Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4633c36e3654ad228ee9875fa5e797e65edd5f1f4dfc18c6f66eb52a90782438
+oid sha256:f84ed94a00e5d0b7abe3092aaf60f37ee3b7067f886171eb68401de191363c20
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1980b0770df31cf1cd1d4e2965c60c6b823853b121fd93a0fccae1d5fdad9bd0
+oid sha256:b1e59614221717bdbd72cd8c21b8e794b7bb88abd0c9bddce17abd5db86ebb0d
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a47e581006cab5c81c1e8f19202964019bdbacf8e3e829e3c49902419535e7
+oid sha256:d41012d426f4d5b3af1d3ffb493825e83f81b37c7d8924b009246b2007dd13b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028373763026534722,
+  "epoch": 0.03152640336281636,
   "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": 27.86,
       "eval_steps_per_second": 3.483,
       "step": 81
+    },
+    {
+      "epoch": 0.029424643138628602,
+      "grad_norm": 0.2582884132862091,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.0749,
+      "step": 84
+    },
+    {
+      "epoch": 0.03047552325072248,
+      "grad_norm": 0.26067253947257996,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.107,
+      "step": 87
+    },
+    {
+      "epoch": 0.03152640336281636,
+      "grad_norm": 0.2517987787723541,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0924,
+      "step": 90
+    },
+    {
+      "epoch": 0.03152640336281636,
+      "eval_loss": 1.078951358795166,
+      "eval_runtime": 172.5708,
+      "eval_samples_per_second": 27.861,
+      "eval_steps_per_second": 3.483,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3351548213919744e+16,
+  "total_flos": 3.705727579324416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null