Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe715dfc3c6655975b4c0cb344e7c945494e1463e96c18bf9c77000e7066604
+oid sha256:3fa532b40d5c0681f2baf3e51922c8aea3f5f742de78d5404e2c7fb13b9d1384
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa28aca63d30e6a77fca80f9f9286ec5bb1020314276276e1f34a85650641b30
+oid sha256:c51b96be3eb3a7f526346cab91aa0e09347e5f1b0e2ea7802e6818d1e2a82d14
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
+oid sha256:eb04243bb25bf686a4dbec102fd9ca7613ad5c31a6a03dfc0541d4df84930100
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541ccba4d24c3fd7a3a1bd1b7c1a8ef18368821282014bf91f536020daf3aafe
+oid sha256:7f110d38baddc83b27dc701018da1279ccbbfd00f24dd48bfba755b5837c286c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.56973293768546,
+  "epoch": 0.8545994065281899,
   "eval_steps": 6,
-  "global_step": 12,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 497.765,
       "eval_steps_per_second": 248.882,
       "step": 12
+    },
+    {
+      "epoch": 0.6172106824925816,
+      "grad_norm": 0.10060179978609085,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 10.3803,
+      "step": 13
+    },
+    {
+      "epoch": 0.6646884272997032,
+      "grad_norm": 0.11765701323747635,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3862,
+      "step": 14
+    },
+    {
+      "epoch": 0.712166172106825,
+      "grad_norm": 0.12245073914527893,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 10.3825,
+      "step": 15
+    },
+    {
+      "epoch": 0.7596439169139466,
+      "grad_norm": 0.10479110479354858,
+      "learning_rate": 5e-05,
+      "loss": 10.3832,
+      "step": 16
+    },
+    {
+      "epoch": 0.8071216617210683,
+      "grad_norm": 0.09735947102308273,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3786,
+      "step": 17
+    },
+    {
+      "epoch": 0.8545994065281899,
+      "grad_norm": 0.11688768118619919,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3835,
+      "step": 18
+    },
+    {
+      "epoch": 0.8545994065281899,
+      "eval_loss": 10.379833221435547,
+      "eval_runtime": 0.0775,
+      "eval_samples_per_second": 464.759,
+      "eval_steps_per_second": 232.379,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 966585384960.0,
+  "total_flos": 1432098078720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null