Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2f4f179e39ab57283eb45b956f51fc538ae88828f13ae7ad366a4bd239001c
+oid sha256:7c4e9ad06bda0f1051506cc5e549dcf5fc9c7571b4e20abef164bf2e570e5ab8
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2260d881cb30b0a70d19b81020c483791b462d9f32e59030eb45a0458d51949d
+oid sha256:03e02d7389a9d974a9cc11d77b77f48bce8b2f039e0675ef37766472d16c3963
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e434457798f9692151fe018459b1bda48cd1e999a3dd276a4432fd1d9a599e
+oid sha256:89aa540b8c3fabbcd74d788f9d4a71f3d52d803910db8076339022610c2b0f1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06615776081424936,
+  "epoch": 0.09923664122137404,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 40.499,
       "eval_steps_per_second": 20.25,
       "step": 26
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "grad_norm": 1.0369246006011963,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.1151,
+      "step": 27
+    },
+    {
+      "epoch": 0.07124681933842239,
+      "grad_norm": 1.37936270236969,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.1626,
+      "step": 28
+    },
+    {
+      "epoch": 0.0737913486005089,
+      "grad_norm": 0.9308303594589233,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.1095,
+      "step": 29
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "grad_norm": 1.8044286966323853,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0947,
+      "step": 30
+    },
+    {
+      "epoch": 0.07888040712468193,
+      "grad_norm": 1.0868867635726929,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.2049,
+      "step": 31
+    },
+    {
+      "epoch": 0.08142493638676845,
+      "grad_norm": 2.401944875717163,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.2697,
+      "step": 32
+    },
+    {
+      "epoch": 0.08396946564885496,
+      "grad_norm": 1.6872973442077637,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.1731,
+      "step": 33
+    },
+    {
+      "epoch": 0.08651399491094147,
+      "grad_norm": 1.331525206565857,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.16,
+      "step": 34
+    },
+    {
+      "epoch": 0.089058524173028,
+      "grad_norm": 2.928229570388794,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.2078,
+      "step": 35
+    },
+    {
+      "epoch": 0.0916030534351145,
+      "grad_norm": 1.3831185102462769,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.0663,
+      "step": 36
+    },
+    {
+      "epoch": 0.09414758269720101,
+      "grad_norm": 1.482015609741211,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.1134,
+      "step": 37
+    },
+    {
+      "epoch": 0.09669211195928754,
+      "grad_norm": 1.5263253450393677,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.1705,
+      "step": 38
+    },
+    {
+      "epoch": 0.09923664122137404,
+      "grad_norm": 1.535754680633545,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.1579,
+      "step": 39
+    },
+    {
+      "epoch": 0.09923664122137404,
+      "eval_loss": 0.16544334590435028,
+      "eval_runtime": 4.1198,
+      "eval_samples_per_second": 40.293,
+      "eval_steps_per_second": 20.147,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1300253059842048.0,
+  "total_flos": 1950379589763072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null