Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f94d6ee6a536e6bb1c74a65e2d88a5ab8f64600b321da41b02769e75e6d2e7
+oid sha256:1d11b80c0dde1dea2cf47b80ddc689f6bfdb7586e9a0cbb126a8fc11c7d8b459
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e9b339947332191311c8064806e2e9afc2fb7a52ff91184dba06de689eb701b
+oid sha256:0f627f4c1fec6290836e3af3fa01aa893dff15b244706d1f925def080de7ac6a
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f87458b56b81341706d06a4ede04bec93a0e13eb8ba6069748b3bb4cddc346b
+oid sha256:53096b7b975e8fce7922c5448a91ed2f4ff5fa0388f5ac5c6e7d67e4278aeafd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016424510423247,
+  "epoch": 0.032849020846494,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 8.07,
       "eval_steps_per_second": 4.035,
       "step": 10
+    },
+    {
+      "epoch": 0.018951358180669616,
+      "grad_norm": 0.6154476404190063,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.6647,
+      "step": 15
+    },
+    {
+      "epoch": 0.025268477574226154,
+      "grad_norm": 0.5439320802688599,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6373,
+      "step": 20
+    },
+    {
+      "epoch": 0.025268477574226154,
+      "eval_loss": 0.5970596075057983,
+      "eval_runtime": 41.5592,
+      "eval_samples_per_second": 8.037,
+      "eval_steps_per_second": 4.018,
+      "step": 20
+    },
+    {
+      "epoch": 0.03158559696778269,
+      "grad_norm": 0.4888911545276642,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.5915,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4210375092338688.0,
+  "total_flos": 8420750184677376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null