Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662e8240fcc8125ee212a998f444a99fcb0584a529faab6cba36c8c0124ed12f
+oid sha256:db26a3a5e53c205f2d4bad20dce751ff2dfc9682295ec167967af50b2b707383
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94679983a837ebe8099bd03c71b3601567757298dfa8dc794ea7fce417dd7ba3
+oid sha256:cded7f24df305c017db794fab5ac075a743c116d0ddb541ba3d8731b641edb06
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ab9b9869e601adf44834e3a12d4a18fbed8343468019356d2f3491dc62e15c
+oid sha256:a5051a0e31a9165b3b43ecaf91c64aba598ba8800af01edf71cd1ee48db7cb7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04428044280442804,
+  "epoch": 0.04920049200492005,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 7.225,
       "eval_steps_per_second": 0.905,
       "step": 81
+    },
+    {
+      "epoch": 0.04592045920459205,
+      "grad_norm": 0.20597471296787262,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.64,
+      "step": 84
+    },
+    {
+      "epoch": 0.04756047560475605,
+      "grad_norm": 0.1945589780807495,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.5816,
+      "step": 87
+    },
+    {
+      "epoch": 0.04920049200492005,
+      "grad_norm": 0.22032710909843445,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.6275,
+      "step": 90
+    },
+    {
+      "epoch": 0.04920049200492005,
+      "eval_loss": 0.620901346206665,
+      "eval_runtime": 426.7055,
+      "eval_samples_per_second": 7.22,
+      "eval_steps_per_second": 0.905,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1188066446147584e+17,
+  "total_flos": 2.3568005266931712e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null