Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145ec1241d02e5ad7c0c5963a613fa26a9f50d41b13b54cf4e31c3a3fd967930
+oid sha256:8d81ad20d6a6c4fe379bacb4c8d4a808360e99a6c66a1dc7f53e2b6139b8d2ab
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe898fa16b6709fa0c7a7e7fc599faecd85a247cbb9d57e586320b5d424d3ee
+oid sha256:fa96847b6f54bdff6418d7a390c990b585b9a48dc362b81f36244df43abcdc59
 size 99241221

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb3d01905ba3db4c3065c85697c168d9e32937350baf828e8a0685920ef9c35
+oid sha256:852572ec0a5139abf7706cbd44b245b4d47b4ea48568f8acba9d5eb3a1ceceea
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4f7c0edc6c0f32a409cb7bdaa5a2587da793fda2041cd5c6f57585074491a5
+oid sha256:7bc95c37cee1aebca09c18497d4c5a88aa069c3ace91dfd78d825324dd82fe2f
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7146047342563644,
+  "epoch": 0.9528063123418192,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,76 @@
       "learning_rate": 1.9741289240311755e-05,
       "loss": 1.0303,
       "step": 300
+    },
+    {
+      "epoch": 0.7384248920649099,
+      "grad_norm": 0.10671300441026688,
+      "learning_rate": 1.675485482450499e-05,
+      "loss": 0.9908,
+      "step": 310
+    },
+    {
+      "epoch": 0.7622450498734554,
+      "grad_norm": 0.11709579080343246,
+      "learning_rate": 1.3967377400236515e-05,
+      "loss": 0.9845,
+      "step": 320
+    },
+    {
+      "epoch": 0.7860652076820009,
+      "grad_norm": 0.1134701669216156,
+      "learning_rate": 1.1395538745233131e-05,
+      "loss": 0.9991,
+      "step": 330
+    },
+    {
+      "epoch": 0.8098853654905463,
+      "grad_norm": 0.11429400742053986,
+      "learning_rate": 9.054730137794886e-06,
+      "loss": 0.9797,
+      "step": 340
+    },
+    {
+      "epoch": 0.8337055232990919,
+      "grad_norm": 0.10862188786268234,
+      "learning_rate": 6.958960247032514e-06,
+      "loss": 1.0064,
+      "step": 350
+    },
+    {
+      "epoch": 0.8575256811076374,
+      "grad_norm": 0.11576621979475021,
+      "learning_rate": 5.120771297388788e-06,
+      "loss": 0.9775,
+      "step": 360
+    },
+    {
+      "epoch": 0.8813458389161828,
+      "grad_norm": 0.11541400104761124,
+      "learning_rate": 3.551164009160429e-06,
+      "loss": 1.0093,
+      "step": 370
+    },
+    {
+      "epoch": 0.9051659967247283,
+      "grad_norm": 0.11458367854356766,
+      "learning_rate": 2.2595317642176038e-06,
+      "loss": 0.9997,
+      "step": 380
+    },
+    {
+      "epoch": 0.9289861545332738,
+      "grad_norm": 0.10918566584587097,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 1.0158,
+      "step": 390
+    },
+    {
+      "epoch": 0.9528063123418192,
+      "grad_norm": 0.10979858785867691,
+      "learning_rate": 5.394019045729448e-07,
+      "loss": 1.016,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -236,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.536869980012544e+17,
+  "total_flos": 3.382493306683392e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null