Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af105525370eec15b17484216a97d4d9480e8f0820c925aeef92384a70380da
+oid sha256:2318934a559574d1d5ffe858353051e44e9a0f98bfcec895a212d5b83e23a6fb
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6bb36cb9ad15841030dda728d353affdde511cff8583c118ebf2d3000f7f488
+oid sha256:1a501e9af8031271f08e11252a83c842fc40ce0f1d5f2bc52866f5bb66073df0
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a040b3377ea29e2e573174f608927490657c8c978fdb95169126a63ddf2673b
+oid sha256:81d341293548ca00e0e58d5d96dd5b9a987f30f65d8d779264a3bcee6bef50b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0759974667511083,
+  "epoch": 0.1013299556681444,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 9.74,
       "eval_steps_per_second": 4.899,
       "step": 15
+    },
+    {
+      "epoch": 0.08106396453451552,
+      "grad_norm": 0.8417478203773499,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0254,
+      "step": 16
+    },
+    {
+      "epoch": 0.08613046231792273,
+      "grad_norm": 1.9363985061645508,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.1866,
+      "step": 17
+    },
+    {
+      "epoch": 0.09119696010132995,
+      "grad_norm": 1.8391631841659546,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.1333,
+      "step": 18
+    },
+    {
+      "epoch": 0.09119696010132995,
+      "eval_loss": 0.12381552159786224,
+      "eval_runtime": 17.1973,
+      "eval_samples_per_second": 9.711,
+      "eval_steps_per_second": 4.884,
+      "step": 18
+    },
+    {
+      "epoch": 0.09626345788473717,
+      "grad_norm": 1.8057817220687866,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.1361,
+      "step": 19
+    },
+    {
+      "epoch": 0.1013299556681444,
+      "grad_norm": 1.080073595046997,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0566,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.98328235065344e+16,
+  "total_flos": 2.64437646753792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null