Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da49b855905db2954a556398d8abe6018ac3f89517408fa049ead3b583da777
+oid sha256:0a6dacd18351efc0ce0ee8d61da0755d63fd5e468bf9dcd5c8e87dd92d211050
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892bfe0cbd4455128e7afeb5dffb7df7d38c1b2a968dfe39e535807739120706
+oid sha256:c50db2c681c1867d6d959aa06062a4a36aad7fe7926d4605a1d84e2eaf45381a
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fccdc03a844878ba63ee9f4845c57b9adeb23476365b7cddbc0a55ab3354f1f
+oid sha256:1c0d77bcd56d96825c5ef028b2dd99ac2e61994d3c453c8d2883da32a92047be
 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": 0.0018444948921679909,
+  "epoch": 0.0036889897843359817,
   "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": 34.448,
       "eval_steps_per_second": 17.224,
       "step": 10
+    },
+    {
+      "epoch": 0.0021282633371169125,
+      "grad_norm": 0.6280760765075684,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.7719,
+      "step": 15
+    },
+    {
+      "epoch": 0.0028376844494892167,
+      "grad_norm": 1.1123079061508179,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.7106,
+      "step": 20
+    },
+    {
+      "epoch": 0.0028376844494892167,
+      "eval_loss": 0.6546657085418701,
+      "eval_runtime": 85.8004,
+      "eval_samples_per_second": 34.592,
+      "eval_steps_per_second": 17.296,
+      "step": 20
+    },
+    {
+      "epoch": 0.003547105561861521,
+      "grad_norm": 0.8203548192977905,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6668,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 336763721613312.0,
+  "total_flos": 697581994770432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null