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:df0e540779c16a9c9b8e0788020851b763c6ccde82f230184c6995b221b6b636
+oid sha256:e064234ed8d8e7184d4b454bb78d8b1d5d07ee735a5256cb86795b2c612e7015
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d03b8186e15e8d8547427ceb0c67f3e312c09939c3148d3ddf48c2bbfe1bde0
+oid sha256:44fd80894608e4528eeb08cb6a85c6cdfc4c686ed4ce631a98cc1e97b5703e70
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c51931e2d3751996d51194bb17f4339acd99c19e556e5384d965eaa00841d426
+oid sha256:cb26bc8fbad6e5e2338653481322bdb8fe110ea54a4af342300b81534d783034
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.306930693069307,
+  "epoch": 1.4144271570014144,
   "eval_steps": 42,
-  "global_step": 462,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1181,6 +1181,90 @@
       "eval_samples_per_second": 92.509,
       "eval_steps_per_second": 11.641,
       "step": 462
+    },
+    {
+      "epoch": 1.3154172560113153,
+      "grad_norm": 0.09070340543985367,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 11.8145,
+      "step": 465
+    },
+    {
+      "epoch": 1.3239038189533239,
+      "grad_norm": 0.0519736111164093,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 11.8139,
+      "step": 468
+    },
+    {
+      "epoch": 1.3323903818953324,
+      "grad_norm": 0.09727457165718079,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 11.8145,
+      "step": 471
+    },
+    {
+      "epoch": 1.340876944837341,
+      "grad_norm": 0.0795770063996315,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 11.8154,
+      "step": 474
+    },
+    {
+      "epoch": 1.3493635077793493,
+      "grad_norm": 0.09474173188209534,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 11.8169,
+      "step": 477
+    },
+    {
+      "epoch": 1.3578500707213579,
+      "grad_norm": 0.13217829167842865,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 11.8165,
+      "step": 480
+    },
+    {
+      "epoch": 1.3663366336633662,
+      "grad_norm": 0.11465727537870407,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 11.8173,
+      "step": 483
+    },
+    {
+      "epoch": 1.3748231966053748,
+      "grad_norm": 0.12922833859920502,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 11.8154,
+      "step": 486
+    },
+    {
+      "epoch": 1.3833097595473833,
+      "grad_norm": 0.05712132155895233,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 11.814,
+      "step": 489
+    },
+    {
+      "epoch": 1.391796322489392,
+      "grad_norm": 0.09231238812208176,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 11.8135,
+      "step": 492
+    },
+    {
+      "epoch": 1.4002828854314002,
+      "grad_norm": 0.08613143861293793,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 11.819,
+      "step": 495
+    },
+    {
+      "epoch": 1.4087694483734088,
+      "grad_norm": 0.11459596455097198,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 11.8119,
+      "step": 498
     }
   ],
   "logging_steps": 3,
@@ -1195,12 +1279,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2832537845760.0,
+  "total_flos": 3067553218560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null