Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b6e71b4884a09a7b1edac5522d21e9515e6abf8e1491bdc89ff852a6ac6a80
+oid sha256:04ad169263f69fb250d44692b9c132a177d248eabba86e793c940456f05f0c38
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8941d9ba9bfd7e363783d8fff8b08f6dd5e12ba9c8b79198fd4b4e144bf3aa
+oid sha256:a65ce144c32272ad985764683a967b6820b525c179e4195d0b1d1768c57f2506
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eda19cb53a7ad30636011d96c41776d3307021fe6c186eb1aec6f9b34d91073
+oid sha256:c1f80896712989f28385b5f2745ee175a373e7981a909af50471561406cc9448
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.040417649040080834,
+  "epoch": 0.05389019872010778,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 3.64,
       "eval_steps_per_second": 1.826,
       "step": 30
+    },
+    {
+      "epoch": 0.04445941394408892,
+      "grad_norm": 0.38887056708335876,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.5696,
+      "step": 33
+    },
+    {
+      "epoch": 0.04715392388009431,
+      "eval_loss": 0.6192119717597961,
+      "eval_runtime": 85.8856,
+      "eval_samples_per_second": 3.644,
+      "eval_steps_per_second": 1.828,
+      "step": 35
+    },
+    {
+      "epoch": 0.048501178848097,
+      "grad_norm": 0.43659067153930664,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5815,
+      "step": 36
+    },
+    {
+      "epoch": 0.05254294375210509,
+      "grad_norm": 0.4002622365951538,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.661,
+      "step": 39
+    },
+    {
+      "epoch": 0.05389019872010778,
+      "eval_loss": 0.6184704899787903,
+      "eval_runtime": 85.8516,
+      "eval_samples_per_second": 3.646,
+      "eval_steps_per_second": 1.829,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.7341615253225472e+16,
+  "total_flos": 2.3091241700818944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null