Training in progress, step 755, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e32ecc4999e66597d6819db1b325b5b0ccede14c58906e75e5fbb00465abcf7
+oid sha256:89c68cd6a438b933914a04b6f5f131ead842b1d7581b44de6aaefbdd24e5b716
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8732632a99ef4adc44a4fba23fd2bdffd4c8f2489dc2047a47877ca39df5ad
+oid sha256:f6f463d62884edf4be3d7052906d7e49a09c5aded8637fd7076342e70d2d5b58
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643cbcf647e05c0752cc07e6bea7b36366cf0ca8f60a1980d267a0557a0793d4
+oid sha256:46997f094839d5a72cf41bb76c4ba6e1f48d2860bbee1aff38dc49eeca98851b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd12adaab97c53ac60ce303cf8c26b269527c4e18959058acb54d1c4d122d8e
+oid sha256:b50c27db27104c6ec65d23e9ee9b2125ae74a4486b331a13d6f8605dd5fb4916
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9705596894208994,
+  "epoch": 0.977030087350372,
   "eval_steps": 386,
-  "global_step": 750,
+  "global_step": 755,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5273,6 +5273,41 @@
       "learning_rate": 9.189981455959874e-05,
       "loss": 0.8788,
       "step": 750
+    },
+    {
+      "epoch": 0.9718537690067939,
+      "grad_norm": 0.830154538154602,
+      "learning_rate": 9.187730305463933e-05,
+      "loss": 0.8609,
+      "step": 751
+    },
+    {
+      "epoch": 0.9731478485926884,
+      "grad_norm": 0.7187288403511047,
+      "learning_rate": 9.185476307699159e-05,
+      "loss": 0.8538,
+      "step": 752
+    },
+    {
+      "epoch": 0.974441928178583,
+      "grad_norm": 0.8054041862487793,
+      "learning_rate": 9.18321946419806e-05,
+      "loss": 0.8907,
+      "step": 753
+    },
+    {
+      "epoch": 0.9757360077644776,
+      "grad_norm": 0.7722858190536499,
+      "learning_rate": 9.180959776495085e-05,
+      "loss": 0.82,
+      "step": 754
+    },
+    {
+      "epoch": 0.977030087350372,
+      "grad_norm": 0.7097930312156677,
+      "learning_rate": 9.178697246126607e-05,
+      "loss": 0.855,
+      "step": 755
     }
   ],
   "logging_steps": 1,
@@ -5292,7 +5327,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.38452878770176e+17,
+  "total_flos": 8.440425646286438e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null