Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5092df653a241c295e8a40fe8a5653dd9db368600a132fc9f1bacfdd9186d561
+oid sha256:eeb743d2fa9bf331d379631b7ef0b8c68e7774e97a71b38840d8975b5d99fc4a
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2697522f49692aec26ba5936d226adf0d45a6ceb6e239b4eab00ec454a7416c
+oid sha256:e07fbe7b1b0f4cd92cbd073a4e31b6a5e3a92d3e33cecc19de5d91d7616d06d3
 size 60387220

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c3cdbf034ef9f86029f99db82daec670863e67518e294d6fbac9a3fc658d9d
+oid sha256:4d9b92fa45e44153a07435b55d5d3d71bf302bfd9a3b3f027d29977fda525192
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601daa59fb095b2a4822edf3d826c0c91406d982679fa2815535f957a5251e5e
+oid sha256:efef9367937c87bc0bc848b4e2adc863b119783b8c6fd51e9157e257a682f5a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030676728633658508,
+  "epoch": 0.03374440149702436,
   "eval_steps": 20,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -382,6 +382,36 @@
       "eval_samples_per_second": 5.066,
       "eval_steps_per_second": 0.659,
       "step": 500
+    },
+    {
+      "epoch": 0.031903797779004844,
+      "grad_norm": 0.7919607162475586,
+      "learning_rate": 0.00019789331587989856,
+      "loss": 1.4158,
+      "step": 520
+    },
+    {
+      "epoch": 0.031903797779004844,
+      "eval_loss": 1.385123610496521,
+      "eval_runtime": 19.7083,
+      "eval_samples_per_second": 5.074,
+      "eval_steps_per_second": 0.66,
+      "step": 520
+    },
+    {
+      "epoch": 0.03313086692435119,
+      "grad_norm": 0.7193537354469299,
+      "learning_rate": 0.00019781150290436065,
+      "loss": 1.4829,
+      "step": 540
+    },
+    {
+      "epoch": 0.03313086692435119,
+      "eval_loss": 1.3717445135116577,
+      "eval_runtime": 19.7284,
+      "eval_samples_per_second": 5.069,
+      "eval_steps_per_second": 0.659,
+      "step": 540
     }
   ],
   "logging_steps": 20,
@@ -389,7 +419,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 3.228714037020672e+16,
+  "total_flos": 3.5324564332032e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null