Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d2c0309b324d037b5a686d7a64b2430f21fe223373c3b1eb0d5fb1f8dbd10d
+oid sha256:5f6cefef2854151810b9c13a0cb0bf5a7c35afd5832abec0244aa468d9fecdf9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318c6f458beec31ed88d4bcfecb3900e94fea2aed49466c58546677e4e12e76e
+oid sha256:b06aa655fc8b7ba16903685b5832a5f9180dc01eeb97927dd5b064e23a1408cb
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f539dc9a6a8b7e3c2df4050a60d03c6feb3292b4a9f73e4e9fc1949690e3447
+oid sha256:75b7fe1ed9d1a988cf26f4ac07eea6ab570c3b37f92d1c4968cd69d6c61bd803
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f61563dfd2fa9a4219ded9723a815e52adadf75f43ccf8a422170b094889e49
+oid sha256:b68eadda5190f74fabbe61c66b0c0f1ecff37d5b9533c9627db38134274ac084
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011629033821106696,
+  "epoch": 0.002325806764221339,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 5.966,
       "eval_steps_per_second": 2.986,
       "step": 3
+    },
+    {
+      "epoch": 0.0015505378428142262,
+      "grad_norm": 17.527694702148438,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 10.9965,
+      "step": 4
+    },
+    {
+      "epoch": 0.0019381723035177827,
+      "grad_norm": 26.354629516601562,
+      "learning_rate": 0.00015,
+      "loss": 10.721,
+      "step": 5
+    },
+    {
+      "epoch": 0.002325806764221339,
+      "grad_norm": 19.539798736572266,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 6.8754,
+      "step": 6
+    },
+    {
+      "epoch": 0.002325806764221339,
+      "eval_loss": 4.309875965118408,
+      "eval_runtime": 182.3056,
+      "eval_samples_per_second": 5.963,
+      "eval_steps_per_second": 2.984,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 8902647402725376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null