Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a61236ce200669c1f43fef349d35dcf3a9c02bf0598fab22dd9da1fd4bd4b3
+oid sha256:784cc2101a6d62c9decede3bd0dcc8f52ec5491dcf2bf06b8a781a4a8aa641f1
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a7f83ba2f8b0e4f007030bee96afe30b58611014891556a689b19bb6b078fc
+oid sha256:f43bec2e7f9bfda48b7faeef54be25f055dab11e39ae17ff9504acfa23c324ba
 size 7825914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151ef2fb6ef7aa1e3d2aba168bc9d53da4ff0613d78aa9606d4f7a2c87414876
+oid sha256:88995ee240ca79abe67b4b9085089095ff68a1140c207890ec746917e6a28ebd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00904977375565611,
+  "epoch": 0.027149321266968326,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,64 @@
       "eval_samples_per_second": 149.898,
       "eval_steps_per_second": 18.793,
       "step": 9
+    },
+    {
+      "epoch": 0.012066365007541479,
+      "grad_norm": 4.279703617095947,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 10.4367,
+      "step": 12
+    },
+    {
+      "epoch": 0.015082956259426848,
+      "grad_norm": 5.507565021514893,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 10.1176,
+      "step": 15
+    },
+    {
+      "epoch": 0.01809954751131222,
+      "grad_norm": 6.325550079345703,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 9.7615,
+      "step": 18
+    },
+    {
+      "epoch": 0.01809954751131222,
+      "eval_loss": 9.461087226867676,
+      "eval_runtime": 11.1633,
+      "eval_samples_per_second": 150.045,
+      "eval_steps_per_second": 18.812,
+      "step": 18
+    },
+    {
+      "epoch": 0.021116138763197588,
+      "grad_norm": 6.642955780029297,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 9.3199,
+      "step": 21
+    },
+    {
+      "epoch": 0.024132730015082957,
+      "grad_norm": 7.369113922119141,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 8.8135,
+      "step": 24
+    },
+    {
+      "epoch": 0.027149321266968326,
+      "grad_norm": 6.994415760040283,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 8.3456,
+      "step": 27
+    },
+    {
+      "epoch": 0.027149321266968326,
+      "eval_loss": 7.989864349365234,
+      "eval_runtime": 11.0595,
+      "eval_samples_per_second": 151.454,
+      "eval_steps_per_second": 18.988,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 771412331593728.0,
+  "total_flos": 2314236994781184.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null