Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1ae13269ddf7f71f6356aee336d5093372f1b6b10e039f0757fef9d8057adc
+oid sha256:773667611f802cea981e49bac6800d8a739277103b0d4b59212eb8eb74ce967f
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6f402be61c4ac432a89c0a9963a9c6df1dbe725e23acb6026e83909b31bef8
+oid sha256:003174572d3615dfae4b2c99effa0e176e89ce1c8cae243fc24064abc63b74f9
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ede76b9f6448762826ce5e6645debde67b7950ad1159a6b865843eae1ffe0cd
+oid sha256:f7d4f58351c2eca4a86344893b1042e13cd813a6550f3b9eb6d3acdc66549a9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab098d97568c94b26c087e3ff4fd649c3aaa775049e6dbf18e927dde2c5feee8
+oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001859773107680863,
+  "epoch": 0.003719546215361726,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 0.0001,
       "loss": 42.2976,
       "step": 5
+    },
+    {
+      "epoch": 0.0022317277292170355,
+      "grad_norm": 37.700042724609375,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 42.5346,
+      "step": 6
+    },
+    {
+      "epoch": 0.0022317277292170355,
+      "eval_loss": 10.256876945495605,
+      "eval_runtime": 138.1284,
+      "eval_samples_per_second": 8.195,
+      "eval_steps_per_second": 4.098,
+      "step": 6
+    },
+    {
+      "epoch": 0.002603682350753208,
+      "grad_norm": 46.39228057861328,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 39.644,
+      "step": 7
+    },
+    {
+      "epoch": 0.0029756369722893808,
+      "grad_norm": 47.501041412353516,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 35.7466,
+      "step": 8
+    },
+    {
+      "epoch": 0.0029756369722893808,
+      "eval_loss": 7.803372859954834,
+      "eval_runtime": 138.0673,
+      "eval_samples_per_second": 8.199,
+      "eval_steps_per_second": 4.099,
+      "step": 8
+    },
+    {
+      "epoch": 0.0033475915938255534,
+      "grad_norm": 45.90718460083008,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 31.2201,
+      "step": 9
+    },
+    {
+      "epoch": 0.003719546215361726,
+      "grad_norm": 51.53364181518555,
+      "learning_rate": 5e-05,
+      "loss": 23.9333,
+      "step": 10
+    },
+    {
+      "epoch": 0.003719546215361726,
+      "eval_loss": 5.604811191558838,
+      "eval_runtime": 138.2369,
+      "eval_samples_per_second": 8.189,
+      "eval_steps_per_second": 4.094,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -85,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166204172697600.0,
+  "total_flos": 6332408345395200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null