Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b8f32df568e901586a05dea3c70a3606885aae6e1350c8573f91588f83c55d
+oid sha256:f46afd64dbadfa0a8623b4c1377c0d92385ff0aaff8a8327f9689e96446d3f00
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5e09ce1d1b0d7a06b08dac927bd206fa1f03a97d0b60cf7a8e57586f528e4a
+oid sha256:4ef6a58e312c6730f413379c7c36fc9de6bc7e5cfcd613eda52529d5f3f84e20
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4153372e5441b0ea2e6a8c0a0ff12401521178273f30862f0b9f4725190679f0
+oid sha256:b1fbac2690de67edd93baf8d76b7485f0d1b64a83524d673302021c491150379
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15,
+  "epoch": 0.19230769230769232,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.6332,
       "step": 35
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 2.8168230056762695,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6108,
+      "step": 40
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "eval_loss": 1.5564663410186768,
+      "eval_runtime": 3.8655,
+      "eval_samples_per_second": 28.457,
+      "eval_steps_per_second": 14.229,
+      "step": 40
+    },
+    {
+      "epoch": 0.17307692307692307,
+      "grad_norm": 3.9268558025360107,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7135,
+      "step": 45
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 3.661607503890991,
+      "learning_rate": 0.0,
+      "loss": 1.6405,
+      "step": 50
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "eval_loss": 1.5520949363708496,
+      "eval_runtime": 3.71,
+      "eval_samples_per_second": 29.65,
+      "eval_steps_per_second": 14.825,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 347248838836224.0,
+  "total_flos": 445190819020800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null