Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540695a3a9f43d9bbd1ef789d552460b8c74b46bd4fe758079e6157729c7e2ec
+oid sha256:611732e8b60b82f65ca3fb621af02d76e06289cda1042b9cb51448095f7f99f2
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7428b52cb33a82912bb70cd558b2213508ff4ab07a0f854523e513b35a9f53
+oid sha256:4b78fd360fd0837a0e24e78ff53bcb54596b905619d3f1795815dbe338f7fdc0
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a808482866d58c57fe0290015fc20e4f8b8939db7d59d8f55d0fcd2b8b4cf266
+oid sha256:bea3603c9a5ac93aadff8538e8c1f7b7097253fb14e88f0b33e0bdddfa5087f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e49a8262b2a61d3153e5d379c20cfb08094371d950647117ad67ae4b87231f
+oid sha256:87bd97bc98e39f7007b5f2750d097c7395ce4bde9cd90085b1ec2b6c643faaf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.75,
   "eval_steps": 24,
-  "global_step": 48,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 48.84,
       "eval_steps_per_second": 6.331,
       "step": 48
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 0.284551739692688,
+      "learning_rate": 4.736424735627193e-05,
+      "loss": 1.5701,
+      "step": 51
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.3086010813713074,
+      "learning_rate": 4.697267418712415e-05,
+      "loss": 1.5359,
+      "step": 54
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 0.31514284014701843,
+      "learning_rate": 4.655584912254727e-05,
+      "loss": 1.5334,
+      "step": 57
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.31487005949020386,
+      "learning_rate": 4.611425119494551e-05,
+      "loss": 1.5224,
+      "step": 60
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 0.36550524830818176,
+      "learning_rate": 4.564838790671e-05,
+      "loss": 1.5222,
+      "step": 63
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.29623621702194214,
+      "learning_rate": 4.515879464697629e-05,
+      "loss": 1.5206,
+      "step": 66
+    },
+    {
+      "epoch": 0.71875,
+      "grad_norm": 0.3229241967201233,
+      "learning_rate": 4.464603407633326e-05,
+      "loss": 1.5232,
+      "step": 69
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2879750728607178,
+      "learning_rate": 4.41106954801906e-05,
+      "loss": 1.5028,
+      "step": 72
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.493626594543457,
+      "eval_runtime": 3.3364,
+      "eval_samples_per_second": 48.555,
+      "eval_steps_per_second": 6.294,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.06657392623616e+16,
+  "total_flos": 1.6211923678789632e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null