Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fd1899e54d143d2f81a5da6bd49edd5f123dd02dff09c374b6433ffd510a41e
+oid sha256:26a3f3b705bc5d832f079ceded9aa22cebef707214a2896fbe31b5a39b2f28f9
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6798a884992637f8fd86ae35c1a2f7f20b19173e66d55c0d2aa0360d93d740d
+oid sha256:7aadb3750252dd5eeb1c71f655fd23bfd464774f9a631699d0aefab4f994a7ef
 size 18813829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181c5f0270cf39930062ddfa3767a2481d0c360f120b11f8e25dbf533a1cdaba
+oid sha256:3d6d8fafcd1ee268414be5acf0366296af5b03d60871978712eac1979cb42d65
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fee0874fa9afae54661807fadac685c3d3f843473b6af99cc43d812ec6e1b36
+oid sha256:20ab57b9b26fc7cb4418a4e1198e25ebb1da623aea7693e1fc71ff284d45724b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142330f2274e6971505182827bf85a03f6f751d0c7c41a1bed02d084e8c2ed30
+oid sha256:d36674cd5023cd616db0a9a98e030c82f7d655c0707dfe4815644a611495e0b5
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 20,
-  "best_metric": 0.9114124178886414,
-  "best_model_checkpoint": "/tmp/checkpoints_/job_0d4521ef-134d-4da5-986e-64cc35a0beaa/checkpoint-20",
-  "epoch": 0.4444444444444444,
+  "best_global_step": 30,
+  "best_metric": 0.4217299818992615,
+  "best_model_checkpoint": "/tmp/checkpoints_/job_0d4521ef-134d-4da5-986e-64cc35a0beaa/checkpoint-30",
+  "epoch": 0.6666666666666666,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,84 @@
       "eval_samples_per_second": 32.293,
       "eval_steps_per_second": 8.073,
       "step": 20
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 4.757471561431885,
+      "learning_rate": 4.837540606713538e-05,
+      "loss": 0.9015084505081177,
+      "step": 21
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 4.183780193328857,
+      "learning_rate": 4.815436622394441e-05,
+      "loss": 0.7763562202453613,
+      "step": 22
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 6.7120466232299805,
+      "learning_rate": 4.791980488291456e-05,
+      "loss": 0.9629366993904114,
+      "step": 23
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 3.9772117137908936,
+      "learning_rate": 4.767185902126364e-05,
+      "loss": 0.7046512365341187,
+      "step": 24
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 4.194173336029053,
+      "learning_rate": 4.7410673432392596e-05,
+      "loss": 0.6537044048309326,
+      "step": 25
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 4.1374287605285645,
+      "learning_rate": 4.713640064133025e-05,
+      "loss": 0.5453305244445801,
+      "step": 26
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.520692825317383,
+      "learning_rate": 4.684920081566295e-05,
+      "loss": 0.6430343985557556,
+      "step": 27
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 6.000478267669678,
+      "learning_rate": 4.654924167200123e-05,
+      "loss": 0.655798614025116,
+      "step": 28
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 3.8246989250183105,
+      "learning_rate": 4.6236698378038026e-05,
+      "loss": 0.5909295082092285,
+      "step": 29
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.1917481422424316,
+      "learning_rate": 4.5911753450255665e-05,
+      "loss": 0.3079158067703247,
+      "step": 30
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.4217299818992615,
+      "eval_runtime": 0.6115,
+      "eval_samples_per_second": 32.706,
+      "eval_steps_per_second": 8.176,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -178,12 +256,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21898370837760.0,
+  "total_flos": 32866257768960.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null