Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da4128d3003d685b3f97b23d6b2cda336a5e534c2cdee68424c05163a2706b7
+oid sha256:5f4588b774dceef1e19bee5dbd70dd6037aeb699f2b3e4222ff18c7641100068
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e7c7294f04e84cda276b521b27c4e27b0e4d9879c90726dd7a9db6e21ca7f1
+oid sha256:ffa1a9910a429b5bfd12e002d8ca0eceafa901f58ebe63c0d5a429c26257844f
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4479d8612262ecedc656e3fb719b965a26864f43306d791dee922d685b13b6f5
+oid sha256:e557af93914c894de252ad5739c858bc8be67dba19068d91502dd049001e333e
 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": 0.0014161605708216455,
+  "epoch": 0.002832321141643291,
   "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": 26.321,
       "eval_steps_per_second": 13.161,
       "step": 10
+    },
+    {
+      "epoch": 0.0016340314278711294,
+      "grad_norm": 1.9587860107421875,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.1211,
+      "step": 15
+    },
+    {
+      "epoch": 0.002178708570494839,
+      "grad_norm": 3.960905075073242,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.1157,
+      "step": 20
+    },
+    {
+      "epoch": 0.002178708570494839,
+      "eval_loss": 3.9367244243621826,
+      "eval_runtime": 147.1567,
+      "eval_samples_per_second": 26.271,
+      "eval_steps_per_second": 13.136,
+      "step": 20
+    },
+    {
+      "epoch": 0.002723385713118549,
+      "grad_norm": 2.2079458236694336,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 3.8274,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1066063264481280.0,
+  "total_flos": 2132126528962560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null