate": 0.00018301840308155507,
+      "loss": 1.1295,
+      "step": 62
+    },
+    {
+      "epoch": 0.03080872913992298,
+      "grad_norm": 1.3706929683685303,
+      "learning_rate": 0.00018197404829072215,
+      "loss": 1.3507,
+      "step": 63
+    },
+    {
+      "epoch": 0.03129775658658842,
+      "grad_norm": 1.0434547662734985,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.9119,
+      "step": 64
+    },
+    {
+      "epoch": 0.03178678403325386,
+      "grad_norm": 1.2470561265945435,
+      "learning_rate": 0.000179801722728024,
+      "loss": 1.1485,
+      "step": 65
     }
   ],
   "logging_steps": 1,
@@ -462,7 +497,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6633725173301248e+17,
+  "total_flos": 2.885320227107635e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null