Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95574d62b2bcdc99e0660cb485adcfaee62e8e031597720db977f50bc89bd916
+oid sha256:3ffbf107e0d54d7e272e64d8988cfba04a7ce8c8d983ebf74ba4a34cb0ada3bf
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed12083c06ea93141288c04f10f3519b6141aec1762e55477422d042a8bab1b3
+oid sha256:03da878531f641f0ce813e8638abf7808e72a7118da75997b16b99fbf684faae
 size 61226900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d0c58e73d020765517414900d2e86c4676d7790f193107286e69f87a07bbef
+oid sha256:21b469ef981b368f3e75b2eb64f35da11e295364d6412509237dd45ef1384a1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0555555555555556,
+  "epoch": 1.1608187134502923,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 10.472,
       "eval_steps_per_second": 1.309,
       "step": 90
+    },
+    {
+      "epoch": 1.090643274853801,
+      "grad_norm": 0.44458574056625366,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 4.9056,
+      "step": 93
+    },
+    {
+      "epoch": 1.1257309941520468,
+      "grad_norm": 0.47579580545425415,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.9345,
+      "step": 96
+    },
+    {
+      "epoch": 1.1608187134502923,
+      "grad_norm": 0.508492648601532,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 5.1551,
+      "step": 99
+    },
+    {
+      "epoch": 1.1608187134502923,
+      "eval_loss": 1.327457308769226,
+      "eval_runtime": 13.7559,
+      "eval_samples_per_second": 10.468,
+      "eval_steps_per_second": 1.309,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.327975769309184e+17,
+  "total_flos": 1.4607733462401024e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null