Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab77eb416bace56c13beb3a8a21df1739be662a3102d27ce20434f9345664f5
+oid sha256:0840ae54eb4a52410d7d99f849c22d7a70f74a04784a6fb21af91e17dd857204
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c716351e5a57659df6560287d8cbddb07137316c8ac19a38eadfd87d82392f7
+oid sha256:8065568e42b1fef2598f8589683ef709884bb9e395953e510357a4dd96c43d29
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6758c94dff08e90104766708e33ff8cbf1018bfc9134136ef3e1f7d88a92f7
+oid sha256:9f823b57963be51e31620f99c418f4a772969cb6e0504382964ebddd1b207eaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06279069767441861,
+  "epoch": 0.08372093023255814,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 69.514,
       "eval_steps_per_second": 8.737,
       "step": 27
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 1.417418360710144,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 4.9417,
+      "step": 30
+    },
+    {
+      "epoch": 0.07674418604651163,
+      "grad_norm": 1.4718533754348755,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 4.5364,
+      "step": 33
+    },
+    {
+      "epoch": 0.08372093023255814,
+      "grad_norm": 1.4996187686920166,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 4.6917,
+      "step": 36
+    },
+    {
+      "epoch": 0.08372093023255814,
+      "eval_loss": 4.580844402313232,
+      "eval_runtime": 10.4483,
+      "eval_samples_per_second": 69.294,
+      "eval_steps_per_second": 8.71,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1693262398095360.0,
+  "total_flos": 2257683197460480.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null