Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8d0c376cd6589d5b11a8f79cee03f674e63829a2290155bc1ede6fbec8d765
+oid sha256:f4e73c64b7e1b7302c8ec1273548c58e5bbee4e530009cf776fea0d69bc4c65e
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8b70b8a342812192d5c3b7c9978254f5ffabf514448203b80e1686d5fdc13b
+oid sha256:b4ceb907403d64367ee6301a6997f012a86962632a165977d5c5fbde39c561f5
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31defcd29d743f2c19de79a505fa9f79f745600b1ccfe976120a3783f910551
+oid sha256:ab47a00c1225fc112a1f9801ef10e677ce5b1363a2b223b4f9b1cd35741d4304
 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": 2.2899628252788102,
+  "epoch": 2.4783147459727384,
   "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": 191.152,
       "eval_steps_per_second": 24.175,
       "step": 462
+    },
+    {
+      "epoch": 2.3048327137546467,
+      "grad_norm": 0.04429741948843002,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 11.539,
+      "step": 465
+    },
+    {
+      "epoch": 2.319702602230483,
+      "grad_norm": 0.04356589540839195,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 12.4901,
+      "step": 468
+    },
+    {
+      "epoch": 2.3345724907063197,
+      "grad_norm": 0.04233817383646965,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 11.4907,
+      "step": 471
+    },
+    {
+      "epoch": 2.349442379182156,
+      "grad_norm": 0.0563838854432106,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 12.2563,
+      "step": 474
+    },
+    {
+      "epoch": 2.3643122676579926,
+      "grad_norm": 0.05499923229217529,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 11.8555,
+      "step": 477
+    },
+    {
+      "epoch": 2.379182156133829,
+      "grad_norm": 0.044174499809741974,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 11.8189,
+      "step": 480
+    },
+    {
+      "epoch": 2.3940520446096656,
+      "grad_norm": 0.05212130397558212,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 12.3588,
+      "step": 483
+    },
+    {
+      "epoch": 2.4089219330855016,
+      "grad_norm": 0.05286373570561409,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 11.2934,
+      "step": 486
+    },
+    {
+      "epoch": 2.423791821561338,
+      "grad_norm": 0.04788150638341904,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 11.9583,
+      "step": 489
+    },
+    {
+      "epoch": 2.4386617100371746,
+      "grad_norm": 0.045176565647125244,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 11.6715,
+      "step": 492
+    },
+    {
+      "epoch": 2.453531598513011,
+      "grad_norm": 0.038598958402872086,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 12.1975,
+      "step": 495
+    },
+    {
+      "epoch": 2.4684014869888475,
+      "grad_norm": 0.04955305531620979,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 12.0849,
+      "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": 2227222609920.0,
+  "total_flos": 2410414080000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null