Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289e32236655fc4bca30f2d52cd58d22e2ff1a45ed62126779a824dc67e8f512
+oid sha256:7a6ed06695c4db14bd59e5c8aeb68e38ef6848f2dc1af659b300cd8b57c36e4c
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219d3eff955c6afa4d0d39f1ce8af3f8174f491576ba0bc4cea030307728a4c9
+oid sha256:502d9aa237ca4474d20271d7fb45b1569aa15624cabe8abc86de78b4de3df594
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a9774053c8dab88194dff5bf837d20f8496859adb946d9d42d2f3a497c9e15
+oid sha256:46d6d20de2aca44cf7cdb6eb2a7b0945d14233d0b35daf6c1772715fc68cd541
 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": 0.005621530461668189,
+  "epoch": 0.008432295692502284,
   "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": 12.292,
       "eval_steps_per_second": 6.146,
       "step": 100
+    },
+    {
+      "epoch": 0.006183683507835008,
+      "grad_norm": 0.3181847929954529,
+      "learning_rate": 0.0002,
+      "loss": 0.3241,
+      "step": 110
+    },
+    {
+      "epoch": 0.006745836554001827,
+      "grad_norm": 0.42424142360687256,
+      "learning_rate": 0.0002,
+      "loss": 0.2953,
+      "step": 120
+    },
+    {
+      "epoch": 0.007307989600168646,
+      "grad_norm": 0.4498586058616638,
+      "learning_rate": 0.0002,
+      "loss": 0.3619,
+      "step": 130
+    },
+    {
+      "epoch": 0.007870142646335464,
+      "grad_norm": 0.35849127173423767,
+      "learning_rate": 0.0002,
+      "loss": 0.3218,
+      "step": 140
+    },
+    {
+      "epoch": 0.008432295692502284,
+      "grad_norm": 0.38611167669296265,
+      "learning_rate": 0.0002,
+      "loss": 0.3287,
+      "step": 150
+    },
+    {
+      "epoch": 0.008432295692502284,
+      "eval_loss": 0.31369704008102417,
+      "eval_runtime": 609.316,
+      "eval_samples_per_second": 12.292,
+      "eval_steps_per_second": 6.146,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.417235372847923e+16,
+  "total_flos": 5.14124601140183e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null