Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e25fc3038a8e3f4d67294734295c486c8bc2398c6811e5f692a270d3008d6eb
+oid sha256:7c57fe09243896e76e6f76c61f17bc3984147f179fca4fb74f9ffa39488fe0c0
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1774f77f007af7b55a69980f0a6cc754386dc022cc57f072771b815409c819b
+oid sha256:fcfdbc7bca82335aae340b66c7faa043a100ef8deb0953fa142d1c1c8131445d
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd17b5df1022d14a6bc409d5199b678b4ef7ee120dd6b803365c640249735528
+oid sha256:cfadc05d2d983979ebf39752461dcf62eb230eb8d820bd09cf23d7888d9df570
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6003b9da5fb97bf7840c3b5bc091d085fbbef473002eef31535fde335f58e3e
+oid sha256:826ab5cbdeebfceff791289dbda0e94c2a0531ba16021b3dca9d34da57cc673a
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b018ac4fe63057a6f92b6fc2b40d2df6ba47ab96e6b212db49c719e05a03a8
+oid sha256:5e4f8bcc2f798ba5b1e1d3cd63c141ee8b120ed84e3abbab7c93fa5dd43e4059
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5241605241605242,
+  "epoch": 0.7862407862407862,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -171,6 +171,84 @@
       "eval_samples_per_second": 36.862,
       "eval_steps_per_second": 9.323,
       "step": 20
+    },
+    {
+      "epoch": 0.5503685503685504,
+      "grad_norm": 0.4809012711048126,
+      "learning_rate": 4.78779398401926e-05,
+      "loss": 1.6745,
+      "step": 21
+    },
+    {
+      "epoch": 0.5765765765765766,
+      "grad_norm": 0.44002801179885864,
+      "learning_rate": 4.364910901265606e-05,
+      "loss": 1.5675,
+      "step": 22
+    },
+    {
+      "epoch": 0.6027846027846028,
+      "grad_norm": 0.4592677652835846,
+      "learning_rate": 3.94660365002137e-05,
+      "loss": 1.7446,
+      "step": 23
+    },
+    {
+      "epoch": 0.628992628992629,
+      "grad_norm": 0.4685349762439728,
+      "learning_rate": 3.5358861436172485e-05,
+      "loss": 1.6143,
+      "step": 24
+    },
+    {
+      "epoch": 0.6552006552006552,
+      "grad_norm": 0.46893665194511414,
+      "learning_rate": 3.135717611098458e-05,
+      "loss": 1.6969,
+      "step": 25
+    },
+    {
+      "epoch": 0.6814086814086814,
+      "grad_norm": 0.4547032415866852,
+      "learning_rate": 2.748981275911633e-05,
+      "loss": 1.6562,
+      "step": 26
+    },
+    {
+      "epoch": 0.7076167076167076,
+      "grad_norm": 0.46321848034858704,
+      "learning_rate": 2.3784635822138424e-05,
+      "loss": 1.6516,
+      "step": 27
+    },
+    {
+      "epoch": 0.7338247338247338,
+      "grad_norm": 0.453426718711853,
+      "learning_rate": 2.026834118478567e-05,
+      "loss": 1.5961,
+      "step": 28
+    },
+    {
+      "epoch": 0.76003276003276,
+      "grad_norm": 0.4333644211292267,
+      "learning_rate": 1.6966263830495936e-05,
+      "loss": 1.6134,
+      "step": 29
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "grad_norm": 0.4507792592048645,
+      "learning_rate": 1.3902195302273779e-05,
+      "loss": 1.5558,
+      "step": 30
+    },
+    {
+      "epoch": 0.7862407862407862,
+      "eval_loss": 1.6152641773223877,
+      "eval_runtime": 6.9374,
+      "eval_samples_per_second": 37.045,
+      "eval_steps_per_second": 9.369,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -190,7 +268,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.275680826713702e+16,
+  "total_flos": 9.425617760446054e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null