Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24857cf0c8edaa59c8dfe422e71ac9c0ba62e19c0a47e15bbbe509803105f964
+oid sha256:3a99a084aa240aec6c58fcfcbab380739990516e0e1cf77f705dfa3277e1b953
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd7cec636a5c9f4a170b1b8695c3fdf4ed84ec297eb38a4595c7d3f9ede13de0
+oid sha256:ec566b1e2db27ee0e79f8477dc9582b2928a3705f67069392f54cd8edc070961
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b18bb018d6f0723e725784b3dab518122397063a13aa6bbd1ff4e3d8e34477
+oid sha256:d96de525e29b1b59094ce58a4bd2e9c387a3978d3ec81d3db8966e892be41c0c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015819655922483685,
+  "epoch": 0.02372948388372553,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.526,
       "eval_steps_per_second": 2.768,
       "step": 20
+    },
+    {
+      "epoch": 0.01661063871860787,
+      "grad_norm": 1.1589887142181396,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.8789,
+      "step": 21
+    },
+    {
+      "epoch": 0.018983587106980424,
+      "grad_norm": 1.2269470691680908,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.0367,
+      "step": 24
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "eval_loss": 1.9202778339385986,
+      "eval_runtime": 96.3717,
+      "eval_samples_per_second": 5.531,
+      "eval_steps_per_second": 2.771,
+      "step": 25
+    },
+    {
+      "epoch": 0.021356535495352977,
+      "grad_norm": 1.1548726558685303,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.7571,
+      "step": 27
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 1.1918234825134277,
+      "learning_rate": 0.0,
+      "loss": 1.8205,
+      "step": 30
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "eval_loss": 1.8914263248443604,
+      "eval_runtime": 96.1971,
+      "eval_samples_per_second": 5.541,
+      "eval_steps_per_second": 2.776,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3292692008140800.0,
+  "total_flos": 4939038012211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null