Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0ecae96ceb987f0cfcecca077bd7ced8ef2bffa5c611b9552e2c331eea5516
+oid sha256:e36740ee494ac54caf06e7fd05ef351a11ed88492d53fdf19688921e9678a26b
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7970349a3d1ed493d1e316ef83961aa84559f07031d13c45ed596c05c83f2d0b
+oid sha256:b59c23068d4df3753cc74f8a347c5a4cd0260d3d8b84f61649355b1d1a1485c1
 size 25859156

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a41f70d43da4cecfbb7fcd01e7f7d6add4e349094ae87aeff5fcdc2178f739d
+oid sha256:8d6bd60281b305485221edf25562b2ccf279558c0ad3bc6188c472d7a6c91b4c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25c68945f3602a4a6ec635e5d5d75e121f2ea5001f8dc93e464695aefe008a9
+oid sha256:93276b798fb2abdf2e68a63204630a20a83a12a517e968355979b9b85b457e3b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1037d3b61683ee2b6cedb1bdd15d984c065bdfca91502ce6838a166ff7b42475
+oid sha256:b85362b5c3b8aa8b1d497c1686af1d1912c8e0dbdf59704e753d14829f93ee5f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf36d22396e084fba8f912b6d042645ea28a9e4ea8114a33effa6c6efa40410d
+oid sha256:acbf90b44f1e9085f310209cd01b0324482a4f0bf51e1623dff812b0f43c42e9
 size 15024

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": 0.09437386569872959,
+  "epoch": 0.18874773139745918,
   "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": 106.407,
       "eval_steps_per_second": 13.301,
       "step": 10
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "grad_norm": 6.565160751342773,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 5.5041,
+      "step": 15
+    },
+    {
+      "epoch": 0.14519056261343014,
+      "grad_norm": 3.8733808994293213,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.5637,
+      "step": 20
+    },
+    {
+      "epoch": 0.14519056261343014,
+      "eval_loss": 1.0715842247009277,
+      "eval_runtime": 2.1777,
+      "eval_samples_per_second": 106.537,
+      "eval_steps_per_second": 13.317,
+      "step": 20
+    },
+    {
+      "epoch": 0.18148820326678766,
+      "grad_norm": 2.763819456100464,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.3577,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4933999508062208.0,
+  "total_flos": 9936845429276672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null