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:fb4201ec9a7c1bc8c5af293d397141621e28c62e220b7e7ef05288181ad37954
+oid sha256:ea75b6f915fe653d869d7bffd991f8b73e5fa69cf5112d03e9375b27cab2d882
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a801cd757d3f8b31b08fea4ae7606ecfbf75cd270daa0107e10b015ade5ecfa
+oid sha256:c522434e0d48d2883143159fe27d69323fbacf23e2284050dab5f35496013381
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47461d8050d7df2d5e65b413e12a632f46aa1979aeb8c23b643ca1c0ba4a828a
+oid sha256:c52f7c118f4f94493141b00ccc8987f28f12a1ed9f46dabc17a34ba6b70835b6
 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": 0.028291621327529923,
+  "epoch": 0.042437431991294884,
   "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": 18.647,
       "eval_steps_per_second": 9.347,
       "step": 26
+    },
+    {
+      "epoch": 0.029379760609358,
+      "grad_norm": 0.19251622259616852,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.1362,
+      "step": 27
+    },
+    {
+      "epoch": 0.030467899891186073,
+      "grad_norm": 0.18412667512893677,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.1466,
+      "step": 28
+    },
+    {
+      "epoch": 0.031556039173014146,
+      "grad_norm": 0.28334978222846985,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.2359,
+      "step": 29
+    },
+    {
+      "epoch": 0.03264417845484222,
+      "grad_norm": 0.22527562081813812,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1213,
+      "step": 30
+    },
+    {
+      "epoch": 0.03373231773667029,
+      "grad_norm": 0.31526511907577515,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.2167,
+      "step": 31
+    },
+    {
+      "epoch": 0.03482045701849837,
+      "grad_norm": 0.14839228987693787,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.1137,
+      "step": 32
+    },
+    {
+      "epoch": 0.035908596300326445,
+      "grad_norm": 0.208391934633255,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.1615,
+      "step": 33
+    },
+    {
+      "epoch": 0.036996735582154515,
+      "grad_norm": 0.1698072850704193,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.1691,
+      "step": 34
+    },
+    {
+      "epoch": 0.03808487486398259,
+      "grad_norm": 0.16231591999530792,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.1603,
+      "step": 35
+    },
+    {
+      "epoch": 0.03917301414581066,
+      "grad_norm": 0.16352759301662445,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.1365,
+      "step": 36
+    },
+    {
+      "epoch": 0.04026115342763874,
+      "grad_norm": 0.2394663244485855,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.2083,
+      "step": 37
+    },
+    {
+      "epoch": 0.041349292709466814,
+      "grad_norm": 0.2228260487318039,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.1766,
+      "step": 38
+    },
+    {
+      "epoch": 0.042437431991294884,
+      "grad_norm": 0.16056722402572632,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.1458,
+      "step": 39
+    },
+    {
+      "epoch": 0.042437431991294884,
+      "eval_loss": 0.18522028625011444,
+      "eval_runtime": 20.7477,
+      "eval_samples_per_second": 18.653,
+      "eval_steps_per_second": 9.35,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4059240891678720.0,
+  "total_flos": 6006856471019520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null