Training in progress, step 143, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9392dfab3d55e54ea39ae535f1f81a34b93b857d22a4f10c329993c296ccf616
+oid sha256:e3dfed9da18e2a0aa5724586b2dca86c36772ef0e1b9e4cacf4f858c70fab168
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d3cf151841a29458afd940f20d3704dadaddb2839c5d166123ccbe83bc2b8a
+oid sha256:2f47773a51c10f9eeab921f21cb6cd939742832f0dccc571871750f5f76b2f68
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa306a615f19cdf4bbc036ac17f0d0affdd165e969573fa03d457dc23dc7e21
+oid sha256:43feb5d67a9fc661e502a4768b53cb9f5ceea2499482a7743fa63ddedb8e8aca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
+oid sha256:a71f60f9bd2ac4332e4682c06bcf0e8b6f23e0f17b0fa94d84f1fe3045e8b4a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3636363636363638,
+  "epoch": 2.6,
   "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": 9.96,
       "eval_steps_per_second": 1.285,
       "step": 130
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.3828240931034088,
+      "learning_rate": 4.023611372427471e-06,
+      "loss": 0.0376,
+      "step": 132
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.315852552652359,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.0392,
+      "step": 135
+    },
+    {
+      "epoch": 2.509090909090909,
+      "grad_norm": 0.43011197447776794,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 0.0369,
+      "step": 138
+    },
+    {
+      "epoch": 2.5636363636363635,
+      "grad_norm": 0.5211729407310486,
+      "learning_rate": 1.016230078838226e-06,
+      "loss": 0.0382,
+      "step": 141
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 0.13515090942382812,
+      "eval_runtime": 9.3396,
+      "eval_samples_per_second": 9.958,
+      "eval_steps_per_second": 1.285,
+      "step": 143
     }
   ],
   "logging_steps": 3,
@@ -415,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9142596699396506e+17,
+  "total_flos": 3.234818805423145e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null