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:b7c9869764170291efa94cf6ad98382e393a0b064553379900371fa1fff0c458
+oid sha256:46f48bd5216b098cfe2c17604e60900c2875caf68690f87a02c2e5e3e745dd56
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4627b59c60f1fded5fe176b93c24c8f5695b0fa3d8802cd79caf83c40029f746
+oid sha256:99cd1f0da7ae31cb8cfb3d96cb082d28bd4e3bb6366c0022f7371c67c630ddc1
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe37c63407c48ce0ffbbc94d79ed9526d3b7ca8181724c47a814334b799d5ac
+oid sha256:f4d8d8ebcb46d94260f53b4b9a201e9e40c1f599536d1ebd047721586dc3451b
 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": 0.0462942354774093,
+  "epoch": 0.0925884709548186,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 4.263,
       "eval_steps_per_second": 2.136,
       "step": 13
+    },
+    {
+      "epoch": 0.049855330514133094,
+      "grad_norm": 2.924900770187378,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.3642,
+      "step": 14
+    },
+    {
+      "epoch": 0.05341642555085689,
+      "grad_norm": 1.9190605878829956,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.245,
+      "step": 15
+    },
+    {
+      "epoch": 0.05697752058758068,
+      "grad_norm": 4.164839744567871,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 2.4275,
+      "step": 16
+    },
+    {
+      "epoch": 0.06053861562430447,
+      "grad_norm": 3.0086185932159424,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 2.5735,
+      "step": 17
+    },
+    {
+      "epoch": 0.06409971066102826,
+      "grad_norm": 2.273061513900757,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.2379,
+      "step": 18
+    },
+    {
+      "epoch": 0.06766080569775205,
+      "grad_norm": 1.9004080295562744,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 2.3375,
+      "step": 19
+    },
+    {
+      "epoch": 0.07122190073447585,
+      "grad_norm": 2.002903461456299,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.2203,
+      "step": 20
+    },
+    {
+      "epoch": 0.07478299577119965,
+      "grad_norm": 1.6309473514556885,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.1511,
+      "step": 21
+    },
+    {
+      "epoch": 0.07834409080792344,
+      "grad_norm": 1.8154593706130981,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.0112,
+      "step": 22
+    },
+    {
+      "epoch": 0.08190518584464723,
+      "grad_norm": 1.8795080184936523,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 1.8034,
+      "step": 23
+    },
+    {
+      "epoch": 0.08546628088137102,
+      "grad_norm": 1.9428141117095947,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.9395,
+      "step": 24
+    },
+    {
+      "epoch": 0.08902737591809481,
+      "grad_norm": 1.6623902320861816,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.1667,
+      "step": 25
+    },
+    {
+      "epoch": 0.0925884709548186,
+      "grad_norm": 1.343985915184021,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.2539,
+      "step": 26
+    },
+    {
+      "epoch": 0.0925884709548186,
+      "eval_loss": 2.0758728981018066,
+      "eval_runtime": 110.911,
+      "eval_samples_per_second": 4.265,
+      "eval_steps_per_second": 2.137,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3232883225329664e+17,
+  "total_flos": 2.6465766450659328e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null