Training in progress, step 52, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc84d6633e49926ea714145b651a406d61ebd7ad5561eff4d11de1ce0fecf93e
+oid sha256:b6edd74da50391d4fc5e07505d76d42499020416716e240c908786b1ae485cba
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d56e75e152e0644a94d2eea40fc20ec9bc18614589b796bfe9d3fd290b174c
+oid sha256:76b58e27905531bb921c4c1187368754f40781cdf1fe952949208c6067d3e472
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c7e644c47c62f5a31332d139d09f879e7b653da5cbc64fa55026f31d1123a9
+oid sha256:00568e605ceafffef2ed3ab927c41a9d69ed991c2bf18e3c9eabc53dd3833d46
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a358404286a5e4f3258996b41c418ca8149d7be647bd8b06e725c0e87267272
+oid sha256:b77b562cb3719c814c3e7999705d44634b14e0d87d91aa14ab1d432f7d2fd6c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04408024865781294,
+  "epoch": 0.05877366487708392,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 52,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -130,6 +130,42 @@
       "eval_samples_per_second": 6.628,
       "eval_steps_per_second": 0.832,
       "step": 39
+    },
+    {
+      "epoch": 0.04747103701610624,
+      "grad_norm": 1.2959660291671753,
+      "learning_rate": 4.382678665009028e-05,
+      "loss": 0.576,
+      "step": 42
+    },
+    {
+      "epoch": 0.050861825374399545,
+      "grad_norm": 1.1517972946166992,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.5597,
+      "step": 45
+    },
+    {
+      "epoch": 0.05425261373269285,
+      "grad_norm": 1.2231593132019043,
+      "learning_rate": 4.144846814849282e-05,
+      "loss": 0.5803,
+      "step": 48
+    },
+    {
+      "epoch": 0.05764340209098615,
+      "grad_norm": 1.1372201442718506,
+      "learning_rate": 4.01447510960205e-05,
+      "loss": 0.5299,
+      "step": 51
+    },
+    {
+      "epoch": 0.05877366487708392,
+      "eval_loss": 0.13713335990905762,
+      "eval_runtime": 224.8683,
+      "eval_samples_per_second": 6.626,
+      "eval_steps_per_second": 0.832,
+      "step": 52
     }
   ],
   "logging_steps": 3,
@@ -149,7 +185,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0968832742208307e+17,
+  "total_flos": 1.462511032294441e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null