Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5a0ad7a4a75d7fa6f6384e2070738c1b462ff380b648a11bce5e9bc8fab545
+oid sha256:cb93ba159817aebca63182f5ae5936a739d2bee6934aea1cdf57449db13f2b35
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d17b129093ff55159a9025cfa1262c6641dba04e6ecbe818780e4e2f9529c27
+oid sha256:a3cea667c401ae2c853e24f8b22de9cf6aedb7bbd7ef97270d3f6f84d690036d
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c51036317a763c4852293ce56ccc83db4ad0fada6d0a3ec596ca30c09a83d490
+oid sha256:065a20972fa16b73c744b52eb7217fc9685e1f23e9e97762f04b6a0e2253034d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4918032786885246,
+  "epoch": 0.5901639344262295,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 15.4,
       "eval_steps_per_second": 2.0,
       "step": 45
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 1.3024663925170898,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 7.5219,
+      "step": 48
+    },
+    {
+      "epoch": 0.5573770491803278,
+      "grad_norm": 1.4016789197921753,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 7.6823,
+      "step": 51
+    },
+    {
+      "epoch": 0.5901639344262295,
+      "grad_norm": 1.232653260231018,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 7.2973,
+      "step": 54
+    },
+    {
+      "epoch": 0.5901639344262295,
+      "eval_loss": 1.835157871246338,
+      "eval_runtime": 10.0097,
+      "eval_samples_per_second": 15.385,
+      "eval_steps_per_second": 1.998,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.946469637318246e+16,
+  "total_flos": 7.122694400743834e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null