Training in progress, step 189, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c519466660fb59967062216d0f5efa7283eb977dba86ef804c3a14dbb3383a
+oid sha256:511b949222194749b3abf5ca656be73eb32c6a12f56b81637812ef450cb31d55
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8789a178c950755bf39e4f96b3897c02395e6d80885c63c680c9f6d871cf95
+oid sha256:b73017ef2252ef16503db219377dade5006705a9940a6886d26cf3e45ea31fb1
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291344f456f153a7376ca0b920135507aac3c857efddc3249e513f3f8ffa1428
+oid sha256:1148d6cd6f8340f6da633aebea9f78d7832bbb61eca78a87b0da29fc68af6870
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
+oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023641992682240362,
+  "epoch": 0.03546298902336054,
   "eval_steps": 63,
-  "global_step": 126,
+  "global_step": 189,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,56 @@
       "eval_samples_per_second": 9.075,
       "eval_steps_per_second": 4.538,
       "step": 126
+    },
+    {
+      "epoch": 0.024392532132470213,
+      "grad_norm": 1.239576816558838,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 1.9303,
+      "step": 130
+    },
+    {
+      "epoch": 0.026268880758044844,
+      "grad_norm": 0.9954649806022644,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 1.9751,
+      "step": 140
+    },
+    {
+      "epoch": 0.028145229383619477,
+      "grad_norm": 1.0179868936538696,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 2.0224,
+      "step": 150
+    },
+    {
+      "epoch": 0.030021578009194107,
+      "grad_norm": 0.906938910484314,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 1.9507,
+      "step": 160
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 1.2570104598999023,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 2.2063,
+      "step": 170
+    },
+    {
+      "epoch": 0.03377427526034337,
+      "grad_norm": 0.9839584827423096,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 1.8448,
+      "step": 180
+    },
+    {
+      "epoch": 0.03546298902336054,
+      "eval_loss": 0.4881777763366699,
+      "eval_runtime": 247.034,
+      "eval_samples_per_second": 9.084,
+      "eval_steps_per_second": 4.542,
+      "step": 189
     }
   ],
   "logging_steps": 10,
@@ -134,7 +184,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.13669484068864e+16,
+  "total_flos": 1.228997644517376e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null