Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be24595f395d6d7765b183cee728d32b99840ca658f833d978fbca9992e57443
+oid sha256:8a71c8735bd9e7e8650ab472872bc03533cf2fecd65580f720033abce76c7adc
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05dbce7a9d7ae90a85c0d67ff88f07df7765396114ea175afbd14fab53521aa9
+oid sha256:566f270553bc454a0207d4a06bc142023c30ab6124e70d708df2f6753aa58abf
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b7301b55f4200431b8f881fd811396c2c4c7720f4ffee7df493010f2c2f506
+oid sha256:42b414c8ef6e9245bee4c2cd8d344348d2e648da20b563df8113241485402611
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15070643642072212,
+  "epoch": 0.30141287284144425,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 2.763,
       "eval_steps_per_second": 1.382,
       "step": 9
+    },
+    {
+      "epoch": 0.20094191522762953,
+      "grad_norm": 40.06981658935547,
+      "learning_rate": 0.00012,
+      "loss": 12.9041,
+      "step": 12
+    },
+    {
+      "epoch": 0.25117739403453687,
+      "grad_norm": 18.526214599609375,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.4587,
+      "step": 15
+    },
+    {
+      "epoch": 0.30141287284144425,
+      "grad_norm": 26.23703384399414,
+      "learning_rate": 0.00018,
+      "loss": 6.8537,
+      "step": 18
+    },
+    {
+      "epoch": 0.30141287284144425,
+      "eval_loss": 0.16974753141403198,
+      "eval_runtime": 73.0714,
+      "eval_samples_per_second": 2.764,
+      "eval_steps_per_second": 1.382,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.733194298248397e+16,
+  "total_flos": 9.466388596496794e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null