Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6fb9b08c2e10e053f3d81ad8d2e0e24099462e2b5a2472f9154ee3481f0255
+oid sha256:30d12559217c7f23d41501f47dca546b26251a84fd89ee55f980fc13aa93f12b
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760dba386ee4560fcbe21cb431d3d8086e73cb0d13b223b37fde2ea0eec443fa
+oid sha256:b2fa88fe8784ca0c128965c9ad8a5a8e29ef38b586f101c90b586476e3ed4558
 size 51613348

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d87bc4656c379289d41186281c9cbad1876e328c641d66e6bd6c9c084caea09
+oid sha256:ac024c06a7fafa2800668c036cb57c23ab71073198d0a72d5ca171de9c65f87b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200db5d515f7fe0d1c4e0bac456fe6b9042173a9f2b890836ad8c5bd6dfb4d2e
+oid sha256:5d6789ad2e7141c857db1a1b89c580a274f669224bfc6f48fb1745262d15c182
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012583798359612,
+  "epoch": 0.018875697539418,
   "eval_steps": 42,
-  "global_step": 84,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,112 @@
       "eval_samples_per_second": 35.94,
       "eval_steps_per_second": 4.495,
       "step": 84
+    },
+    {
+      "epoch": 0.013033219729598143,
+      "grad_norm": 0.12993893027305603,
+      "learning_rate": 4.701488829641845e-05,
+      "loss": 1.1313,
+      "step": 87
+    },
+    {
+      "epoch": 0.013482641099584285,
+      "grad_norm": 0.18705669045448303,
+      "learning_rate": 4.678296760308474e-05,
+      "loss": 1.2752,
+      "step": 90
+    },
+    {
+      "epoch": 0.013932062469570428,
+      "grad_norm": 0.14135660231113434,
+      "learning_rate": 4.6542988418269876e-05,
+      "loss": 1.1628,
+      "step": 93
+    },
+    {
+      "epoch": 0.01438148383955657,
+      "grad_norm": 0.11707276850938797,
+      "learning_rate": 4.629503952098011e-05,
+      "loss": 1.0801,
+      "step": 96
+    },
+    {
+      "epoch": 0.014830905209542713,
+      "grad_norm": 0.14167702198028564,
+      "learning_rate": 4.6039212638573833e-05,
+      "loss": 1.0452,
+      "step": 99
+    },
+    {
+      "epoch": 0.015280326579528856,
+      "grad_norm": 0.15983764827251434,
+      "learning_rate": 4.5775602412827604e-05,
+      "loss": 1.1844,
+      "step": 102
+    },
+    {
+      "epoch": 0.015729747949515,
+      "grad_norm": 0.12750358879566193,
+      "learning_rate": 4.55043063649239e-05,
+      "loss": 1.0877,
+      "step": 105
+    },
+    {
+      "epoch": 0.01617916931950114,
+      "grad_norm": 0.1487520933151245,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.1373,
+      "step": 108
+    },
+    {
+      "epoch": 0.016628590689487285,
+      "grad_norm": 0.16089919209480286,
+      "learning_rate": 4.493906106688712e-05,
+      "loss": 1.1806,
+      "step": 111
+    },
+    {
+      "epoch": 0.017078012059473426,
+      "grad_norm": 0.158865287899971,
+      "learning_rate": 4.4645320926206064e-05,
+      "loss": 1.0689,
+      "step": 114
+    },
+    {
+      "epoch": 0.01752743342945957,
+      "grad_norm": 0.16464003920555115,
+      "learning_rate": 4.434431310491267e-05,
+      "loss": 1.1319,
+      "step": 117
+    },
+    {
+      "epoch": 0.017976854799445715,
+      "grad_norm": 0.12468679249286652,
+      "learning_rate": 4.4036148959228365e-05,
+      "loss": 1.0237,
+      "step": 120
+    },
+    {
+      "epoch": 0.018426276169431856,
+      "grad_norm": 0.14475342631340027,
+      "learning_rate": 4.372094249281821e-05,
+      "loss": 1.1352,
+      "step": 123
+    },
+    {
+      "epoch": 0.018875697539418,
+      "grad_norm": 0.1386341154575348,
+      "learning_rate": 4.3398810314615876e-05,
+      "loss": 1.177,
+      "step": 126
+    },
+    {
+      "epoch": 0.018875697539418,
+      "eval_loss": 1.1068843603134155,
+      "eval_runtime": 312.5635,
+      "eval_samples_per_second": 35.97,
+      "eval_steps_per_second": 4.498,
+      "step": 126
     }
   ],
   "logging_steps": 3,
@@ -246,7 +352,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.765900651220173e+16,
+  "total_flos": 4.03686064914432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null