Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ec1f71e8a58628b38e46eab8da79ed873b4ba022e71692d2df7dca37dff837
+oid sha256:f6e9693f35e165079ed3e11aacddcc767a0f60b7b572eb342620d085c950c3dc
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4f02b9c3b5bcb15be2c7324e1fde42ab8d9d0a2dc971479d840b7c1acd8d8a
+oid sha256:cc1f95da4d9c6b620be952ddfd70190b9dedcc5f70c06fdb52adbff5b77fa693
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad9cfa2a8dccff47b818d8bc530fee820cce157f145335f873d55243753a718
+oid sha256:95b7185e590278f6f9b499f3452bf508a28b1fd572e7d8c2f71e1ca40516afc9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d8ec93266e4bc8a64331da6b277e98dfae3d3d4bab70d66d65fad27bc26c8c
+oid sha256:0af27ed5b5e5c3013f1da7a97e494138e751399ceff1f8e7486b6e269bc7092f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.036677454153182305,
+  "epoch": 0.07335490830636461,
   "eval_steps": 17,
-  "global_step": 17,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,56 @@
       "eval_samples_per_second": 51.368,
       "eval_steps_per_second": 6.446,
       "step": 17
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 0.42941978573799133,
+      "learning_rate": 9.956320346634876e-05,
+      "loss": 0.0104,
+      "step": 18
+    },
+    {
+      "epoch": 0.045307443365695796,
+      "grad_norm": 0.16689348220825195,
+      "learning_rate": 9.917525374361912e-05,
+      "loss": 0.0053,
+      "step": 21
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.1845988631248474,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.0032,
+      "step": 24
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 0.2645643949508667,
+      "learning_rate": 9.803768380684242e-05,
+      "loss": 0.0052,
+      "step": 27
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.019420228898525238,
+      "learning_rate": 9.729086208503174e-05,
+      "loss": 0.0056,
+      "step": 30
+    },
+    {
+      "epoch": 0.07119741100323625,
+      "grad_norm": 0.054533425718545914,
+      "learning_rate": 9.642770192448536e-05,
+      "loss": 0.0043,
+      "step": 33
+    },
+    {
+      "epoch": 0.07335490830636461,
+      "eval_loss": 0.004006265662610531,
+      "eval_runtime": 15.2337,
+      "eval_samples_per_second": 51.268,
+      "eval_steps_per_second": 6.433,
+      "step": 34
     }
   ],
   "logging_steps": 3,
@@ -77,7 +127,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3387028993474560.0,
+  "total_flos": 6677285729992704.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null