Training in progress, step 2850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43112abe39c06a0b5ca17135fa11e0bfe258e79ff269b917a6b1d5a4e62477c
+oid sha256:409aaaeded0bcf83a1ad2f8a8aa2059e25e2d11c459671d0ad07902951d56ccb
 size 1369734456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2110ad331782e7a158b2f226a8442097be138b75c8d14f4126f67501be717f6
+oid sha256:7a6fa660e08860b38ae51215c9910f76eac4a3b8c3ca3626a5f9a00ef37913e5
 size 2739607354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b3e8f27fcfe401550ad8e68339098586ba2c4a315de25f2c3e273105526b21
+oid sha256:34535a0f5b3e2caaabc8b8b4e44f0c5669dbce6fa3579b2dfd70851f33133c4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1538c5f25725d45bc5a00763d606d44f6c2d4924289d5e4bc3ac345f59d988a
+oid sha256:fefd4a4db1014a9c64900d77fe95c22931ab60a40f8d1f6d23a762afabfc9cde
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9992671012878418,
-  "best_model_checkpoint": "./output/checkpoint-2700",
-  "epoch": 0.7714285714285715,
+  "best_metric": 0.9964351058006287,
+  "best_model_checkpoint": "./output/checkpoint-2850",
+  "epoch": 0.8142857142857143,
   "eval_steps": 150,
-  "global_step": 2700,
+  "global_step": 2850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2249,6 +2249,143 @@
       "EMA_steps_per_second": 4.945,
       "epoch": 0.7714285714285715,
       "step": 2700
+    },
+    {
+      "epoch": 0.7742857142857142,
+      "grad_norm": 2.9369349479675293,
+      "learning_rate": 3.440770640467657e-05,
+      "loss": 1.0366,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 2.5735695362091064,
+      "learning_rate": 3.440591922877432e-05,
+      "loss": 0.9736,
+      "step": 2720
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.095432996749878,
+      "learning_rate": 3.440412528076098e-05,
+      "loss": 0.987,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7828571428571428,
+      "grad_norm": 2.998671293258667,
+      "learning_rate": 3.44023245613476e-05,
+      "loss": 0.9876,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 3.2118659019470215,
+      "learning_rate": 3.4400517071247936e-05,
+      "loss": 0.9523,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7885714285714286,
+      "grad_norm": 2.917165756225586,
+      "learning_rate": 3.4398702811178414e-05,
+      "loss": 0.9638,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7914285714285715,
+      "grad_norm": 3.0773892402648926,
+      "learning_rate": 3.439688178185815e-05,
+      "loss": 0.9997,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7942857142857143,
+      "grad_norm": 3.3943119049072266,
+      "learning_rate": 3.4395053984008946e-05,
+      "loss": 1.0008,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7971428571428572,
+      "grad_norm": 2.786585807800293,
+      "learning_rate": 3.439321941835528e-05,
+      "loss": 0.8922,
+      "step": 2790
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.2204439640045166,
+      "learning_rate": 3.4391378085624315e-05,
+      "loss": 1.0093,
+      "step": 2800
+    },
+    {
+      "epoch": 0.8028571428571428,
+      "grad_norm": 3.294858694076538,
+      "learning_rate": 3.43895299865459e-05,
+      "loss": 1.024,
+      "step": 2810
+    },
+    {
+      "epoch": 0.8057142857142857,
+      "grad_norm": 3.8853487968444824,
+      "learning_rate": 3.4387675121852555e-05,
+      "loss": 0.9855,
+      "step": 2820
+    },
+    {
+      "epoch": 0.8085714285714286,
+      "grad_norm": 2.766892194747925,
+      "learning_rate": 3.43858134922795e-05,
+      "loss": 1.0017,
+      "step": 2830
+    },
+    {
+      "epoch": 0.8114285714285714,
+      "grad_norm": 3.4095218181610107,
+      "learning_rate": 3.4383945098564614e-05,
+      "loss": 0.9873,
+      "step": 2840
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "grad_norm": 3.2278494834899902,
+      "learning_rate": 3.438206994144847e-05,
+      "loss": 1.0113,
+      "step": 2850
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "eval_loss": 0.9964351058006287,
+      "eval_runtime": 101.0632,
+      "eval_samples_per_second": 4.947,
+      "eval_steps_per_second": 4.947,
+      "step": 2850
+    },
+    {
+      "Raw_Model_loss": 0.9964351058006287,
+      "Raw_Model_runtime": 101.1423,
+      "Raw_Model_samples_per_second": 4.944,
+      "Raw_Model_steps_per_second": 4.944,
+      "epoch": 0.8142857142857143,
+      "step": 2850
+    },
+    {
+      "SWA_loss": 0.995207667350769,
+      "SWA_runtime": 101.0346,
+      "SWA_samples_per_second": 4.949,
+      "SWA_steps_per_second": 4.949,
+      "epoch": 0.8142857142857143,
+      "step": 2850
+    },
+    {
+      "EMA_loss": 1.0361887216567993,
+      "EMA_runtime": 101.0635,
+      "EMA_samples_per_second": 4.947,
+      "EMA_steps_per_second": 4.947,
+      "epoch": 0.8142857142857143,
+      "step": 2850
     }
   ],
   "logging_steps": 10,
@@ -2268,7 +2405,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0274909037272678e+18,
+  "total_flos": 1.0842856817574298e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null