Training in progress, step 340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8527b967128133645e100c466a08cc181daa69f21ade7b0c7d2c2340369ecee
+oid sha256:f2d25b88e084ebd1782d201ceb195fe6db0730594ab101aeca0c6eef087fe8aa
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a030a746ecbed1a27675003fabd902feca0e845682af282e9619dd3883d2dd16
+oid sha256:2450dc03895aa4a5edc22e7d6710bfb27b0462b4e19005486a1604c4a7f4ceee
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232340abfd6d132ef8ac9c5ef9374bc62390215c131732dba5d9141001cfc574
+oid sha256:bd3ee42edb81b08784cce5af0d531cc06157d25956a649c4a46b5f301140f33b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542eeb761eff9bd2c88163850a5018d7ed947bdab57ea917e6e376b6cb0c0259
+oid sha256:e6999f9aad8d44fbf7db1d80d56ad86630abb8e28a7187e80ed24f8546462146
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020618556701030927,
+  "epoch": 0.022909507445589918,
   "eval_steps": 34,
-  "global_step": 306,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -801,6 +801,91 @@
       "eval_samples_per_second": 14.037,
       "eval_steps_per_second": 1.755,
       "step": 306
+    },
+    {
+      "epoch": 0.020820699413786132,
+      "grad_norm": 0.8132256269454956,
+      "learning_rate": 6.421379363065142e-06,
+      "loss": 0.8069,
+      "step": 309
+    },
+    {
+      "epoch": 0.02102284212654134,
+      "grad_norm": 0.7123071551322937,
+      "learning_rate": 6.022586521156715e-06,
+      "loss": 0.7624,
+      "step": 312
+    },
+    {
+      "epoch": 0.021224984839296544,
+      "grad_norm": 0.6497386693954468,
+      "learning_rate": 5.634875954308638e-06,
+      "loss": 0.7902,
+      "step": 315
+    },
+    {
+      "epoch": 0.02142712755205175,
+      "grad_norm": 0.6508458256721497,
+      "learning_rate": 5.258474074573877e-06,
+      "loss": 0.8201,
+      "step": 318
+    },
+    {
+      "epoch": 0.021629270264806953,
+      "grad_norm": 0.9117996096611023,
+      "learning_rate": 4.893600690050579e-06,
+      "loss": 0.8328,
+      "step": 321
+    },
+    {
+      "epoch": 0.021831412977562158,
+      "grad_norm": 0.693020761013031,
+      "learning_rate": 4.540468876520323e-06,
+      "loss": 0.7926,
+      "step": 324
+    },
+    {
+      "epoch": 0.022033555690317366,
+      "grad_norm": 0.6869902014732361,
+      "learning_rate": 4.199284853017896e-06,
+      "loss": 0.805,
+      "step": 327
+    },
+    {
+      "epoch": 0.02223569840307257,
+      "grad_norm": 0.7282816171646118,
+      "learning_rate": 3.8702478614051355e-06,
+      "loss": 0.8067,
+      "step": 330
+    },
+    {
+      "epoch": 0.022437841115827774,
+      "grad_norm": 0.6699129343032837,
+      "learning_rate": 3.5535500500193357e-06,
+      "loss": 0.8041,
+      "step": 333
+    },
+    {
+      "epoch": 0.02263998382858298,
+      "grad_norm": 0.6829515695571899,
+      "learning_rate": 3.249376361464021e-06,
+      "loss": 0.8149,
+      "step": 336
+    },
+    {
+      "epoch": 0.022842126541338183,
+      "grad_norm": 0.7807720303535461,
+      "learning_rate": 2.957904424607652e-06,
+      "loss": 0.825,
+      "step": 339
+    },
+    {
+      "epoch": 0.022909507445589918,
+      "eval_loss": 0.8090208768844604,
+      "eval_runtime": 1781.7524,
+      "eval_samples_per_second": 14.028,
+      "eval_steps_per_second": 1.754,
+      "step": 340
     }
   ],
   "logging_steps": 3,
@@ -820,7 +905,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.3031549961673114e+17,
+  "total_flos": 4.7812833290747904e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null