Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f367d2242ad80350965a9970ea6144ecfd87beedca7178846e04606a0725844
+oid sha256:441fe7c0aeb3a8ca922e3700372d02b6f386faf91257feea2c24d6c0444b25a5
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e3e968f1ef58eb2714a62ec1f5266ebb299eaefa64f5fa895fb18508c96679
+oid sha256:d4b64c33a9ef37e366a1d24db27393fc1bbd38f4d83b80a5494eca61bfeaaa58
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd68f1cff6add0a7142cd175354304a672953f2dd8538ececc38636192f2eede
+oid sha256:917adaa20d62fb616cea0abf8f6c84a3f7c5f416c800b7d601903d4c10c88a33
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013678867218808443,
+  "epoch": 0.020518300828212665,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 28.234,
       "eval_steps_per_second": 14.117,
       "step": 16
+    },
+    {
+      "epoch": 0.01453379641998397,
+      "grad_norm": 12.619002342224121,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.5653,
+      "step": 17
+    },
+    {
+      "epoch": 0.015388725621159498,
+      "grad_norm": 8.323529243469238,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5732,
+      "step": 18
+    },
+    {
+      "epoch": 0.016243654822335026,
+      "grad_norm": 6.280013084411621,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.4411,
+      "step": 19
+    },
+    {
+      "epoch": 0.017098584023510555,
+      "grad_norm": 8.90284252166748,
+      "learning_rate": 5e-05,
+      "loss": 0.4957,
+      "step": 20
+    },
+    {
+      "epoch": 0.01795351322468608,
+      "grad_norm": 14.239660263061523,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.5933,
+      "step": 21
+    },
+    {
+      "epoch": 0.018808442425861608,
+      "grad_norm": 6.530233860015869,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4186,
+      "step": 22
+    },
+    {
+      "epoch": 0.019663371627037136,
+      "grad_norm": 4.9676833152771,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.412,
+      "step": 23
+    },
+    {
+      "epoch": 0.020518300828212665,
+      "grad_norm": 9.296878814697266,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.497,
+      "step": 24
+    },
+    {
+      "epoch": 0.020518300828212665,
+      "eval_loss": 0.4413914680480957,
+      "eval_runtime": 70.1243,
+      "eval_samples_per_second": 28.093,
+      "eval_steps_per_second": 14.046,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2386848890421248e+16,
+  "total_flos": 1.858027333563187e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null