Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf3b554a722161d949f66405978a8112bd762c52b942d8b436544e3dad153d9
+oid sha256:c465b0e3b15658575943591e823cbcdecd76aced8e5b9eb3b46fb7c3e5f89def
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9659418d3605e5b40babd95284fbf5ec8686f8df71e70dc60388ce063f42d584
+oid sha256:38b8f98710483c8d3cd51b5ea223c460194d9ac7e6e5c31f0946ed657c6a258f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f121b3f8e6b3ed310c94a49893eb97a3ee7cfc910bf43c67bb9322868d758fd
+oid sha256:49b94774303e58a13c6692326b1b2c8587483979f24ee2e9470fb045acc1a400
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005988472191032263,
+  "epoch": 0.007186166629238716,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,42 @@
       "eval_samples_per_second": 8.467,
       "eval_steps_per_second": 8.467,
       "step": 20
+    },
+    {
+      "epoch": 0.006287895800583876,
+      "grad_norm": 18.60074806213379,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 4.4333,
+      "step": 21
+    },
+    {
+      "epoch": 0.006587319410135489,
+      "grad_norm": 15.545724868774414,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 3.6316,
+      "step": 22
+    },
+    {
+      "epoch": 0.0068867430196871025,
+      "grad_norm": 23.216941833496094,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 3.2189,
+      "step": 23
+    },
+    {
+      "epoch": 0.007186166629238716,
+      "grad_norm": 16.716583251953125,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 3.0378,
+      "step": 24
+    },
+    {
+      "epoch": 0.007186166629238716,
+      "eval_loss": 3.7071402072906494,
+      "eval_runtime": 83.2372,
+      "eval_samples_per_second": 8.458,
+      "eval_steps_per_second": 8.458,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -214,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 8902647402725376.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null