Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3355e94058a53cad7c6d0239bda879bff4ca7a4fd70783189dc485084a503236
+oid sha256:bcd0dc07f8468af1d5a75c28ec5bf1e0425f693eeb5eb0fd1545d727210abaec
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d3e8a4d6acb2fb8b52aebd7af348f4567e36ea211d1cffac381840dca07fc2
+oid sha256:6576bb5b97b31ae9c2dbe40f1920f42fda092c96079dfa545e56a39acc825815
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae30e70644334ba58e5c990bb22075127b24ef6e4c7a0b149c16de65cbd225fb
+oid sha256:bf4678f22263b499b2336dd8c5f6a0b45dbd7d6f97aa6e1ba4fd1b5dc1d9be75
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016842105263157894,
+  "epoch": 0.03368421052631579,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 10.184,
       "eval_steps_per_second": 5.092,
       "step": 10
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 14.489277839660645,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.086,
+      "step": 12
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 4.496290683746338,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.2389,
+      "step": 15
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 2.3330087661743164,
+      "eval_runtime": 24.5945,
+      "eval_samples_per_second": 10.165,
+      "eval_steps_per_second": 5.082,
+      "step": 15
+    },
+    {
+      "epoch": 0.03031578947368421,
+      "grad_norm": 2.6100714206695557,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2098,
+      "step": 18
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "eval_loss": 2.2271230220794678,
+      "eval_runtime": 24.609,
+      "eval_samples_per_second": 10.159,
+      "eval_steps_per_second": 5.079,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3834471807713280.0,
+  "total_flos": 7668943615426560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null