Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7995363b558a42a00339bd402df4268108793d10725ed57d7a81675a49d660f1
+oid sha256:d4c11d5c1c990abf7d8314fea9f0075071fc70c09322b6aaf30e13704ffba818
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d73f3fe0852a477bafabb2531c67be967c1b8d9ddbe12bda372a577d6ba10b5
+oid sha256:0ca978b685fb676166bf8dc89b64f1e2d1105fc3bb42d39ad15826c823c369e2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955fc11d95973ad3e55aafab2e3c2f9e1ac3dd672ace2bf41cd1f3359c6778ae
+oid sha256:a701f637c15f3cdfd7666884f9cc5c15b42b346d8a6766fda320843e4c8da6b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0121558378411232,
+  "epoch": 0.0182337567616848,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 26.798,
       "eval_steps_per_second": 13.399,
       "step": 100
+    },
+    {
+      "epoch": 0.01337142162523552,
+      "grad_norm": 1.7065634727478027,
+      "learning_rate": 0.0002,
+      "loss": 9.0676,
+      "step": 110
+    },
+    {
+      "epoch": 0.014587005409347839,
+      "grad_norm": 2.568800210952759,
+      "learning_rate": 0.0002,
+      "loss": 8.584,
+      "step": 120
+    },
+    {
+      "epoch": 0.01580258919346016,
+      "grad_norm": 2.7793874740600586,
+      "learning_rate": 0.0002,
+      "loss": 8.6535,
+      "step": 130
+    },
+    {
+      "epoch": 0.01701817297757248,
+      "grad_norm": 2.116802453994751,
+      "learning_rate": 0.0002,
+      "loss": 8.6239,
+      "step": 140
+    },
+    {
+      "epoch": 0.0182337567616848,
+      "grad_norm": 1.6645129919052124,
+      "learning_rate": 0.0002,
+      "loss": 8.5241,
+      "step": 150
+    },
+    {
+      "epoch": 0.0182337567616848,
+      "eval_loss": 2.1867380142211914,
+      "eval_runtime": 129.2587,
+      "eval_samples_per_second": 26.799,
+      "eval_steps_per_second": 13.399,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.873061628346368e+16,
+  "total_flos": 2.8014486963093504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null