Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab7cafe1196ec878b8d3d2a3fc6884678d599ff025eaf88982d550d3f25d645
+oid sha256:c94fc6653a6657011149912d979ea84e5d764001724e6c10946162dfa0bb0d5d
 size 58680

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546e9ffa163a869b7fbcf985cc08dc91fa5c651df09b0cd03cc29c573b6d749a
+oid sha256:9ef74568d1c054685626697a586f47b5fbb2cd890f27cd1bc19f7016bf19783e
 size 127270

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
+oid sha256:2d1201220196b0eea01cc2e9383598f0df0fda082156bad64ee5af51ec629e09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3da5b3ae9debb9fbcab0805794dfaab406f2d5635e0407c25e32749f5f7b455
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0073370562100028534,
+  "epoch": 0.008152284677780949,
   "eval_steps": 5,
-  "global_step": 45,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 141.981,
       "eval_steps_per_second": 71.018,
       "step": 45
+    },
+    {
+      "epoch": 0.007500101903558472,
+      "grad_norm": 0.8296800255775452,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 41.4416,
+      "step": 46
+    },
+    {
+      "epoch": 0.007663147597114091,
+      "grad_norm": 1.1589857339859009,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 41.4379,
+      "step": 47
+    },
+    {
+      "epoch": 0.007826193290669711,
+      "grad_norm": 0.8042440414428711,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 41.4556,
+      "step": 48
+    },
+    {
+      "epoch": 0.007989238984225329,
+      "grad_norm": 0.7898399233818054,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 41.4265,
+      "step": 49
+    },
+    {
+      "epoch": 0.008152284677780949,
+      "grad_norm": 0.9658806920051575,
+      "learning_rate": 0.0,
+      "loss": 41.4237,
+      "step": 50
+    },
+    {
+      "epoch": 0.008152284677780949,
+      "eval_loss": 10.35954475402832,
+      "eval_runtime": 18.3291,
+      "eval_samples_per_second": 140.923,
+      "eval_steps_per_second": 70.489,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -416,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9300344832000.0,
+  "total_flos": 10333716480000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null