Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec7cf387be58928af20b1c14d447112e492eca8ed0a2518bc379fecdd0b99a4
+oid sha256:f4fb448f9d1a03951ffc4b6e1eed40a60b40cd1c0a8bd25d0d01a8549ea89d33
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6064881d792bc71625312f8d9664b46a2cd969dfbb8e60aab57f5270016007
+oid sha256:2ae6fb30012b99bcc88a881dc16bebbafc840b1202aa241bc31a47acad3234e5
 size 136814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
+oid sha256:eed7443db706351be6dd27431c0a74aab9cc8fb80aac1c56005e8e16b28688cb
 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": 0.0017062298718194808,
+  "epoch": 0.0025593448077292215,
   "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": 88.879,
       "eval_steps_per_second": 44.44,
       "step": 20
+    },
+    {
+      "epoch": 0.001791541365410455,
+      "grad_norm": 0.6076815128326416,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 44.3081,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020474758461833773,
+      "grad_norm": 0.539865255355835,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 44.3182,
+      "step": 24
+    },
+    {
+      "epoch": 0.002132787339774351,
+      "eval_loss": 11.077737808227539,
+      "eval_runtime": 55.587,
+      "eval_samples_per_second": 88.798,
+      "eval_steps_per_second": 44.399,
+      "step": 25
+    },
+    {
+      "epoch": 0.0023034103269562994,
+      "grad_norm": 0.5873799920082092,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 44.31,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025593448077292215,
+      "grad_norm": 0.4953111410140991,
+      "learning_rate": 0.0,
+      "loss": 44.3161,
+      "step": 30
+    },
+    {
+      "epoch": 0.0025593448077292215,
+      "eval_loss": 11.07754135131836,
+      "eval_runtime": 55.5375,
+      "eval_samples_per_second": 88.877,
+      "eval_steps_per_second": 44.438,
+      "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": 40241725440.0,
+  "total_flos": 58958807040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null