Training in progress, step 750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec824641add39464132135bb7a178865727158172de3bdde8ba2e0a866892f41
+oid sha256:2e32ecc4999e66597d6819db1b325b5b0ccede14c58906e75e5fbb00465abcf7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e6bf779b6bee53a40e25587a5a42e0d05bf8ba9a3e393cce3a2b2f78901828
+oid sha256:3a8732632a99ef4adc44a4fba23fd2bdffd4c8f2489dc2047a47877ca39df5ad
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f710d7aa27629692705a763863916eca2f9c0f51210ce83e8b983733d085a79
+oid sha256:643cbcf647e05c0752cc07e6bea7b36366cf0ca8f60a1980d267a0557a0793d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292ac4e1ecba553470239753cee72c97588f1df45bbde70904d7eb64da490cd4
+oid sha256:bdd12adaab97c53ac60ce303cf8c26b269527c4e18959058acb54d1c4d122d8e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9640892914914267,
+  "epoch": 0.9705596894208994,
   "eval_steps": 386,
-  "global_step": 745,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5238,6 +5238,41 @@
       "learning_rate": 9.201194445904803e-05,
       "loss": 1.0089,
       "step": 745
+    },
+    {
+      "epoch": 0.9653833710773213,
+      "grad_norm": 0.747582733631134,
+      "learning_rate": 9.198957554672885e-05,
+      "loss": 0.9392,
+      "step": 746
+    },
+    {
+      "epoch": 0.9666774506632158,
+      "grad_norm": 0.7720314264297485,
+      "learning_rate": 9.196717808538641e-05,
+      "loss": 0.9572,
+      "step": 747
+    },
+    {
+      "epoch": 0.9679715302491103,
+      "grad_norm": 0.802967369556427,
+      "learning_rate": 9.194475209024895e-05,
+      "loss": 0.697,
+      "step": 748
+    },
+    {
+      "epoch": 0.9692656098350049,
+      "grad_norm": 0.7272825837135315,
+      "learning_rate": 9.192229757656406e-05,
+      "loss": 0.7704,
+      "step": 749
+    },
+    {
+      "epoch": 0.9705596894208994,
+      "grad_norm": 0.7247483730316162,
+      "learning_rate": 9.189981455959874e-05,
+      "loss": 0.8788,
+      "step": 750
     }
   ],
   "logging_steps": 1,
@@ -5257,7 +5292,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.328631929117082e+17,
+  "total_flos": 8.38452878770176e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null