Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb15a74b3702f66007f2eb3fb5d517e7d45ca36b21e019f87cd567d4eeca531
+oid sha256:d3bc0f4fd031baa461a08a73c9d0b5c6557be7235ea59fbd23db3fc7dcaeaf52
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5888324401df92ecd87b8c160db131f2352fa716b1dc5c258a5e358f39586d3
+oid sha256:bffac84eaac97cbaa77d1adc85cb7ccd4ffae53d401e54121aef1789235dda6a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bd630772456bf478ad7859a7b0ea3f36dda482f354ce665d158b5f4b742076
+oid sha256:e8f50bcb282a535c8d60e0cd286b37ee0fb35f76262156b1484dc636b0a4dd7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bbb5cc30267ffbb6fcba5b12ec3b2b908df1e2e422c7d381d682f082ea4159
+oid sha256:507bfe4270aab5b2aa070e93d9c3404af996914dd61586771e0cc504e5b0252c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03640040444893832,
+  "epoch": 0.04044489383215369,
   "eval_steps": 13,
-  "global_step": 117,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,42 @@
       "eval_samples_per_second": 13.876,
       "eval_steps_per_second": 1.735,
       "step": 117
+    },
+    {
+      "epoch": 0.03733374815275725,
+      "grad_norm": 1.1355212926864624,
+      "learning_rate": 5.454212938299255e-06,
+      "loss": 1.4929,
+      "step": 120
+    },
+    {
+      "epoch": 0.03826709185657618,
+      "grad_norm": 1.2554372549057007,
+      "learning_rate": 4.4499481138022544e-06,
+      "loss": 1.4357,
+      "step": 123
+    },
+    {
+      "epoch": 0.03920043556039512,
+      "grad_norm": 1.289537787437439,
+      "learning_rate": 3.5387801599533475e-06,
+      "loss": 1.4257,
+      "step": 126
+    },
+    {
+      "epoch": 0.04013377926421405,
+      "grad_norm": 1.439562201499939,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 1.4607,
+      "step": 129
+    },
+    {
+      "epoch": 0.04044489383215369,
+      "eval_loss": 1.4785248041152954,
+      "eval_runtime": 390.0687,
+      "eval_samples_per_second": 13.88,
+      "eval_steps_per_second": 1.736,
+      "step": 130
     }
   ],
   "logging_steps": 3,
@@ -379,7 +415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7360162435314483e+17,
+  "total_flos": 1.9289069372571648e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null