Training in progress, step 225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:777110b9885805d05b54b83c0078c17d2c3f56f401f8d414b249c230762358bb
+oid sha256:79cc0f0d4da8dc41e74774dbe3bfeab0c15fec40247cbabd3e59c325c765c7a5
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd299fcb2d78913771ba672fc903a33ad3ee1376e8feba78832d4267d4cbedd
+oid sha256:35fc8e78c68beb9d55d5f8c9737abc89321e71f3ac3fe3bd94c06fd11b5eae05
 size 281829907

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c4ae54d27cbe43b4c5fa652d71ae90547dadc724f75624e3d3c44e35870949
+oid sha256:606420a76df9020f0375458d71a968da3eb2527da0a6f0d6f52ba573a3d73d92
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74ad02c6868c7927ba45f4229ae211aa9e779d68ecfa33c6fcfa330a9d67a76
+oid sha256:92ef75ec69ab83d00b269577ccea9ea264ded16c482996c8d7d7cfc5af58b9a5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6666666666666665,
+  "epoch": 3.0,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -304,6 +304,41 @@
       "eval_samples_per_second": 0.378,
       "eval_steps_per_second": 0.378,
       "step": 200
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.13668841123580933,
+      "learning_rate": 1.3215442672249972e-05,
+      "loss": 0.4098,
+      "step": 205
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.11291203647851944,
+      "learning_rate": 7.70025020008347e-06,
+      "loss": 0.3316,
+      "step": 210
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.1049598902463913,
+      "learning_rate": 3.64949617782967e-06,
+      "loss": 0.3406,
+      "step": 215
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.10330229252576828,
+      "learning_rate": 1.0876630077453487e-06,
+      "loss": 0.3846,
+      "step": 220
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.11973880231380463,
+      "learning_rate": 3.023418496261865e-08,
+      "loss": 0.3517,
+      "step": 225
     }
   ],
   "logging_steps": 5,
@@ -318,12 +353,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6611475205324800.0,
+  "total_flos": 7437909605990400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null