Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481085b30ee5f927e5d704c8be51232c281acadaff66ec75c1d803f9bc7c8170
+oid sha256:9a0fcb339befae292cd96ff9dfb7bea0bc15d956ffc71dbf01eafed3c443e3c0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d888cd77035d979c264d5ab1c8985f720c8bf79f7b0aa583e21d9b1a3d22a2
+oid sha256:91e591e1d82b0782792a4c27bf347ad990c411c790b8503658b42ea632a06a6f
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb96bfb54c19a1842e34c0c48be90df061af9551eacf6da39e5338cc5990279
+oid sha256:71cddd6c4ff643d7889f00bac1c58dd1b0b622d1a22609d3502d45129df9795c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00045391959570894675,
+  "epoch": 0.000605226127611929,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 16.417,
       "eval_steps_per_second": 8.208,
       "step": 15
+    },
+    {
+      "epoch": 0.0004841809020895432,
+      "grad_norm": 7.714522838592529,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 9.9248,
+      "step": 16
+    },
+    {
+      "epoch": 0.0005144422084701396,
+      "grad_norm": 7.84112024307251,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.7425,
+      "step": 17
+    },
+    {
+      "epoch": 0.0005447035148507362,
+      "grad_norm": 6.446829319000244,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.3292,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005749648212313326,
+      "grad_norm": 7.735879421234131,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 10.3231,
+      "step": 19
+    },
+    {
+      "epoch": 0.000605226127611929,
+      "grad_norm": 6.886676788330078,
+      "learning_rate": 0.0,
+      "loss": 9.9093,
+      "step": 20
+    },
+    {
+      "epoch": 0.000605226127611929,
+      "eval_loss": 2.6602911949157715,
+      "eval_runtime": 843.1817,
+      "eval_samples_per_second": 16.502,
+      "eval_steps_per_second": 8.251,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4900984832655360.0,
+  "total_flos": 6534646443540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null