Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e58f190f0a19b574e782cfd6a63dd8082c3b916a84885dca77b6d848f9eae51
+oid sha256:c58fbf22821d5ddd89f8f0371fcd6e275cc4303da8e85f66fe324e9e9e77b457
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b50aed80f0fe7ea4d4b29241caae2998402dec7a69c855ef11be8a40b1dd88c
+oid sha256:2ce55eb5c7af6e8080edd51421f0304e64814854d1d14a3973453afd3bc853fc
 size 15611732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb7b88fde3d49d1800cfb6a606d2abc469146233dd09628bf7b85f2e974e8ea
+oid sha256:03875118d09855e6a66800decf56d9db8fcb2516925d3d7ed640f2fb0d895a13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6336d9295f9054a1bd08411a37c67a0588c56d0f45f7492296231c3ba16a6d33
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9942711648631444,
+  "epoch": 3.3948652662847443,
   "eval_steps": 32,
-  "global_step": 441,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,64 @@
       "learning_rate": 3.654162132698918e-06,
       "loss": 1.8139,
       "step": 440
+    },
+    {
+      "epoch": 3.0417992785911308,
+      "eval_loss": 2.039308786392212,
+      "eval_runtime": 14.3442,
+      "eval_samples_per_second": 17.359,
+      "eval_steps_per_second": 17.359,
+      "step": 448
+    },
+    {
+      "epoch": 3.0553787396562697,
+      "grad_norm": 0.9411285519599915,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 2.0269,
+      "step": 450
+    },
+    {
+      "epoch": 3.123276044981965,
+      "grad_norm": 0.9969708323478699,
+      "learning_rate": 1.6352568480485276e-06,
+      "loss": 1.8136,
+      "step": 460
+    },
+    {
+      "epoch": 3.19117335030766,
+      "grad_norm": 1.0875673294067383,
+      "learning_rate": 9.220421504467281e-07,
+      "loss": 1.8409,
+      "step": 470
+    },
+    {
+      "epoch": 3.2590706556333546,
+      "grad_norm": 0.9148634076118469,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 1.7138,
+      "step": 480
+    },
+    {
+      "epoch": 3.2590706556333546,
+      "eval_loss": 2.039867877960205,
+      "eval_runtime": 14.3381,
+      "eval_samples_per_second": 17.366,
+      "eval_steps_per_second": 17.366,
+      "step": 480
+    },
+    {
+      "epoch": 3.3269679609590495,
+      "grad_norm": 0.9893661737442017,
+      "learning_rate": 1.0273036248318324e-07,
+      "loss": 1.8856,
+      "step": 490
+    },
+    {
+      "epoch": 3.3948652662847443,
+      "grad_norm": 1.122750163078308,
+      "learning_rate": 0.0,
+      "loss": 1.8205,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -441,12 +499,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.60005442961408e+16,
+  "total_flos": 6.349892226121728e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null