Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ffe6dfd3fda6166569dca8fd4206441fab84382574468a7d016dfff75a13ffa
+oid sha256:bed6dbe9a463afbdaa420d23f53fbeefe0bd5abe4bae29fe559d3f9cb28b9eab
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ee0a22e7754951c6a5e53b9f0e7234ea3abf0eac9e4ec5d3f4d7f0044a86a5
+oid sha256:bbed3428b24e1c58e48c953eaea8913eb17ef0ed962516d13f3ea9bf5fa5c0c7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a782246aff15a3409595f4a10bd4fc20fe0486446db75db049245365ae75220e
+oid sha256:15a65fb9fd056a32de3901e991c48a566cc7007cf9d229006a3b1a882eda11f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1088139281828074,
+  "epoch": 0.1632208922742111,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 15.949,
       "eval_steps_per_second": 7.995,
       "step": 100
+    },
+    {
+      "epoch": 0.11969532100108814,
+      "grad_norm": 1.7176902294158936,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.4559,
+      "step": 110
+    },
+    {
+      "epoch": 0.1305767138193689,
+      "grad_norm": 0.39822494983673096,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.4364,
+      "step": 120
+    },
+    {
+      "epoch": 0.14145810663764963,
+      "grad_norm": 0.42606645822525024,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.3936,
+      "step": 130
+    },
+    {
+      "epoch": 0.15233949945593037,
+      "grad_norm": 0.992786169052124,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.4474,
+      "step": 140
+    },
+    {
+      "epoch": 0.1632208922742111,
+      "grad_norm": 0.35880205035209656,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.3639,
+      "step": 150
+    },
+    {
+      "epoch": 0.1632208922742111,
+      "eval_loss": 0.09264663606882095,
+      "eval_runtime": 24.2837,
+      "eval_samples_per_second": 15.937,
+      "eval_steps_per_second": 7.989,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.017257970879693e+16,
+  "total_flos": 4.511635400451686e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null