Training in progress, step 143, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3bc0f4fd031baa461a08a73c9d0b5c6557be7235ea59fbd23db3fc7dcaeaf52
+oid sha256:ba8f92fff3d0704cfd2878c9aa27bb09f39f0ef1e36537ab31b00f6a2c8a455e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffac84eaac97cbaa77d1adc85cb7ccd4ffae53d401e54121aef1789235dda6a
+oid sha256:c32d27d70ffbf1baca00df2feb354808d5cf048c65ef6a942fa8d997b9f702a8
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f50bcb282a535c8d60e0cd286b37ee0fb35f76262156b1484dc636b0a4dd7d
+oid sha256:9acb4bb3f272325115fb1e1ca543e5418b0ce7c8f1090e6957b7e3fd0ec598ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507bfe4270aab5b2aa070e93d9c3404af996914dd61586771e0cc504e5b0252c
+oid sha256:431c6c53bdba57f808cd9c2e6f738bda5a26247416d68b6f96cb4f3eef6f54ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04044489383215369,
+  "epoch": 0.044489383215369056,
   "eval_steps": 13,
-  "global_step": 130,
+  "global_step": 143,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -396,6 +396,42 @@
       "eval_samples_per_second": 13.88,
       "eval_steps_per_second": 1.736,
       "step": 130
+    },
+    {
+      "epoch": 0.04106712296803298,
+      "grad_norm": 1.2261285781860352,
+      "learning_rate": 2.0118056862137357e-06,
+      "loss": 1.5202,
+      "step": 132
+    },
+    {
+      "epoch": 0.04200046667185191,
+      "grad_norm": 1.3027156591415405,
+      "learning_rate": 1.4029167422908107e-06,
+      "loss": 1.5151,
+      "step": 135
+    },
+    {
+      "epoch": 0.04293381037567084,
+      "grad_norm": 1.1372510194778442,
+      "learning_rate": 9.009284826036691e-07,
+      "loss": 1.5352,
+      "step": 138
+    },
+    {
+      "epoch": 0.043867154079489774,
+      "grad_norm": 1.248124122619629,
+      "learning_rate": 5.08115039419113e-07,
+      "loss": 1.5216,
+      "step": 141
+    },
+    {
+      "epoch": 0.044489383215369056,
+      "eval_loss": 1.4776010513305664,
+      "eval_runtime": 389.8727,
+      "eval_samples_per_second": 13.887,
+      "eval_steps_per_second": 1.736,
+      "step": 143
     }
   ],
   "logging_steps": 3,
@@ -415,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9289069372571648e+17,
+  "total_flos": 2.1217976309828813e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null