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:c277c6a474db1d0e66cd4ff4231f78c23eadd042d194ff04ec74b7862101f360
+oid sha256:ae3c02c479e88b8957e7370f92cee0452ab2034a79f77d06db8067909b217dd2
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cece15272ccd22514d72108df25c1a83b32fd016f2392b0d29aff83a87871df
+oid sha256:eb7b0bbe3f6e745f3727c758238cbf475e26df982a7fa9d154bfe042022cf6ec
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f080030f5b286f1e7bfc110f7d762d403e1cf123e63a139a735a46e59a30a720
+oid sha256:53ec0c08396b20e23d59c3ef1f065270b4621099f93ba0a1351d46f5ea61fcf9
 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": 0.049049662783568364,
+  "epoch": 0.07357449417535254,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 249.923,
       "eval_steps_per_second": 124.962,
       "step": 20
+    },
+    {
+      "epoch": 0.05150214592274678,
+      "grad_norm": 1.1043449640274048,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 44.2863,
+      "step": 21
+    },
+    {
+      "epoch": 0.05885959534028203,
+      "grad_norm": 1.0619176626205444,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 44.2996,
+      "step": 24
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "eval_loss": 11.062753677368164,
+      "eval_runtime": 0.6727,
+      "eval_samples_per_second": 255.701,
+      "eval_steps_per_second": 127.85,
+      "step": 25
+    },
+    {
+      "epoch": 0.06621704475781728,
+      "grad_norm": 1.1007205247879028,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 44.2594,
+      "step": 27
+    },
+    {
+      "epoch": 0.07357449417535254,
+      "grad_norm": 1.1125785112380981,
+      "learning_rate": 0.0,
+      "loss": 44.2477,
+      "step": 30
+    },
+    {
+      "epoch": 0.07357449417535254,
+      "eval_loss": 11.061006546020508,
+      "eval_runtime": 0.6899,
+      "eval_samples_per_second": 249.323,
+      "eval_steps_per_second": 124.661,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 421190959104.0,
+  "total_flos": 634386382848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null