Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3735de88806029eb6a64f359a71dfa113c7ca43bddbfa5e2795dfecdd99036
+oid sha256:26f08dc26a19449309abc5d4a24e01b72b778b017289c841b0a98363989e9b54
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366585fa8ed7d98b5155543da4333802aee52b2b21c27fe14326f35e151ca378
+oid sha256:ebb96381a2a1bfa26198f730dd894b2e2b3b586a69610c0bfb994e0ad85378d0
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a85c0d761ee51f4bf8753893ad4124fdfc0c0156b12ff37487ff5cf9e94cc2
+oid sha256:7e68e8c94436fb2c4e62dfaf4244245a7868bbeda6394da760b25601ca859df3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003806080213140492,
+  "epoch": 0.005709120319710738,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 4.5092,
       "step": 18
+    },
+    {
+      "epoch": 0.0039963842237975165,
+      "grad_norm": 10.855512619018555,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.3654,
+      "step": 21
+    },
+    {
+      "epoch": 0.0045672962557685905,
+      "grad_norm": 3.5917742252349854,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.9673,
+      "step": 24
+    },
+    {
+      "epoch": 0.0045672962557685905,
+      "eval_loss": 3.9958908557891846,
+      "eval_runtime": 51.1395,
+      "eval_samples_per_second": 43.274,
+      "eval_steps_per_second": 21.647,
+      "step": 24
+    },
+    {
+      "epoch": 0.005138208287739664,
+      "grad_norm": 4.35882043838501,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.8858,
+      "step": 27
+    },
+    {
+      "epoch": 0.005709120319710738,
+      "grad_norm": 2.9137649536132812,
+      "learning_rate": 0.0,
+      "loss": 3.7191,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1029368772034560.0,
+  "total_flos": 1544053158051840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null