Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df3189200d2a19afd6bf65e1b7abee07cc56a66a3605f3e697d63af3c3d6a814
+oid sha256:ef352b3755cd2c3514a70e0f1913121f3c90f77b381ac85eeb778430e7a0492f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c4b751dac4de342f4aba0e1bf7d18453a9fe7ff26a6340f73105e47974449c
+oid sha256:255220845625b8a532eac68bcefb4bfe60d87d73a6ff5f76ef1a4f52d1f270d8
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc6c5ef268f1183211150fcad03d95bec24795d013490d0fe87a02db0afe595
+oid sha256:624617eb67c5ae66a26f74399b042214fe4beaf1a0d11ffcede0e4228de76c62
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d8ec93266e4bc8a64331da6b277e98dfae3d3d4bab70d66d65fad27bc26c8c
+oid sha256:0af27ed5b5e5c3013f1da7a97e494138e751399ceff1f8e7486b6e269bc7092f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00436316971446904,
+  "epoch": 0.00872633942893808,
   "eval_steps": 17,
-  "global_step": 17,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,56 @@
       "eval_samples_per_second": 13.291,
       "eval_steps_per_second": 1.663,
       "step": 17
+    },
+    {
+      "epoch": 0.0046198267564966315,
+      "grad_norm": 0.3675502836704254,
+      "learning_rate": 9.956320346634876e-05,
+      "loss": 2.4945,
+      "step": 18
+    },
+    {
+      "epoch": 0.005389797882579404,
+      "grad_norm": 0.4536501169204712,
+      "learning_rate": 9.917525374361912e-05,
+      "loss": 2.5246,
+      "step": 21
+    },
+    {
+      "epoch": 0.006159769008662175,
+      "grad_norm": 0.39700689911842346,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 2.4664,
+      "step": 24
+    },
+    {
+      "epoch": 0.006929740134744947,
+      "grad_norm": 0.3603559732437134,
+      "learning_rate": 9.803768380684242e-05,
+      "loss": 2.4274,
+      "step": 27
+    },
+    {
+      "epoch": 0.007699711260827719,
+      "grad_norm": 0.368173211812973,
+      "learning_rate": 9.729086208503174e-05,
+      "loss": 2.4661,
+      "step": 30
+    },
+    {
+      "epoch": 0.00846968238691049,
+      "grad_norm": 0.35239627957344055,
+      "learning_rate": 9.642770192448536e-05,
+      "loss": 2.3349,
+      "step": 33
+    },
+    {
+      "epoch": 0.00872633942893808,
+      "eval_loss": 2.3943283557891846,
+      "eval_runtime": 493.7443,
+      "eval_samples_per_second": 13.292,
+      "eval_steps_per_second": 1.663,
+      "step": 34
     }
   ],
   "logging_steps": 3,
@@ -77,7 +127,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4391533604110336e+16,
+  "total_flos": 4.977191316514406e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null