Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c93d9cd9e775cc2106eac30f9f059b47d89028cf3736ceb33e28dc36cdcfde8
+oid sha256:bdf831601c76e03dd1febe077efcf2102051a597a16a337d9ff906654112ac38
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fb8b294e60cd01b4b37b31540390fd9be8f620140341dd4be381358c042275
+oid sha256:fdf25ae2652a2cb16923b0abd7b2c17bae6f9571b9ae6041dc6d0e3443de71ac
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2025cb03a4684a108557f8f3a9ba171c77f481d43f222713f2ffc50638e98395
+oid sha256:436b3ae1600b35e58c15b8d4e7a27b57fd3a761313e5a31cd36c608b15ad7bfd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035182679296346414,
+  "epoch": 0.07036535859269283,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 20.588,
       "eval_steps_per_second": 10.294,
       "step": 10
+    },
+    {
+      "epoch": 0.04059539918809202,
+      "grad_norm": 0.4265204966068268,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.3519,
+      "step": 15
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 0.5590308904647827,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.4073,
+      "step": 20
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "eval_loss": 1.296107530593872,
+      "eval_runtime": 7.5375,
+      "eval_samples_per_second": 20.696,
+      "eval_steps_per_second": 10.348,
+      "step": 20
+    },
+    {
+      "epoch": 0.06765899864682003,
+      "grad_norm": 0.48316705226898193,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2226,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1476087596974080.0,
+  "total_flos": 2849669110824960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null