Training in progress, step 4200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120c01426d977197b39b1f0009eba2eaf0399f797a43f25b8296782bb1c7f727
+oid sha256:78ad2800a71edbf10431e06720d1d6873d6962ef1fd11d8c5dc726b24e0d8f28
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:747714729eb0260553ac517d27720ea5282588752a3f4c080aba0c7ed5f57266
+oid sha256:17d37f1348f823c28b3eaddba75e3c0c2ca3f44b92d541b35de0b22c8c3a4303
 size 640010002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec09828e725ea8e5465799ac246a72800a11225a4aa5d07b638afa9c5c8fe320
+oid sha256:e8afb4c65ba75845b61dba85d34976f94823f8b3f858229d00979f1187c6debf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a421c1aa44eafb26a0447c42566a2cb9ceb53f55068e96124eecff6613899e
+oid sha256:820726d6ef8ac6d9f9ca34e9eb1daa2e5ba6a674a46b1cafa3773bfd40fd74af
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.32636332511901855,
   "best_model_checkpoint": "./output/checkpoint-3600",
-  "epoch": 0.22899468506163068,
+  "epoch": 0.23747596969354293,
   "eval_steps": 150,
-  "global_step": 4050,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3058,6 +3058,119 @@
       "eval_samples_per_second": 12.597,
       "eval_steps_per_second": 12.597,
       "step": 4050
+    },
+    {
+      "epoch": 0.22956010403709148,
+      "grad_norm": 4.386037349700928,
+      "learning_rate": 6.606620664160438e-07,
+      "loss": 0.1743,
+      "step": 4060
+    },
+    {
+      "epoch": 0.2301255230125523,
+      "grad_norm": 0.43842968344688416,
+      "learning_rate": 6.470970781530139e-07,
+      "loss": 0.1721,
+      "step": 4070
+    },
+    {
+      "epoch": 0.23069094198801313,
+      "grad_norm": 0.4264715611934662,
+      "learning_rate": 6.336596380758604e-07,
+      "loss": 0.1568,
+      "step": 4080
+    },
+    {
+      "epoch": 0.23125636096347393,
+      "grad_norm": 0.2072145938873291,
+      "learning_rate": 6.203502985451152e-07,
+      "loss": 0.2589,
+      "step": 4090
+    },
+    {
+      "epoch": 0.23182177993893474,
+      "grad_norm": 0.47133326530456543,
+      "learning_rate": 6.071696066555978e-07,
+      "loss": 0.2778,
+      "step": 4100
+    },
+    {
+      "epoch": 0.23238719891439558,
+      "grad_norm": 9.583172798156738,
+      "learning_rate": 5.941181042139258e-07,
+      "loss": 0.322,
+      "step": 4110
+    },
+    {
+      "epoch": 0.23295261788985638,
+      "grad_norm": 2.681870460510254,
+      "learning_rate": 5.811963277162466e-07,
+      "loss": 0.0906,
+      "step": 4120
+    },
+    {
+      "epoch": 0.2335180368653172,
+      "grad_norm": 1.2123790979385376,
+      "learning_rate": 5.684048083261789e-07,
+      "loss": 0.1341,
+      "step": 4130
+    },
+    {
+      "epoch": 0.23408345584077803,
+      "grad_norm": 0.409408837556839,
+      "learning_rate": 5.557440718529848e-07,
+      "loss": 0.0791,
+      "step": 4140
+    },
+    {
+      "epoch": 0.23464887481623883,
+      "grad_norm": 5.215662002563477,
+      "learning_rate": 5.432146387299522e-07,
+      "loss": 0.2075,
+      "step": 4150
+    },
+    {
+      "epoch": 0.23521429379169964,
+      "grad_norm": 10.576168060302734,
+      "learning_rate": 5.308170239930022e-07,
+      "loss": 0.2556,
+      "step": 4160
+    },
+    {
+      "epoch": 0.23577971276716048,
+      "grad_norm": 0.5010024309158325,
+      "learning_rate": 5.185517372595187e-07,
+      "loss": 0.1953,
+      "step": 4170
+    },
+    {
+      "epoch": 0.23634513174262128,
+      "grad_norm": 4.521603107452393,
+      "learning_rate": 5.064192827073995e-07,
+      "loss": 0.1843,
+      "step": 4180
+    },
+    {
+      "epoch": 0.2369105507180821,
+      "grad_norm": 6.856910705566406,
+      "learning_rate": 4.944201590543308e-07,
+      "loss": 0.1933,
+      "step": 4190
+    },
+    {
+      "epoch": 0.23747596969354293,
+      "grad_norm": 3.1912882328033447,
+      "learning_rate": 4.825548595372898e-07,
+      "loss": 0.1511,
+      "step": 4200
+    },
+    {
+      "epoch": 0.23747596969354293,
+      "eval_loss": 0.32930639386177063,
+      "eval_runtime": 39.7678,
+      "eval_samples_per_second": 12.573,
+      "eval_steps_per_second": 12.573,
+      "step": 4200
     }
   ],
   "logging_steps": 10,
@@ -3077,7 +3190,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2662168077736346e+17,
+  "total_flos": 2.3523473691957658e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null