Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596da61471f7acd22dfed810279a826afb7b67f26080e0055da80a685e50ae03
+oid sha256:ff0260d1e3631bfaf3aad882c37dfe986418a9da16b6a4e18e4aa30e93aa2502
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a70f332281dffbc44dd442c0eb6fba71dece1c53fc85584adbaed85acee7fe1
+oid sha256:5661af4bb46bd4690466f1c6547cb2605855d735bc15f0f625b75eddd477b21b
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72223fd40b61c72a4df43aea9c90ca091d8f4c0b5e6bb74b51346988ac0956d2
+oid sha256:0c9d6305112455934908c7bfd9606d4794d06684c6273dfde936a82028d5a005
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cedaf8893734b19717a3bbbc716629d55965a18bdde504cf46d9182fcb60eb14
+oid sha256:666e3907648b0318630be4f0e9270d7d902986930986134493537abd333e959c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014670823399963322,
+  "epoch": 0.017115960633290545,
   "eval_steps": 34,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -225,6 +225,49 @@
       "learning_rate": 0.0002,
       "loss": 10.644,
       "step": 30
+    },
+    {
+      "epoch": 0.015159850846628768,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019998292504580528,
+      "loss": 8.4753,
+      "step": 31
+    },
+    {
+      "epoch": 0.01564887829329421,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001999317060143023,
+      "loss": 9.0983,
+      "step": 32
+    },
+    {
+      "epoch": 0.016137905739959654,
+      "grad_norm": 1.1584913556352532e+18,
+      "learning_rate": 0.0001998463603967434,
+      "loss": 7.7383,
+      "step": 33
+    },
+    {
+      "epoch": 0.0166269331866251,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019972691733857883,
+      "loss": 9.1453,
+      "step": 34
+    },
+    {
+      "epoch": 0.0166269331866251,
+      "eval_loss": 9.285249710083008,
+      "eval_runtime": 881.9276,
+      "eval_samples_per_second": 2.929,
+      "eval_steps_per_second": 0.976,
+      "step": 34
+    },
+    {
+      "epoch": 0.017115960633290545,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019957341762950344,
+      "loss": 10.3859,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -244,7 +287,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.613439027871744e+16,
+  "total_flos": 7.715678865850368e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null