Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0421aa29105f02d352b3e31dec1837b8b4c6b078120ab76e42ec9cf8461c1663
+oid sha256:7b640a13586a8ddaf8af206ceb427b23824056b8e5ac8f6466ee4942daea4a9d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46462f547f758d2c2c12bf486d24e294ac00c4663f542674bb46aec4385a2083
+oid sha256:f3e7d193b2ea8d745bf561d24fdf24f1260fdc96256c3c498b8b27226fe06be1
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
+oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005700583631181287,
+  "epoch": 0.006514952721350043,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 12.93,
       "eval_steps_per_second": 1.616,
       "step": 63
+    },
+    {
+      "epoch": 0.005972039994570873,
+      "grad_norm": 1.9437718391418457,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.5445,
+      "step": 66
+    },
+    {
+      "epoch": 0.006243496357960458,
+      "grad_norm": 1.3337701559066772,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.4558,
+      "step": 69
+    },
+    {
+      "epoch": 0.006514952721350043,
+      "grad_norm": 2.283390998840332,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.5451,
+      "step": 72
+    },
+    {
+      "epoch": 0.006514952721350043,
+      "eval_loss": 0.4924093782901764,
+      "eval_runtime": 1439.0551,
+      "eval_samples_per_second": 12.934,
+      "eval_steps_per_second": 1.617,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.098385168531456e+16,
+  "total_flos": 1.0398154478321664e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null